diff --git a/examples/common-ggml.cpp b/examples/common-ggml.cpp index 53811ad19..cf2478f0a 100644 --- a/examples/common-ggml.cpp +++ b/examples/common-ggml.cpp @@ -90,8 +90,6 @@ bool ggml_common_quantize_0( std::vector data_f16; std::vector data_f32; - std::vector hist_all(1 << 4, 0); - while (true) { int32_t n_dims; int32_t length; @@ -176,8 +174,6 @@ bool ggml_common_quantize_0( work.resize(nelements); // for quantization size_t cur_size = 0; - std::vector hist_cur(1 << 4, 0); - switch ((ggml_type) ttype) { case GGML_TYPE_Q4_0: case GGML_TYPE_Q4_1: @@ -190,7 +186,7 @@ bool ggml_common_quantize_0( case GGML_TYPE_Q5_K: case GGML_TYPE_Q6_K: { - cur_size = ggml_quantize_chunk((ggml_type) ttype, data_f32.data(), work.data(), 0, nelements/ne[0], ne[0], hist_cur.data(), nullptr); + cur_size = ggml_quantize_chunk((ggml_type) ttype, data_f32.data(), work.data(), 0, nelements/ne[0], ne[0], nullptr); } break; case GGML_TYPE_F32: case GGML_TYPE_F16: @@ -217,15 +213,7 @@ bool ggml_common_quantize_0( fout.write(reinterpret_cast(work.data()), cur_size); total_size_new += cur_size; - printf("size = %8.2f MB -> %8.2f MB | hist: ", nelements * sizeof(float)/1024.0/1024.0, cur_size/1024.0/1024.0); - for (int i = 0; i < (int) hist_cur.size(); ++i) { - hist_all[i] += hist_cur[i]; - } - - for (int i = 0; i < (int) hist_cur.size(); ++i) { - printf("%5.3f ", hist_cur[i] / (float)nelements); - } - printf("\n"); + printf("size = %8.2f MB -> %8.2f MB\n", nelements * sizeof(float)/1024.0/1024.0, cur_size/1024.0/1024.0); } else { printf("size = %8.3f MB\n", data_u8.size()/1024.0/1024.0); fout.write(reinterpret_cast(data_u8.data()), data_u8.size()); @@ -238,18 +226,5 @@ bool ggml_common_quantize_0( printf("%s: model size = %8.2f MB\n", __func__, total_size_org/1024.0/1024.0); printf("%s: quant size = %8.2f MB | ftype = %d (%s)\n", __func__, total_size_new/1024.0/1024.0, ftype, ggml_type_name(qtype)); - { - int64_t sum_all = 0; - for (int i = 0; i < (int) hist_all.size(); ++i) { - sum_all += hist_all[i]; - } - - printf("%s: hist: ", __func__); - for (int i = 0; i < (int) hist_all.size(); ++i) { - printf("%5.3f ", hist_all[i] / (float)sum_all); - } - printf("\n"); - } - return true; } diff --git a/examples/gpt-2/main-batched.cpp b/examples/gpt-2/main-batched.cpp index 6ad1838b7..9ba4496cf 100644 --- a/examples/gpt-2/main-batched.cpp +++ b/examples/gpt-2/main-batched.cpp @@ -419,21 +419,19 @@ bool gpt2_model_load(const std::string & fname, gpt2_model & model, gpt_vocab & // allocate the tensors into the backend buffer { - ggml_tallocr * alloc = ggml_tallocr_new(model.kv_cache.buffer); + ggml_tallocr alloc = ggml_tallocr_new(model.kv_cache.buffer); // this updates the pointers in the tensors to point to the correct location in the buffer // this is necessary since the ggml_context is .no_alloc == true // note that the buffer can actually be a device buffer, depending on the backend - ggml_tallocr_alloc(alloc, model.kv_cache.k); - ggml_tallocr_alloc(alloc, model.kv_cache.v); - - ggml_tallocr_free(alloc); + ggml_tallocr_alloc(&alloc, model.kv_cache.k); + ggml_tallocr_alloc(&alloc, model.kv_cache.v); } } // load weights { - ggml_tallocr * alloc = ggml_tallocr_new(model.buffer_w); + ggml_tallocr alloc = ggml_tallocr_new(model.buffer_w); size_t total_size = 0; @@ -495,7 +493,7 @@ bool gpt2_model_load(const std::string & fname, gpt2_model & model, gpt_vocab & return false; } - ggml_tallocr_alloc(alloc, tensor); + ggml_tallocr_alloc(&alloc, tensor); if (ggml_backend_is_cpu (model.backend) #ifdef GGML_USE_METAL @@ -525,7 +523,6 @@ bool gpt2_model_load(const std::string & fname, gpt2_model & model, gpt_vocab & total_size += ggml_nbytes(tensor); } - ggml_tallocr_free(alloc); printf("%s: model size = %8.2f MB\n", __func__, total_size/1024.0/1024.0); } diff --git a/examples/gpt-2/main-sched.cpp b/examples/gpt-2/main-sched.cpp index e753d5fb3..ad10aa961 100644 --- a/examples/gpt-2/main-sched.cpp +++ b/examples/gpt-2/main-sched.cpp @@ -342,7 +342,7 @@ bool gpt2_model_load(const std::string & fname, gpt2_model & model, gpt_vocab & } // allocate buffers - std::map> backend_buffers; + std::map backend_buffers; for (auto backend : model.backends) { // compute the size of the buffer size_t size = 0; @@ -359,7 +359,7 @@ bool gpt2_model_load(const std::string & fname, gpt2_model & model, gpt_vocab & model.buffers_w.push_back(buffer); // create an allocator for the buffer to allocate the tensors - auto alloc = std::unique_ptr(ggml_tallocr_new(buffer), ggml_tallocr_free); + auto alloc = ggml_tallocr_new(buffer); backend_buffers.insert(std::make_pair(backend, std::move(alloc))); } else { model.buffers_w.push_back(NULL); @@ -394,15 +394,13 @@ bool gpt2_model_load(const std::string & fname, gpt2_model & model, gpt_vocab & // allocate the tensors into the backend buffer { - ggml_tallocr * alloc = ggml_tallocr_new(model.buffer_kv); + ggml_tallocr alloc = ggml_tallocr_new(model.buffer_kv); // this updates the pointers in the tensors to point to the correct location in the buffer // this is necessary since the ggml_context is .no_alloc == true // note that the buffer can actually be a device buffer, depending on the backend - ggml_tallocr_alloc(alloc, model.memory_k); - ggml_tallocr_alloc(alloc, model.memory_v); - - ggml_tallocr_free(alloc); + ggml_tallocr_alloc(&alloc, model.memory_k); + ggml_tallocr_alloc(&alloc, model.memory_v); } } @@ -470,7 +468,7 @@ bool gpt2_model_load(const std::string & fname, gpt2_model & model, gpt_vocab & // allocate the tensor ggml_backend_t backend = tensor_backends[name]; - ggml_tallocr * alloc = backend_buffers.find(backend)->second.get(); + ggml_tallocr * alloc = &backend_buffers.find(backend)->second; ggml_tallocr_alloc(alloc, tensor); //printf("%s: [%5.5s] %s\n", __func__, ggml_backend_name(backend), name.c_str()); @@ -490,7 +488,8 @@ bool gpt2_model_load(const std::string & fname, gpt2_model & model, gpt_vocab & // GPT-2 models share the WTE tensor as the LM head if (name == "model/wte" && has_lm_head == false) { - ggml_tallocr_alloc(backend_buffers.find(tensor_backends["model/lm_head"])->second.get(), model.lm_head); + ggml_tallocr * alloc_head = &backend_buffers.find(tensor_backends["model/lm_head"])->second; + ggml_tallocr_alloc(alloc_head, model.lm_head); //printf("%s: [%5.5s] %s (copied)\n", __func__, ggml_backend_name(tensor_backends["model/lm_head"]), "model/lm_head"); ggml_backend_tensor_copy(tensor, model.lm_head); total_size += ggml_nbytes(model.lm_head); @@ -524,10 +523,9 @@ bool gpt2_model_load(const std::string & fname, gpt2_model & model, gpt_vocab & printf("%s: backend_in = %s (%zu bytes)\n", __func__, ggml_backend_name(backend_input), input_size); // allocate the tensors into the backend buffer - ggml_tallocr * alloc = ggml_tallocr_new(model.buffer_input); - ggml_tallocr_alloc(alloc, model.embd); - ggml_tallocr_alloc(alloc, model.position); - ggml_tallocr_free(alloc); + ggml_tallocr alloc = ggml_tallocr_new(model.buffer_input); + ggml_tallocr_alloc(&alloc, model.embd); + ggml_tallocr_alloc(&alloc, model.position); } return true; @@ -867,6 +865,7 @@ bool gpt2_eval( struct ggml_cgraph * gf = gpt2_graph(model, n_past, embd_inp); // run the computation + ggml_backend_sched_reset(sched); ggml_backend_sched_graph_compute(sched, gf); //if (n_past%100 == 0) { @@ -934,7 +933,7 @@ int main(int argc, char ** argv) { ggml_backend_sched_t sched; { // initialize the scheduler - sched = ggml_backend_sched_new(model.backends.data(), NULL, model.backends.size(), GPT2_MAX_NODES); + sched = ggml_backend_sched_new(model.backends.data(), NULL, model.backends.size(), GPT2_MAX_NODES, false); // create the worst case graph for memory usage estimation int n_tokens = std::min(model.hparams.n_ctx, params.n_batch); diff --git a/ggml-common.h b/ggml-common.h new file mode 100644 index 000000000..0257c928c --- /dev/null +++ b/ggml-common.h @@ -0,0 +1,1830 @@ +#ifndef GGML_COMMON_DECL + +#if defined(GGML_COMMON_DECL_C) +#include + +typedef uint16_t ggml_half; +typedef uint32_t ggml_half2; + +#define GGML_COMMON_AGGR + +#define GGML_COMMON_DECL +#elif defined(GGML_COMMON_DECL_METAL) +#include + +typedef half ggml_half; +typedef half2 ggml_half2; + +#define GGML_COMMON_AGGR + +#define GGML_COMMON_DECL +#elif defined(GGML_COMMON_DECL_CUDA) +#include +#include + +typedef half ggml_half; +typedef half2 ggml_half2; + +#define GGML_COMMON_AGGR data + +#define GGML_COMMON_DECL +#elif defined(GGML_COMMON_DECL_HIP) +#include +#include + +typedef half ggml_half; +typedef half2 ggml_half2; + +#define GGML_COMMON_AGGR data + +#define GGML_COMMON_DECL +#elif defined(GGML_COMMON_DECL_SYCL) +#include +#include + +typedef sycl::half ggml_half; +typedef sycl::half2 ggml_half2; + +#define GGML_COMMON_AGGR data + +#define GGML_COMMON_DECL +#endif + +#if defined(GGML_COMMON_DECL) + +#ifndef __cplusplus +#ifndef static_assert +#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 201100L) +#define static_assert(cond, msg) _Static_assert(cond, msg) +#else +#define static_assert(cond, msg) struct global_scope_noop_trick +#endif +#endif +#endif // __cplusplus + +// QK = number of values after dequantization +// QK_K = super-block size + +#ifdef GGML_QKK_64 +#define QK_K 64 +#define K_SCALE_SIZE 4 +#else +#define QK_K 256 +#define K_SCALE_SIZE 12 +#endif // GGML_QKK_64 + +#if defined(GGML_COMMON_DECL_CUDA) || defined(GGML_COMMON_DECL_HIP) || defined(GGML_COMMON_DECL_SYCL) +// QR = QK / number of values before dequantization +// QI = number of 32 bit integers before dequantization + +#define QI4_0 (QK4_0 / (4 * QR4_0)) +#define QR4_0 2 + +#define QI4_1 (QK4_1 / (4 * QR4_1)) +#define QR4_1 2 + +#define QI5_0 (QK5_0 / (4 * QR5_0)) +#define QR5_0 2 + +#define QI5_1 (QK5_1 / (4 * QR5_1)) +#define QR5_1 2 + +#define QI8_0 (QK8_0 / (4 * QR8_0)) +#define QR8_0 1 + +#define QI8_1 (QK8_1 / (4 * QR8_1)) +#define QR8_1 1 + +#define QI2_K (QK_K / (4*QR2_K)) +#define QR2_K 4 + +#define QI3_K (QK_K / (4*QR3_K)) +#define QR3_K 4 + +#define QI4_K (QK_K / (4*QR4_K)) +#define QR4_K 2 + +#define QI5_K (QK_K / (4*QR5_K)) +#define QR5_K 2 + +#define QI6_K (QK_K / (4*QR6_K)) +#define QR6_K 2 + +#define QI2_XXS (QK_K / (4*QR2_XXS)) +#define QR2_XXS 8 + +#define QI2_XS (QK_K / (4*QR2_XS)) +#define QR2_XS 8 + +#define QI2_S (QK_K / (4*QR2_S)) +#define QR2_S 8 + +#define QI3_XXS (QK_K / (4*QR3_XXS)) +#define QR3_XXS 8 + +#define QI3_XS (QK_K / (4*QR3_XS)) +#define QR3_XS 8 + +#define QI1_S (QK_K / (4*QR1_S)) +#define QR1_S 8 + +#define QI4_NL (QK4_NL / (4*QR4_NL)) +#define QR4_NL 2 + +#if QK_K == 64 +#define QI4_XS QI4_NL +#define QR4_XS QR4_NL +#else +#define QI4_XS (QK_K / (4*QR4_XS)) +#define QR4_XS 8 +#endif + +#endif // GGML_COMMON_DECL_CUDA || GGML_COMMON_DECL_HIP + +#define QK4_0 32 +typedef struct { + ggml_half d; // delta + uint8_t qs[QK4_0 / 2]; // nibbles / quants +} block_q4_0; +static_assert(sizeof(block_q4_0) == sizeof(ggml_half) + QK4_0 / 2, "wrong q4_0 block size/padding"); + +#define QK4_1 32 +typedef struct { + union { + struct { + ggml_half d; // delta + ggml_half m; // min + } GGML_COMMON_AGGR; + ggml_half2 dm; + }; + uint8_t qs[QK4_1 / 2]; // nibbles / quants +} block_q4_1; +static_assert(sizeof(block_q4_1) == 2 * sizeof(ggml_half) + QK4_1 / 2, "wrong q4_1 block size/padding"); + +#define QK5_0 32 +typedef struct { + ggml_half d; // delta + uint8_t qh[4]; // 5-th bit of quants + uint8_t qs[QK5_0 / 2]; // nibbles / quants +} block_q5_0; +static_assert(sizeof(block_q5_0) == sizeof(ggml_half) + sizeof(uint32_t) + QK5_0 / 2, "wrong q5_0 block size/padding"); + +#define QK5_1 32 +typedef struct { + union { + struct { + ggml_half d; // delta + ggml_half m; // min + } GGML_COMMON_AGGR; + ggml_half2 dm; + }; + uint8_t qh[4]; // 5-th bit of quants + uint8_t qs[QK5_1 / 2]; // nibbles / quants +} block_q5_1; +static_assert(sizeof(block_q5_1) == 2 * sizeof(ggml_half) + sizeof(uint32_t) + QK5_1 / 2, "wrong q5_1 block size/padding"); + +#define QK8_0 32 +typedef struct { + ggml_half d; // delta + int8_t qs[QK8_0]; // quants +} block_q8_0; +static_assert(sizeof(block_q8_0) == sizeof(ggml_half) + QK8_0, "wrong q8_0 block size/padding"); + +#define QK8_1 32 +typedef struct { + union { + struct { + ggml_half d; // delta + ggml_half s; // d * sum(qs[i]) + } GGML_COMMON_AGGR; + ggml_half2 ds; + }; + int8_t qs[QK8_1]; // quants +} block_q8_1; +static_assert(sizeof(block_q8_1) == 2*sizeof(ggml_half) + QK8_1, "wrong q8_1 block size/padding"); + +// +// Super-block quantization structures +// + +// 2-bit quantization +// weight is represented as x = a * q + b +// 16 blocks of 16 elements each +// Effectively 2.625 bits per weight +typedef struct { + uint8_t scales[QK_K/16]; // scales and mins, quantized with 4 bits + uint8_t qs[QK_K/4]; // quants + union { + struct { + ggml_half d; // super-block scale for quantized scales + ggml_half dmin; // super-block scale for quantized mins + } GGML_COMMON_AGGR; + ggml_half2 dm; + }; +} block_q2_K; +static_assert(sizeof(block_q2_K) == 2*sizeof(ggml_half) + QK_K/16 + QK_K/4, "wrong q2_K block size/padding"); + +// 3-bit quantization +// weight is represented as x = a * q +// 16 blocks of 16 elements each +// Effectively 3.4375 bits per weight +#ifdef GGML_QKK_64 +typedef struct { + uint8_t hmask[QK_K/8]; // quants - high bit + uint8_t qs[QK_K/4]; // quants - low 2 bits + uint8_t scales[2]; + ggml_half d; // super-block scale +} block_q3_K; +static_assert(sizeof(block_q3_K) == sizeof(ggml_half) + QK_K / 4 + QK_K / 8 + 2, "wrong q3_K block size/padding"); +#else +typedef struct { + uint8_t hmask[QK_K/8]; // quants - high bit + uint8_t qs[QK_K/4]; // quants - low 2 bits + uint8_t scales[12]; // scales, quantized with 6 bits + ggml_half d; // super-block scale +} block_q3_K; +static_assert(sizeof(block_q3_K) == sizeof(ggml_half) + QK_K / 4 + QK_K / 8 + 12, "wrong q3_K block size/padding"); +#endif + +// 4-bit quantization +// 8 blocks of 32 elements each +// weight is represented as x = a * q + b +// Effectively 4.5 bits per weight +#ifdef GGML_QKK_64 +typedef struct { + ggml_half d[2]; // super-block scales/mins + uint8_t scales[2]; // 4-bit block scales/mins + uint8_t qs[QK_K/2]; // 4--bit quants +} block_q4_K; +static_assert(sizeof(block_q4_K) == 2*sizeof(ggml_half) + QK_K/2 + 2, "wrong q4_K block size/padding"); +#else +typedef struct { + union { + struct { + ggml_half d; // super-block scale for quantized scales + ggml_half dmin; // super-block scale for quantized mins + } GGML_COMMON_AGGR; + ggml_half2 dm; + }; + uint8_t scales[K_SCALE_SIZE]; // scales and mins, quantized with 6 bits + uint8_t qs[QK_K/2]; // 4--bit quants +} block_q4_K; +static_assert(sizeof(block_q4_K) == 2*sizeof(ggml_half) + K_SCALE_SIZE + QK_K/2, "wrong q4_K block size/padding"); +#endif + +// 5-bit quantization +// 8 blocks of 32 elements each +// weight is represented as x = a * q + b +// Effectively 5.5 bits per weight +#ifdef GGML_QKK_64 +typedef struct { + ggml_half d; // super-block scale + int8_t scales[QK_K/16]; // 8-bit block scales + uint8_t qh[QK_K/8]; // quants, high bit + uint8_t qs[QK_K/2]; // quants, low 4 bits +} block_q5_K; +static_assert(sizeof(block_q5_K) == sizeof(ggml_half) + QK_K/2 + QK_K/8 + QK_K/16, "wrong q5_K block size/padding"); +#else +typedef struct { + union { + struct { + ggml_half d; // super-block scale for quantized scales + ggml_half dmin; // super-block scale for quantized mins + } GGML_COMMON_AGGR; + ggml_half2 dm; + }; + uint8_t scales[K_SCALE_SIZE]; // scales and mins, quantized with 6 bits + uint8_t qh[QK_K/8]; // quants, high bit + uint8_t qs[QK_K/2]; // quants, low 4 bits +} block_q5_K; +static_assert(sizeof(block_q5_K) == 2*sizeof(ggml_half) + K_SCALE_SIZE + QK_K/2 + QK_K/8, "wrong q5_K block size/padding"); +#endif + +// 6-bit quantization +// weight is represented as x = a * q +// 16 blocks of 16 elements each +// Effectively 6.5625 bits per weight +typedef struct { + uint8_t ql[QK_K/2]; // quants, lower 4 bits + uint8_t qh[QK_K/4]; // quants, upper 2 bits + int8_t scales[QK_K/16]; // scales, quantized with 8 bits + ggml_half d; // super-block scale +} block_q6_K; +static_assert(sizeof(block_q6_K) == sizeof(ggml_half) + QK_K / 16 + 3*QK_K/4, "wrong q6_K block size/padding"); + +// This is only used for intermediate quantization and dot products +typedef struct { + float d; // delta + int8_t qs[QK_K]; // quants + int16_t bsums[QK_K/16]; // sum of quants in groups of 16 +} block_q8_K; +static_assert(sizeof(block_q8_K) == sizeof(float) + QK_K + QK_K/16*sizeof(int16_t), "wrong q8_K block size/padding"); + +// (Almost) "true" 2-bit quantization. +// Due to the need to use blocks as per ggml design, it ends up using +// 2.0625 bpw because of the 16-bit scale for each block of 256. +typedef struct { + ggml_half d; + uint16_t qs[QK_K/8]; +} block_iq2_xxs; +static_assert(sizeof(block_iq2_xxs) == sizeof(ggml_half) + QK_K/8*sizeof(uint16_t), "wrong iq2_xxs block size/padding"); + +// 2.3125 bpw quants +typedef struct { + ggml_half d; + uint16_t qs[QK_K/8]; + uint8_t scales[QK_K/32]; +} block_iq2_xs; +static_assert(sizeof(block_iq2_xs) == sizeof(ggml_half) + QK_K/8*sizeof(uint16_t) + QK_K/32, "wrong iq2_xs block size/padding"); + +// 2.5625 bpw quants +typedef struct { + ggml_half d; + uint8_t qs[QK_K/4]; + uint8_t qh[QK_K/32]; + uint8_t scales[QK_K/32]; +} block_iq2_s; +static_assert(sizeof(block_iq2_s) == sizeof(ggml_half) + QK_K/4 + QK_K/16, "wrong iq2_s block size/padding"); + +// (Almost) "true" 3-bit quantization. +// Due to the need to use blocks as per ggml design, it ends up using +// 3.0625 bpw because of the 16-bit scale for each block of 256. +typedef struct { + ggml_half d; + uint8_t qs[3*QK_K/8]; +} block_iq3_xxs; +static_assert(sizeof(block_iq3_xxs) == sizeof(ggml_half) + 3*(QK_K/8), "wrong iq3_xxs block size/padding"); + +// 3.4375 bpw +#if QK_K == 64 +#define IQ3S_N_SCALE 2 +#else +#define IQ3S_N_SCALE QK_K/64 +#endif +typedef struct { + ggml_half d; + uint8_t qs[QK_K/4]; + uint8_t qh[QK_K/32]; + uint8_t signs[QK_K/8]; + uint8_t scales[IQ3S_N_SCALE]; +} block_iq3_s; +static_assert(sizeof(block_iq3_s) == sizeof(ggml_half) + 13*(QK_K/32) + IQ3S_N_SCALE, "wrong iq3_s block size/padding"); + +typedef struct { + ggml_half d; + uint8_t qs[QK_K/8]; + uint16_t qh[QK_K/32]; +} block_iq1_s; +static_assert(sizeof(block_iq1_s) == sizeof(ggml_half) + QK_K/8 + QK_K/16, "wrong iq1_s block size/padding"); + +// Non-linear quants +#define QK4_NL 32 +typedef struct { + ggml_half d; + uint8_t qs[QK4_NL/2]; +} block_iq4_nl; +static_assert(sizeof(block_iq4_nl) == sizeof(ggml_half) + QK4_NL/2, "wrong iq4_nl block size/padding"); + +#if QK_K == 64 +#define block_iq4_xs block_iq4_nl +#else +typedef struct { + ggml_half d; + uint16_t scales_h; + uint8_t scales_l[QK_K/64]; + uint8_t qs[QK_K/2]; +} block_iq4_xs; +static_assert(sizeof(block_iq4_xs) == sizeof(ggml_half) + sizeof(uint16_t) + QK_K/64 + QK_K/2, "wrong iq4_xs block size/padding"); +#endif + +#endif // GGML_COMMON_DECL +#endif // GGML_COMMON_DECL + +//////////////////////////////////////////////////////////////////////////////// + +#ifndef GGML_COMMON_IMPL + +#if defined(GGML_COMMON_IMPL_C) +#include + +#define GGML_TABLE_BEGIN(type, name, size) static const type name[size] = { +#define GGML_TABLE_END() }; + +#define GGML_COMMON_IMPL +#elif defined(GGML_COMMON_IMPL_METAL) +#include + +#define GGML_TABLE_BEGIN(type, name, size) static const constant type name[size] = { +#define GGML_TABLE_END() }; + +#define GGML_COMMON_IMPL +#elif defined(GGML_COMMON_IMPL_CUDA) || defined(GGML_COMMON_IMPL_HIP) +#include + +#define GGML_TABLE_BEGIN(type, name, size) static const __device__ type name[size] = { +#define GGML_TABLE_END() }; + +#define GGML_COMMON_IMPL +#elif defined(GGML_COMMON_IMPL_SYCL) +#include + +#define GGML_TABLE_BEGIN(type, name, size) static dpct::global_memory name(sycl::range<1>(size), { +#define GGML_TABLE_END() }); + +#define GGML_COMMON_IMPL +#endif + +#if defined(GGML_COMMON_IMPL) + +GGML_TABLE_BEGIN(uint8_t, kmask_iq2xs, 8) + 1, 2, 4, 8, 16, 32, 64, 128 +GGML_TABLE_END() + +GGML_TABLE_BEGIN(uint8_t, ksigns_iq2xs, 128) + 0, 129, 130, 3, 132, 5, 6, 135, 136, 9, 10, 139, 12, 141, 142, 15, + 144, 17, 18, 147, 20, 149, 150, 23, 24, 153, 154, 27, 156, 29, 30, 159, + 160, 33, 34, 163, 36, 165, 166, 39, 40, 169, 170, 43, 172, 45, 46, 175, + 48, 177, 178, 51, 180, 53, 54, 183, 184, 57, 58, 187, 60, 189, 190, 63, + 192, 65, 66, 195, 68, 197, 198, 71, 72, 201, 202, 75, 204, 77, 78, 207, + 80, 209, 210, 83, 212, 85, 86, 215, 216, 89, 90, 219, 92, 221, 222, 95, + 96, 225, 226, 99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111, + 240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255, +GGML_TABLE_END() + +//#if __CUDA_ARCH__ >= MIN_CC_DP4A // lowest compute capability for integer intrinsics +GGML_TABLE_BEGIN(uint64_t, ksigns64, 128) + 0x0000000000000000, 0xff000000000000ff, 0xff0000000000ff00, 0x000000000000ffff, + 0xff00000000ff0000, 0x0000000000ff00ff, 0x0000000000ffff00, 0xff00000000ffffff, + 0xff000000ff000000, 0x00000000ff0000ff, 0x00000000ff00ff00, 0xff000000ff00ffff, + 0x00000000ffff0000, 0xff000000ffff00ff, 0xff000000ffffff00, 0x00000000ffffffff, + 0xff0000ff00000000, 0x000000ff000000ff, 0x000000ff0000ff00, 0xff0000ff0000ffff, + 0x000000ff00ff0000, 0xff0000ff00ff00ff, 0xff0000ff00ffff00, 0x000000ff00ffffff, + 0x000000ffff000000, 0xff0000ffff0000ff, 0xff0000ffff00ff00, 0x000000ffff00ffff, + 0xff0000ffffff0000, 0x000000ffffff00ff, 0x000000ffffffff00, 0xff0000ffffffffff, + 0xff00ff0000000000, 0x0000ff00000000ff, 0x0000ff000000ff00, 0xff00ff000000ffff, + 0x0000ff0000ff0000, 0xff00ff0000ff00ff, 0xff00ff0000ffff00, 0x0000ff0000ffffff, + 0x0000ff00ff000000, 0xff00ff00ff0000ff, 0xff00ff00ff00ff00, 0x0000ff00ff00ffff, + 0xff00ff00ffff0000, 0x0000ff00ffff00ff, 0x0000ff00ffffff00, 0xff00ff00ffffffff, + 0x0000ffff00000000, 0xff00ffff000000ff, 0xff00ffff0000ff00, 0x0000ffff0000ffff, + 0xff00ffff00ff0000, 0x0000ffff00ff00ff, 0x0000ffff00ffff00, 0xff00ffff00ffffff, + 0xff00ffffff000000, 0x0000ffffff0000ff, 0x0000ffffff00ff00, 0xff00ffffff00ffff, + 0x0000ffffffff0000, 0xff00ffffffff00ff, 0xff00ffffffffff00, 0x0000ffffffffffff, + 0xffff000000000000, 0x00ff0000000000ff, 0x00ff00000000ff00, 0xffff00000000ffff, + 0x00ff000000ff0000, 0xffff000000ff00ff, 0xffff000000ffff00, 0x00ff000000ffffff, + 0x00ff0000ff000000, 0xffff0000ff0000ff, 0xffff0000ff00ff00, 0x00ff0000ff00ffff, + 0xffff0000ffff0000, 0x00ff0000ffff00ff, 0x00ff0000ffffff00, 0xffff0000ffffffff, + 0x00ff00ff00000000, 0xffff00ff000000ff, 0xffff00ff0000ff00, 0x00ff00ff0000ffff, + 0xffff00ff00ff0000, 0x00ff00ff00ff00ff, 0x00ff00ff00ffff00, 0xffff00ff00ffffff, + 0xffff00ffff000000, 0x00ff00ffff0000ff, 0x00ff00ffff00ff00, 0xffff00ffff00ffff, + 0x00ff00ffffff0000, 0xffff00ffffff00ff, 0xffff00ffffffff00, 0x00ff00ffffffffff, + 0x00ffff0000000000, 0xffffff00000000ff, 0xffffff000000ff00, 0x00ffff000000ffff, + 0xffffff0000ff0000, 0x00ffff0000ff00ff, 0x00ffff0000ffff00, 0xffffff0000ffffff, + 0xffffff00ff000000, 0x00ffff00ff0000ff, 0x00ffff00ff00ff00, 0xffffff00ff00ffff, + 0x00ffff00ffff0000, 0xffffff00ffff00ff, 0xffffff00ffffff00, 0x00ffff00ffffffff, + 0xffffffff00000000, 0x00ffffff000000ff, 0x00ffffff0000ff00, 0xffffffff0000ffff, + 0x00ffffff00ff0000, 0xffffffff00ff00ff, 0xffffffff00ffff00, 0x00ffffff00ffffff, + 0x00ffffffff000000, 0xffffffffff0000ff, 0xffffffffff00ff00, 0x00ffffffff00ffff, + 0xffffffffffff0000, 0x00ffffffffff00ff, 0x00ffffffffffff00, 0xffffffffffffffff, +GGML_TABLE_END() +//#endif + + +GGML_TABLE_BEGIN(uint64_t, iq2xxs_grid, 256) + 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, + 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808, + 0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819, + 0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819, + 0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b, + 0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808, + 0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08, + 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b, + 0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819, + 0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08, + 0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808, + 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08, + 0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808, + 0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808, + 0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919, + 0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819, + 0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08, + 0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908, + 0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819, + 0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808, + 0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808, + 0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908, + 0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808, + 0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08, + 0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819, + 0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819, + 0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819, + 0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908, + 0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19, + 0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819, + 0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b, + 0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808, + 0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908, + 0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08, + 0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08, + 0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908, + 0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819, + 0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808, + 0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808, + 0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19, + 0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819, + 0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, + 0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b, + 0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08, + 0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808, + 0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908, + 0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b, + 0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819, + 0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08, + 0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08, + 0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808, + 0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b, + 0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b, + 0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908, + 0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819, + 0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808, + 0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908, + 0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b, + 0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808, + 0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b, + 0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b, + 0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808, + 0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19, + 0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908, +GGML_TABLE_END() + +GGML_TABLE_BEGIN(uint64_t, iq2xs_grid, 512) + 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, + 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b, + 0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919, + 0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b, + 0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919, + 0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808, + 0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819, + 0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819, + 0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, + 0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b, + 0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b, + 0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908, + 0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908, + 0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919, + 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808, + 0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919, + 0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908, + 0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, + 0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, + 0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08, + 0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808, + 0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808, + 0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819, + 0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908, + 0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819, + 0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808, + 0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b, + 0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819, + 0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819, + 0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808, + 0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908, + 0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19, + 0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b, + 0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b, + 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919, + 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808, + 0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819, + 0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819, + 0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b, + 0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908, + 0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808, + 0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819, + 0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808, + 0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919, + 0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808, + 0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808, + 0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908, + 0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908, + 0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808, + 0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b, + 0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819, + 0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, + 0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908, + 0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808, + 0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908, + 0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919, + 0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08, + 0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19, + 0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b, + 0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b, + 0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808, + 0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08, + 0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b, + 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908, + 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b, + 0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908, + 0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, + 0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808, + 0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808, + 0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08, + 0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819, + 0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919, + 0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808, + 0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808, + 0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819, + 0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819, + 0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908, + 0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908, + 0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b, + 0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908, + 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908, + 0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908, + 0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808, + 0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, + 0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819, + 0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819, + 0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808, + 0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b, + 0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819, + 0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819, + 0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08, + 0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808, + 0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19, + 0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919, + 0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808, + 0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19, + 0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b, + 0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808, + 0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b, + 0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b, + 0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, + 0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b, + 0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808, + 0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819, + 0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808, + 0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808, + 0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08, + 0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b, + 0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19, + 0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08, + 0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919, + 0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08, + 0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08, + 0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908, + 0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908, + 0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b, + 0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908, + 0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808, + 0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b, + 0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808, + 0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808, + 0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19, + 0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08, + 0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808, + 0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b, + 0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808, + 0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b, + 0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b, +GGML_TABLE_END() + +GGML_TABLE_BEGIN(uint64_t, iq2s_grid, 1024) + 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, + 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b, + 0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919, + 0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b, + 0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919, + 0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x08080808192b192b, + 0x08080808192b2b19, 0x080808082b080808, 0x080808082b08082b, 0x080808082b081919, + 0x080808082b082b08, 0x080808082b190819, 0x080808082b191908, 0x080808082b2b0808, + 0x080808082b2b1919, 0x080808082b2b2b2b, 0x0808081908080819, 0x0808081908081908, + 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, 0x080808190819082b, + 0x0808081908191919, 0x0808081908192b08, 0x08080819082b0819, 0x08080819082b1908, + 0x0808081919080808, 0x080808191908082b, 0x0808081919081919, 0x0808081919082b08, + 0x0808081919190819, 0x0808081919191908, 0x080808191919192b, 0x0808081919192b19, + 0x08080819192b0808, 0x08080819192b1919, 0x08080819192b2b08, 0x080808192b080819, + 0x080808192b081908, 0x080808192b190808, 0x080808192b19082b, 0x080808192b191919, + 0x080808192b2b0819, 0x080808192b2b1908, 0x0808082b08080808, 0x0808082b0808082b, + 0x0808082b08081919, 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, + 0x0808082b082b0808, 0x0808082b082b2b2b, 0x0808082b19080819, 0x0808082b19081908, + 0x0808082b1908192b, 0x0808082b19082b19, 0x0808082b19190808, 0x0808082b19191919, + 0x0808082b2b080808, 0x0808082b2b081919, 0x0808082b2b082b2b, 0x0808082b2b191908, + 0x0808082b2b2b082b, 0x0808190808080819, 0x0808190808081908, 0x080819080808192b, + 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, 0x0808190808191919, + 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, 0x08081908082b192b, + 0x08081908082b2b19, 0x0808190819080808, 0x080819081908082b, 0x0808190819081919, + 0x0808190819082b08, 0x0808190819082b2b, 0x0808190819190819, 0x0808190819191908, + 0x080819081919192b, 0x0808190819192b19, 0x08081908192b0808, 0x08081908192b082b, + 0x08081908192b1919, 0x080819082b080819, 0x080819082b081908, 0x080819082b08192b, + 0x080819082b082b19, 0x080819082b190808, 0x080819082b191919, 0x080819082b192b08, + 0x080819082b2b0819, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, + 0x0808191908081919, 0x0808191908082b08, 0x0808191908082b2b, 0x0808191908190819, + 0x0808191908191908, 0x080819190819192b, 0x0808191908192b19, 0x08081919082b0808, + 0x08081919082b1919, 0x08081919082b2b08, 0x0808191919080819, 0x0808191919081908, + 0x080819191908192b, 0x0808191919082b19, 0x0808191919190808, 0x080819191919082b, + 0x0808191919191919, 0x0808191919192b08, 0x08081919192b0819, 0x08081919192b1908, + 0x080819192b080808, 0x080819192b08082b, 0x080819192b081919, 0x080819192b082b08, + 0x080819192b190819, 0x080819192b191908, 0x080819192b2b0808, 0x0808192b08080819, + 0x0808192b08081908, 0x0808192b0808192b, 0x0808192b08082b19, 0x0808192b08190808, + 0x0808192b08191919, 0x0808192b19080808, 0x0808192b19081919, 0x0808192b19082b08, + 0x0808192b19190819, 0x0808192b19191908, 0x0808192b192b0808, 0x0808192b2b080819, + 0x0808192b2b081908, 0x0808192b2b190808, 0x08082b0808080808, 0x08082b080808082b, + 0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808190819, 0x08082b0808191908, + 0x08082b080819192b, 0x08082b0808192b19, 0x08082b08082b0808, 0x08082b08082b1919, + 0x08082b08082b2b2b, 0x08082b0819080819, 0x08082b0819081908, 0x08082b081908192b, + 0x08082b0819082b19, 0x08082b0819190808, 0x08082b081919082b, 0x08082b0819191919, + 0x08082b0819192b08, 0x08082b08192b0819, 0x08082b08192b1908, 0x08082b082b080808, + 0x08082b082b081919, 0x08082b082b191908, 0x08082b082b2b2b2b, 0x08082b1908080819, + 0x08082b1908081908, 0x08082b1908190808, 0x08082b190819082b, 0x08082b1908191919, + 0x08082b1908192b08, 0x08082b19082b0819, 0x08082b1919080808, 0x08082b1919081919, + 0x08082b1919082b08, 0x08082b1919190819, 0x08082b1919191908, 0x08082b19192b0808, + 0x08082b192b080819, 0x08082b192b190808, 0x08082b2b08080808, 0x08082b2b08190819, + 0x08082b2b08191908, 0x08082b2b082b082b, 0x08082b2b082b2b08, 0x08082b2b082b2b2b, + 0x08082b2b19190808, 0x08082b2b2b192b19, 0x0819080808080819, 0x0819080808081908, + 0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, + 0x0819080808191919, 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, + 0x08190808082b192b, 0x0819080819080808, 0x081908081908082b, 0x0819080819081919, + 0x0819080819082b08, 0x0819080819190819, 0x0819080819191908, 0x081908081919192b, + 0x0819080819192b19, 0x08190808192b0808, 0x08190808192b082b, 0x08190808192b1919, + 0x08190808192b2b08, 0x081908082b080819, 0x081908082b081908, 0x081908082b08192b, + 0x081908082b190808, 0x081908082b191919, 0x081908082b192b08, 0x081908082b2b0819, + 0x081908082b2b1908, 0x0819081908080808, 0x081908190808082b, 0x0819081908081919, + 0x0819081908082b08, 0x0819081908082b2b, 0x0819081908190819, 0x0819081908191908, + 0x081908190819192b, 0x0819081908192b19, 0x08190819082b0808, 0x08190819082b082b, + 0x08190819082b1919, 0x08190819082b2b08, 0x0819081919080819, 0x0819081919081908, + 0x081908191908192b, 0x0819081919082b19, 0x0819081919190808, 0x081908191919082b, + 0x0819081919191919, 0x0819081919192b08, 0x08190819192b0819, 0x08190819192b1908, + 0x081908192b080808, 0x081908192b08082b, 0x081908192b081919, 0x081908192b082b08, + 0x081908192b190819, 0x081908192b191908, 0x0819082b08080819, 0x0819082b08081908, + 0x0819082b08082b19, 0x0819082b08190808, 0x0819082b08191919, 0x0819082b082b0819, + 0x0819082b082b1908, 0x0819082b19080808, 0x0819082b19081919, 0x0819082b19190819, + 0x0819082b19191908, 0x0819082b2b080819, 0x0819082b2b081908, 0x0819082b2b190808, + 0x0819190808080808, 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08, + 0x0819190808190819, 0x0819190808191908, 0x081919080819192b, 0x0819190808192b19, + 0x08191908082b0808, 0x08191908082b1919, 0x08191908082b2b08, 0x0819190819080819, + 0x0819190819081908, 0x081919081908192b, 0x0819190819082b19, 0x0819190819190808, + 0x081919081919082b, 0x0819190819191919, 0x0819190819192b08, 0x08191908192b0819, + 0x08191908192b1908, 0x081919082b080808, 0x081919082b08082b, 0x081919082b081919, + 0x081919082b082b08, 0x081919082b190819, 0x081919082b191908, 0x081919082b2b0808, + 0x0819191908080819, 0x0819191908081908, 0x081919190808192b, 0x0819191908082b19, + 0x0819191908190808, 0x081919190819082b, 0x0819191908191919, 0x0819191908192b08, + 0x08191919082b0819, 0x08191919082b1908, 0x0819191919080808, 0x081919191908082b, + 0x0819191919081919, 0x0819191919082b08, 0x0819191919190819, 0x0819191919191908, + 0x08191919192b0808, 0x081919192b080819, 0x081919192b081908, 0x081919192b190808, + 0x0819192b08080808, 0x0819192b08081919, 0x0819192b08082b08, 0x0819192b08190819, + 0x0819192b08191908, 0x0819192b082b0808, 0x0819192b19080819, 0x0819192b19081908, + 0x0819192b19190808, 0x0819192b2b080808, 0x0819192b2b2b2b2b, 0x08192b0808080819, + 0x08192b0808081908, 0x08192b080808192b, 0x08192b0808082b19, 0x08192b0808190808, + 0x08192b0808191919, 0x08192b0808192b08, 0x08192b08082b0819, 0x08192b0819080808, + 0x08192b081908082b, 0x08192b0819081919, 0x08192b0819082b08, 0x08192b0819190819, + 0x08192b0819191908, 0x08192b08192b0808, 0x08192b082b080819, 0x08192b082b081908, + 0x08192b1908080808, 0x08192b190808082b, 0x08192b1908081919, 0x08192b1908082b08, + 0x08192b1908190819, 0x08192b1908191908, 0x08192b19082b0808, 0x08192b1919080819, + 0x08192b1919081908, 0x08192b1919190808, 0x08192b19192b2b19, 0x08192b192b2b082b, + 0x08192b2b08081908, 0x08192b2b08190808, 0x08192b2b19080808, 0x08192b2b1919192b, + 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, 0x082b080808082b08, + 0x082b080808190819, 0x082b080808191908, 0x082b08080819192b, 0x082b080808192b19, + 0x082b0808082b0808, 0x082b0808082b1919, 0x082b0808082b2b2b, 0x082b080819080819, + 0x082b080819081908, 0x082b080819190808, 0x082b08081919082b, 0x082b080819191919, + 0x082b0808192b1908, 0x082b08082b080808, 0x082b08082b082b2b, 0x082b08082b191908, + 0x082b08082b2b2b2b, 0x082b081908080819, 0x082b081908081908, 0x082b081908190808, + 0x082b08190819082b, 0x082b081908191919, 0x082b0819082b0819, 0x082b081919080808, + 0x082b08191908082b, 0x082b081919081919, 0x082b081919190819, 0x082b081919191908, + 0x082b0819192b0808, 0x082b08192b080819, 0x082b08192b081908, 0x082b08192b190808, + 0x082b082b08080808, 0x082b082b08082b2b, 0x082b082b082b082b, 0x082b082b082b2b08, + 0x082b082b082b2b2b, 0x082b082b19081908, 0x082b082b19190808, 0x082b082b2b082b08, + 0x082b082b2b082b2b, 0x082b082b2b2b2b08, 0x082b190808080819, 0x082b190808081908, + 0x082b19080808192b, 0x082b190808082b19, 0x082b190808190808, 0x082b190808191919, + 0x082b190808192b08, 0x082b1908082b0819, 0x082b1908082b1908, 0x082b190819080808, + 0x082b19081908082b, 0x082b190819081919, 0x082b190819082b08, 0x082b190819190819, + 0x082b190819191908, 0x082b1908192b0808, 0x082b19082b080819, 0x082b19082b081908, + 0x082b19082b190808, 0x082b191908080808, 0x082b191908081919, 0x082b191908082b08, + 0x082b191908190819, 0x082b191908191908, 0x082b1919082b0808, 0x082b191919080819, + 0x082b191919081908, 0x082b191919190808, 0x082b1919192b192b, 0x082b19192b080808, + 0x082b192b08080819, 0x082b192b08081908, 0x082b192b08190808, 0x082b192b19080808, + 0x082b192b19192b19, 0x082b2b0808080808, 0x082b2b0808081919, 0x082b2b0808190819, + 0x082b2b0808191908, 0x082b2b0819080819, 0x082b2b0819081908, 0x082b2b0819190808, + 0x082b2b082b082b2b, 0x082b2b082b2b2b2b, 0x082b2b1908080819, 0x082b2b1908081908, + 0x082b2b1908190808, 0x082b2b192b191919, 0x082b2b2b08082b2b, 0x082b2b2b082b082b, + 0x082b2b2b192b1908, 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, + 0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, + 0x190808080819082b, 0x1908080808191919, 0x1908080808192b08, 0x1908080808192b2b, + 0x19080808082b0819, 0x19080808082b1908, 0x19080808082b192b, 0x1908080819080808, + 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, 0x1908080819082b2b, + 0x1908080819190819, 0x1908080819191908, 0x190808081919192b, 0x1908080819192b19, + 0x19080808192b0808, 0x19080808192b082b, 0x19080808192b1919, 0x190808082b080819, + 0x190808082b081908, 0x190808082b190808, 0x190808082b191919, 0x190808082b192b08, + 0x190808082b2b0819, 0x190808082b2b1908, 0x1908081908080808, 0x190808190808082b, + 0x1908081908081919, 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908, + 0x190808190819192b, 0x1908081908192b19, 0x19080819082b0808, 0x19080819082b082b, + 0x19080819082b1919, 0x1908081919080819, 0x1908081919081908, 0x190808191908192b, + 0x1908081919082b19, 0x1908081919190808, 0x190808191919082b, 0x1908081919191919, + 0x1908081919192b08, 0x19080819192b0819, 0x19080819192b1908, 0x190808192b080808, + 0x190808192b08082b, 0x190808192b081919, 0x190808192b082b08, 0x190808192b190819, + 0x190808192b191908, 0x190808192b2b0808, 0x1908082b08080819, 0x1908082b08081908, + 0x1908082b08190808, 0x1908082b0819082b, 0x1908082b08191919, 0x1908082b08192b08, + 0x1908082b082b1908, 0x1908082b19080808, 0x1908082b19081919, 0x1908082b19082b08, + 0x1908082b19190819, 0x1908082b19191908, 0x1908082b192b0808, 0x1908082b2b080819, + 0x1908082b2b081908, 0x1908190808080808, 0x190819080808082b, 0x1908190808081919, + 0x1908190808082b08, 0x1908190808082b2b, 0x1908190808190819, 0x1908190808191908, + 0x190819080819192b, 0x1908190808192b19, 0x19081908082b0808, 0x19081908082b082b, + 0x19081908082b1919, 0x19081908082b2b08, 0x1908190819080819, 0x1908190819081908, + 0x190819081908192b, 0x1908190819082b19, 0x1908190819190808, 0x190819081919082b, + 0x1908190819191919, 0x1908190819192b08, 0x19081908192b0819, 0x19081908192b1908, + 0x190819082b080808, 0x190819082b08082b, 0x190819082b081919, 0x190819082b082b08, + 0x190819082b190819, 0x190819082b191908, 0x190819082b2b0808, 0x1908191908080819, + 0x1908191908081908, 0x190819190808192b, 0x1908191908082b19, 0x1908191908190808, + 0x190819190819082b, 0x1908191908191919, 0x1908191908192b08, 0x19081919082b0819, + 0x19081919082b1908, 0x1908191919080808, 0x190819191908082b, 0x1908191919081919, + 0x1908191919082b08, 0x1908191919190819, 0x1908191919191908, 0x19081919192b0808, + 0x19081919192b2b2b, 0x190819192b080819, 0x190819192b081908, 0x190819192b190808, + 0x1908192b08080808, 0x1908192b0808082b, 0x1908192b08081919, 0x1908192b08082b08, + 0x1908192b08190819, 0x1908192b08191908, 0x1908192b082b0808, 0x1908192b19080819, + 0x1908192b19081908, 0x1908192b19190808, 0x1908192b2b080808, 0x1908192b2b2b1919, + 0x19082b0808080819, 0x19082b0808081908, 0x19082b0808082b19, 0x19082b0808190808, + 0x19082b080819082b, 0x19082b0808191919, 0x19082b0808192b08, 0x19082b08082b0819, + 0x19082b08082b1908, 0x19082b0819080808, 0x19082b081908082b, 0x19082b0819081919, + 0x19082b0819082b08, 0x19082b0819190819, 0x19082b0819191908, 0x19082b08192b0808, + 0x19082b082b081908, 0x19082b082b190808, 0x19082b1908080808, 0x19082b190808082b, + 0x19082b1908081919, 0x19082b1908082b08, 0x19082b1908190819, 0x19082b1908191908, + 0x19082b19082b0808, 0x19082b1919080819, 0x19082b1919081908, 0x19082b1919190808, + 0x19082b192b080808, 0x19082b192b19192b, 0x19082b2b08080819, 0x19082b2b08081908, + 0x19082b2b08190808, 0x19082b2b19080808, 0x1919080808080808, 0x191908080808082b, + 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, 0x1919080808191908, + 0x191908080819192b, 0x1919080808192b19, 0x19190808082b0808, 0x19190808082b082b, + 0x19190808082b1919, 0x19190808082b2b08, 0x1919080819080819, 0x1919080819081908, + 0x191908081908192b, 0x1919080819082b19, 0x1919080819190808, 0x191908081919082b, + 0x1919080819191919, 0x1919080819192b08, 0x19190808192b0819, 0x19190808192b1908, + 0x191908082b080808, 0x191908082b08082b, 0x191908082b081919, 0x191908082b082b08, + 0x191908082b190819, 0x191908082b191908, 0x1919081908080819, 0x1919081908081908, + 0x191908190808192b, 0x1919081908082b19, 0x1919081908190808, 0x191908190819082b, + 0x1919081908191919, 0x1919081908192b08, 0x19190819082b0819, 0x19190819082b1908, + 0x1919081919080808, 0x191908191908082b, 0x1919081919081919, 0x1919081919082b08, + 0x1919081919190819, 0x1919081919191908, 0x19190819192b0808, 0x191908192b080819, + 0x191908192b081908, 0x191908192b190808, 0x1919082b08080808, 0x1919082b08081919, + 0x1919082b08082b08, 0x1919082b08190819, 0x1919082b08191908, 0x1919082b082b0808, + 0x1919082b19080819, 0x1919082b19081908, 0x1919082b19190808, 0x1919082b192b2b19, + 0x1919082b2b080808, 0x1919190808080819, 0x1919190808081908, 0x191919080808192b, + 0x1919190808082b19, 0x1919190808190808, 0x191919080819082b, 0x1919190808191919, + 0x1919190808192b08, 0x19191908082b0819, 0x19191908082b1908, 0x1919190819080808, + 0x191919081908082b, 0x1919190819081919, 0x1919190819082b08, 0x1919190819190819, + 0x1919190819191908, 0x19191908192b0808, 0x191919082b080819, 0x191919082b081908, + 0x191919082b190808, 0x1919191908080808, 0x191919190808082b, 0x1919191908081919, + 0x1919191908082b08, 0x1919191908190819, 0x1919191908191908, 0x19191919082b0808, + 0x1919191919080819, 0x1919191919081908, 0x1919191919190808, 0x191919192b080808, + 0x1919192b08080819, 0x1919192b08081908, 0x1919192b08190808, 0x1919192b082b192b, + 0x1919192b19080808, 0x19192b0808080808, 0x19192b080808082b, 0x19192b0808081919, + 0x19192b0808082b08, 0x19192b0808190819, 0x19192b0808191908, 0x19192b08082b0808, + 0x19192b0819080819, 0x19192b0819081908, 0x19192b0819190808, 0x19192b0819192b2b, + 0x19192b082b080808, 0x19192b1908080819, 0x19192b1908081908, 0x19192b1908190808, + 0x19192b1919080808, 0x19192b2b08080808, 0x19192b2b08192b19, 0x19192b2b2b081919, + 0x19192b2b2b2b2b08, 0x192b080808080819, 0x192b080808081908, 0x192b08080808192b, + 0x192b080808190808, 0x192b08080819082b, 0x192b080808191919, 0x192b080808192b08, + 0x192b0808082b0819, 0x192b0808082b1908, 0x192b080819080808, 0x192b080819081919, + 0x192b080819082b08, 0x192b080819190819, 0x192b080819191908, 0x192b0808192b0808, + 0x192b08082b081908, 0x192b08082b190808, 0x192b081908080808, 0x192b08190808082b, + 0x192b081908081919, 0x192b081908082b08, 0x192b081908190819, 0x192b081908191908, + 0x192b0819082b0808, 0x192b081919080819, 0x192b081919081908, 0x192b081919190808, + 0x192b08192b080808, 0x192b08192b192b19, 0x192b082b08081908, 0x192b082b08190808, + 0x192b082b19080808, 0x192b082b1919192b, 0x192b082b2b2b0819, 0x192b190808080808, + 0x192b190808081919, 0x192b190808082b08, 0x192b190808190819, 0x192b190808191908, + 0x192b1908082b0808, 0x192b190819080819, 0x192b190819081908, 0x192b190819190808, + 0x192b19082b080808, 0x192b191908080819, 0x192b191908081908, 0x192b191908190808, + 0x192b191919080808, 0x192b191919082b2b, 0x192b1919192b2b08, 0x192b19192b19082b, + 0x192b192b08080808, 0x192b192b2b191908, 0x192b2b0808080819, 0x192b2b0808081908, + 0x192b2b0808190808, 0x192b2b08192b1919, 0x192b2b082b192b08, 0x192b2b1908080808, + 0x192b2b19082b2b2b, 0x192b2b2b1908082b, 0x192b2b2b2b2b0819, 0x2b08080808080808, + 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819, + 0x2b08080808191908, 0x2b08080808192b19, 0x2b080808082b0808, 0x2b080808082b1919, + 0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808081919082b, + 0x2b08080819191919, 0x2b08080819192b08, 0x2b080808192b0819, 0x2b0808082b080808, + 0x2b0808082b081919, 0x2b0808082b190819, 0x2b0808082b191908, 0x2b08081908080819, + 0x2b08081908081908, 0x2b08081908082b19, 0x2b08081908190808, 0x2b0808190819082b, + 0x2b08081908191919, 0x2b08081908192b08, 0x2b080819082b0819, 0x2b080819082b1908, + 0x2b08081919080808, 0x2b0808191908082b, 0x2b08081919081919, 0x2b08081919082b08, + 0x2b08081919190819, 0x2b08081919191908, 0x2b0808192b080819, 0x2b0808192b081908, + 0x2b0808192b190808, 0x2b0808192b2b2b19, 0x2b08082b08080808, 0x2b08082b08081919, + 0x2b08082b08082b2b, 0x2b08082b08190819, 0x2b08082b08191908, 0x2b08082b19080819, + 0x2b08082b19081908, 0x2b08082b19190808, 0x2b08190808080819, 0x2b08190808081908, + 0x2b0819080808192b, 0x2b08190808082b19, 0x2b08190808190808, 0x2b0819080819082b, + 0x2b08190808191919, 0x2b08190808192b08, 0x2b081908082b0819, 0x2b08190819080808, + 0x2b0819081908082b, 0x2b08190819081919, 0x2b08190819082b08, 0x2b08190819190819, + 0x2b08190819191908, 0x2b081908192b0808, 0x2b0819082b080819, 0x2b0819082b081908, + 0x2b0819082b190808, 0x2b08191908080808, 0x2b0819190808082b, 0x2b08191908081919, + 0x2b08191908082b08, 0x2b08191908190819, 0x2b08191908191908, 0x2b081919082b0808, + 0x2b08191919080819, 0x2b08191919081908, 0x2b08191919190808, 0x2b0819192b080808, + 0x2b0819192b082b2b, 0x2b08192b08080819, 0x2b08192b08081908, 0x2b08192b08190808, + 0x2b08192b082b2b19, 0x2b08192b19080808, 0x2b082b0808080808, 0x2b082b0808081919, + 0x2b082b0808190819, 0x2b082b0808191908, 0x2b082b0819080819, 0x2b082b0819081908, + 0x2b082b0819190808, 0x2b082b082b2b082b, 0x2b082b1908080819, 0x2b082b1908081908, + 0x2b082b1919080808, 0x2b082b19192b1919, 0x2b082b2b082b082b, 0x2b082b2b19192b08, + 0x2b082b2b19192b2b, 0x2b082b2b2b08082b, 0x2b082b2b2b2b082b, 0x2b19080808080819, + 0x2b19080808081908, 0x2b19080808082b19, 0x2b19080808190808, 0x2b1908080819082b, + 0x2b19080808191919, 0x2b19080808192b08, 0x2b190808082b1908, 0x2b19080819080808, + 0x2b1908081908082b, 0x2b19080819081919, 0x2b19080819082b08, 0x2b19080819190819, + 0x2b19080819191908, 0x2b190808192b0808, 0x2b1908082b080819, 0x2b1908082b081908, + 0x2b1908082b190808, 0x2b19081908080808, 0x2b19081908081919, 0x2b19081908190819, + 0x2b19081908191908, 0x2b19081919080819, 0x2b19081919081908, 0x2b19081919190808, + 0x2b19081919192b2b, 0x2b19082b08080819, 0x2b19082b08081908, 0x2b19082b08190808, + 0x2b19082b19080808, 0x2b19082b2b2b192b, 0x2b19190808080808, 0x2b1919080808082b, + 0x2b19190808081919, 0x2b19190808082b08, 0x2b19190808190819, 0x2b19190808191908, + 0x2b191908082b0808, 0x2b19190819080819, 0x2b19190819081908, 0x2b19190819190808, + 0x2b1919082b080808, 0x2b1919082b19192b, 0x2b19191908080819, 0x2b19191908081908, + 0x2b19191908190808, 0x2b19191919080808, 0x2b1919192b192b08, 0x2b1919192b2b0819, + 0x2b19192b08080808, 0x2b19192b1908192b, 0x2b19192b192b1908, 0x2b192b0808080819, + 0x2b192b0808081908, 0x2b192b0808190808, 0x2b192b08082b192b, 0x2b192b0819080808, + 0x2b192b082b2b2b19, 0x2b192b1908080808, 0x2b192b1919082b19, 0x2b192b191919082b, + 0x2b192b2b2b190808, 0x2b2b080808080808, 0x2b2b080808081919, 0x2b2b080808082b2b, + 0x2b2b080808191908, 0x2b2b0808082b082b, 0x2b2b0808082b2b2b, 0x2b2b080819080819, + 0x2b2b080819081908, 0x2b2b080819190808, 0x2b2b08082b2b082b, 0x2b2b08082b2b2b2b, + 0x2b2b081919080808, 0x2b2b0819192b1919, 0x2b2b082b0808082b, 0x2b2b082b08082b2b, + 0x2b2b082b082b082b, 0x2b2b082b082b2b08, 0x2b2b082b082b2b2b, 0x2b2b082b2b08082b, + 0x2b2b082b2b082b08, 0x2b2b082b2b082b2b, 0x2b2b082b2b2b2b08, 0x2b2b190808080819, + 0x2b2b190808081908, 0x2b2b190808190808, 0x2b2b190819080808, 0x2b2b19082b082b19, + 0x2b2b19082b2b1908, 0x2b2b191908080808, 0x2b2b191908192b19, 0x2b2b192b19190819, + 0x2b2b2b0808082b2b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b082b, 0x2b2b2b1919191908, + 0x2b2b2b192b08192b, 0x2b2b2b2b08082b08, 0x2b2b2b2b08082b2b, 0x2b2b2b2b082b0808, + 0x2b2b2b2b082b082b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b2b082b08, 0x2b2b2b2b2b2b2b2b, +GGML_TABLE_END() + +GGML_TABLE_BEGIN(uint32_t, iq3xxs_grid, 256) + 0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, 0x04041404, 0x04041414, + 0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14, + 0x040c140c, 0x040c142c, 0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404, + 0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c, 0x04141c1c, 0x04141c3e, + 0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c, 0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c, + 0x041c3e04, 0x04240c1c, 0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c, + 0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04, 0x043e0c24, 0x043e0c34, + 0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c, 0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c, + 0x0c041c04, 0x0c041c14, 0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c, + 0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14, 0x0c14140c, 0x0c141c04, + 0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404, 0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c, + 0x0c24042c, 0x0c242c04, 0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414, + 0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404, 0x14041414, 0x14041434, + 0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c, 0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c, + 0x140c1c04, 0x140c341c, 0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e, + 0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c, 0x141c0c04, 0x141c0c24, + 0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c, 0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24, + 0x143e040c, 0x143e041c, 0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c, + 0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414, 0x1c0c1404, 0x1c0c1c0c, + 0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c, 0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14, + 0x1c1c0c0c, 0x1c1c1c1c, 0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414, + 0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404, 0x24040424, 0x24040c3e, + 0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e, 0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404, + 0x24143404, 0x24143434, 0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c, + 0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04, 0x2c040c14, 0x2c04240c, + 0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434, 0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14, + 0x2c1c0414, 0x2c1c2c1c, 0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c, + 0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434, 0x34043424, 0x340c140c, + 0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04, 0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14, + 0x34341c1c, 0x343e041c, 0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14, + 0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14, 0x3e1c0404, 0x3e1c0c2c, + 0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c, 0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04, +GGML_TABLE_END() + +GGML_TABLE_BEGIN(uint32_t, iq3s_grid, 512) + 0x01010101, 0x01010103, 0x01010105, 0x0101010b, 0x0101010f, 0x01010301, 0x01010303, 0x01010305, + 0x01010309, 0x0101030d, 0x01010501, 0x01010503, 0x0101050b, 0x01010707, 0x01010901, 0x01010905, + 0x0101090b, 0x0101090f, 0x01010b03, 0x01010b07, 0x01010d01, 0x01010d05, 0x01010f03, 0x01010f09, + 0x01010f0f, 0x01030101, 0x01030103, 0x01030105, 0x01030109, 0x01030301, 0x01030303, 0x0103030b, + 0x01030501, 0x01030507, 0x0103050f, 0x01030703, 0x0103070b, 0x01030909, 0x01030d03, 0x01030d0b, + 0x01030f05, 0x01050101, 0x01050103, 0x0105010b, 0x0105010f, 0x01050301, 0x01050307, 0x0105030d, + 0x01050503, 0x0105050b, 0x01050701, 0x01050709, 0x01050905, 0x0105090b, 0x0105090f, 0x01050b03, + 0x01050b07, 0x01050f01, 0x01050f07, 0x01070107, 0x01070303, 0x0107030b, 0x01070501, 0x01070505, + 0x01070703, 0x01070707, 0x0107070d, 0x01070909, 0x01070b01, 0x01070b05, 0x01070d0f, 0x01070f03, + 0x01070f0b, 0x01090101, 0x01090307, 0x0109030f, 0x01090503, 0x01090509, 0x01090705, 0x01090901, + 0x01090907, 0x01090b03, 0x01090f01, 0x010b0105, 0x010b0109, 0x010b0501, 0x010b0505, 0x010b050d, + 0x010b0707, 0x010b0903, 0x010b090b, 0x010b090f, 0x010b0d0d, 0x010b0f07, 0x010d010d, 0x010d0303, + 0x010d0307, 0x010d0703, 0x010d0b05, 0x010d0f03, 0x010f0101, 0x010f0105, 0x010f0109, 0x010f0501, + 0x010f0505, 0x010f050d, 0x010f0707, 0x010f0b01, 0x010f0b09, 0x03010101, 0x03010103, 0x03010105, + 0x03010109, 0x03010301, 0x03010303, 0x03010307, 0x0301030b, 0x0301030f, 0x03010501, 0x03010505, + 0x03010703, 0x03010709, 0x0301070d, 0x03010b09, 0x03010b0d, 0x03010d03, 0x03010f05, 0x03030101, + 0x03030103, 0x03030107, 0x0303010d, 0x03030301, 0x03030309, 0x03030503, 0x03030701, 0x03030707, + 0x03030903, 0x03030b01, 0x03030b05, 0x03030f01, 0x03030f0d, 0x03050101, 0x03050305, 0x0305030b, + 0x0305030f, 0x03050501, 0x03050509, 0x03050705, 0x03050901, 0x03050907, 0x03050b0b, 0x03050d01, + 0x03050f05, 0x03070103, 0x03070109, 0x0307010f, 0x03070301, 0x03070307, 0x03070503, 0x0307050f, + 0x03070701, 0x03070709, 0x03070903, 0x03070d05, 0x03070f01, 0x03090107, 0x0309010b, 0x03090305, + 0x03090309, 0x03090703, 0x03090707, 0x03090905, 0x0309090d, 0x03090b01, 0x03090b09, 0x030b0103, + 0x030b0301, 0x030b0307, 0x030b0503, 0x030b0701, 0x030b0705, 0x030b0b03, 0x030d0501, 0x030d0509, + 0x030d050f, 0x030d0909, 0x030d090d, 0x030f0103, 0x030f0107, 0x030f0301, 0x030f0305, 0x030f0503, + 0x030f070b, 0x030f0903, 0x030f0d05, 0x030f0f01, 0x05010101, 0x05010103, 0x05010107, 0x0501010b, + 0x0501010f, 0x05010301, 0x05010305, 0x05010309, 0x0501030d, 0x05010503, 0x05010507, 0x0501050f, + 0x05010701, 0x05010705, 0x05010903, 0x05010907, 0x0501090b, 0x05010b01, 0x05010b05, 0x05010d0f, + 0x05010f01, 0x05010f07, 0x05010f0b, 0x05030101, 0x05030105, 0x05030301, 0x05030307, 0x0503030f, + 0x05030505, 0x0503050b, 0x05030703, 0x05030709, 0x05030905, 0x05030b03, 0x05050103, 0x05050109, + 0x0505010f, 0x05050503, 0x05050507, 0x05050701, 0x0505070f, 0x05050903, 0x05050b07, 0x05050b0f, + 0x05050f03, 0x05050f09, 0x05070101, 0x05070105, 0x0507010b, 0x05070303, 0x05070505, 0x05070509, + 0x05070703, 0x05070707, 0x05070905, 0x05070b01, 0x05070d0d, 0x05090103, 0x0509010f, 0x05090501, + 0x05090507, 0x05090705, 0x0509070b, 0x05090903, 0x05090f05, 0x05090f0b, 0x050b0109, 0x050b0303, + 0x050b0505, 0x050b070f, 0x050b0901, 0x050b0b07, 0x050b0f01, 0x050d0101, 0x050d0105, 0x050d010f, + 0x050d0503, 0x050d0b0b, 0x050d0d03, 0x050f010b, 0x050f0303, 0x050f050d, 0x050f0701, 0x050f0907, + 0x050f0b01, 0x07010105, 0x07010303, 0x07010307, 0x0701030b, 0x0701030f, 0x07010505, 0x07010703, + 0x07010707, 0x0701070b, 0x07010905, 0x07010909, 0x0701090f, 0x07010b03, 0x07010d07, 0x07010f03, + 0x07030103, 0x07030107, 0x0703010b, 0x07030309, 0x07030503, 0x07030507, 0x07030901, 0x07030d01, + 0x07030f05, 0x07030f0d, 0x07050101, 0x07050305, 0x07050501, 0x07050705, 0x07050709, 0x07050b01, + 0x07070103, 0x07070301, 0x07070309, 0x07070503, 0x07070507, 0x0707050f, 0x07070701, 0x07070903, + 0x07070907, 0x0707090f, 0x07070b0b, 0x07070f07, 0x07090107, 0x07090303, 0x0709030d, 0x07090505, + 0x07090703, 0x07090b05, 0x07090d01, 0x07090d09, 0x070b0103, 0x070b0301, 0x070b0305, 0x070b050b, + 0x070b0705, 0x070b0909, 0x070b0b0d, 0x070b0f07, 0x070d030d, 0x070d0903, 0x070f0103, 0x070f0107, + 0x070f0501, 0x070f0505, 0x070f070b, 0x09010101, 0x09010109, 0x09010305, 0x09010501, 0x09010509, + 0x0901050f, 0x09010705, 0x09010903, 0x09010b01, 0x09010f01, 0x09030105, 0x0903010f, 0x09030303, + 0x09030307, 0x09030505, 0x09030701, 0x0903070b, 0x09030907, 0x09030b03, 0x09030b0b, 0x09050103, + 0x09050107, 0x09050301, 0x0905030b, 0x09050503, 0x09050707, 0x09050901, 0x09050b0f, 0x09050d05, + 0x09050f01, 0x09070109, 0x09070303, 0x09070307, 0x09070501, 0x09070505, 0x09070703, 0x0907070b, + 0x09090101, 0x09090105, 0x09090509, 0x0909070f, 0x09090901, 0x09090f03, 0x090b010b, 0x090b010f, + 0x090b0503, 0x090b0d05, 0x090d0307, 0x090d0709, 0x090d0d01, 0x090f0301, 0x090f030b, 0x090f0701, + 0x090f0907, 0x090f0b03, 0x0b010105, 0x0b010301, 0x0b010309, 0x0b010505, 0x0b010901, 0x0b010909, + 0x0b01090f, 0x0b010b05, 0x0b010d0d, 0x0b010f09, 0x0b030103, 0x0b030107, 0x0b03010b, 0x0b030305, + 0x0b030503, 0x0b030705, 0x0b030f05, 0x0b050101, 0x0b050303, 0x0b050507, 0x0b050701, 0x0b05070d, + 0x0b050b07, 0x0b070105, 0x0b07010f, 0x0b070301, 0x0b07050f, 0x0b070909, 0x0b070b03, 0x0b070d0b, + 0x0b070f07, 0x0b090103, 0x0b090109, 0x0b090501, 0x0b090705, 0x0b09090d, 0x0b0b0305, 0x0b0b050d, + 0x0b0b0b03, 0x0b0b0b07, 0x0b0d0905, 0x0b0f0105, 0x0b0f0109, 0x0b0f0505, 0x0d010303, 0x0d010307, + 0x0d01030b, 0x0d010703, 0x0d010707, 0x0d010d01, 0x0d030101, 0x0d030501, 0x0d03050f, 0x0d030d09, + 0x0d050305, 0x0d050709, 0x0d050905, 0x0d050b0b, 0x0d050d05, 0x0d050f01, 0x0d070101, 0x0d070309, + 0x0d070503, 0x0d070901, 0x0d09050b, 0x0d090907, 0x0d090d05, 0x0d0b0101, 0x0d0b0107, 0x0d0b0709, + 0x0d0b0d01, 0x0d0d010b, 0x0d0d0901, 0x0d0f0303, 0x0d0f0307, 0x0f010101, 0x0f010109, 0x0f01010f, + 0x0f010501, 0x0f010505, 0x0f01070d, 0x0f010901, 0x0f010b09, 0x0f010d05, 0x0f030105, 0x0f030303, + 0x0f030509, 0x0f030907, 0x0f03090b, 0x0f050103, 0x0f050109, 0x0f050301, 0x0f05030d, 0x0f050503, + 0x0f050701, 0x0f050b03, 0x0f070105, 0x0f070705, 0x0f07070b, 0x0f070b07, 0x0f090103, 0x0f09010b, + 0x0f090307, 0x0f090501, 0x0f090b01, 0x0f0b0505, 0x0f0b0905, 0x0f0d0105, 0x0f0d0703, 0x0f0f0101, +GGML_TABLE_END() + +#define NGRID_IQ1S 2048 +#define IQ1S_DELTA 0.125f +#if defined(GGML_COMMON_IMPL_C) +GGML_TABLE_BEGIN(uint64_t, iq1s_grid, NGRID_IQ1S) + 0xffffffffffffffff, 0xffffffffffffff01, 0xffffffffffff0000, 0xffffffffffff01ff, + 0xffffffffffff0101, 0xffffffffff00ff00, 0xffffffffff000000, 0xffffffffff01ffff, + 0xffffffffff01ff01, 0xffffffffff0101ff, 0xffffffffff010101, 0xffffffff00ff0000, + 0xffffffff0000ff00, 0xffffffff000000ff, 0xffffffff00000001, 0xffffffff00010000, + 0xffffffff01ffffff, 0xffffffff01ffff01, 0xffffffff01ff01ff, 0xffffffff01ff0101, + 0xffffffff01000000, 0xffffffff0101ffff, 0xffffffff0101ff01, 0xffffffff010101ff, + 0xffffffff01010101, 0xffffff00ffff00ff, 0xffffff00ffff0000, 0xffffff00ff00ff00, + 0xffffff00ff0000ff, 0xffffff00ff000001, 0xffffff00ff000100, 0xffffff00ff000101, + 0xffffff00ff010000, 0xffffff0000ffff00, 0xffffff0000ff0001, 0xffffff0000ff0100, + 0xffffff000000ff01, 0xffffff0000000000, 0xffffff0000000101, 0xffffff000001ff00, + 0xffffff00000100ff, 0xffffff0000010001, 0xffffff00000101ff, 0xffffff0001ff0000, + 0xffffff000100ff00, 0xffffff00010000ff, 0xffffff0001000001, 0xffffff0001010000, + 0xffffff01ffffffff, 0xffffff01ffffff01, 0xffffff01ffff01ff, 0xffffff01ffff0101, + 0xffffff01ff000000, 0xffffff01ff01ffff, 0xffffff01ff01ff01, 0xffffff01ff0101ff, + 0xffffff01ff010101, 0xffffff0100ff0000, 0xffffff010000ff00, 0xffffff0100000100, + 0xffffff01000100ff, 0xffffff0100010100, 0xffffff0101ffffff, 0xffffff0101ffff01, + 0xffffff0101ff01ff, 0xffffff0101ff0101, 0xffffff010100ff00, 0xffffff0101000000, + 0xffffff0101000100, 0xffffff010101ffff, 0xffffff010101ff01, 0xffffff01010101ff, + 0xffffff0101010101, 0xffff00ffff00ff00, 0xffff00ffff0000ff, 0xffff00ffff000001, + 0xffff00ffff010000, 0xffff00ff00ffff00, 0xffff00ff00ff0100, 0xffff00ff00000000, + 0xffff00ff00000101, 0xffff00ff000100ff, 0xffff00ff00010000, 0xffff00ff0100ff00, + 0xffff00ff01000100, 0xffff00ff01010000, 0xffff0000ffffff00, 0xffff0000ffff00ff, + 0xffff0000ffff0000, 0xffff0000ffff0001, 0xffff0000ff000000, 0xffff0000ff0001ff, + 0xffff0000ff000101, 0xffff0000ff010100, 0xffff000000ffffff, 0xffff000000ff0000, + 0xffff000000ff0101, 0xffff00000000ffff, 0xffff00000000ff00, 0xffff0000000000ff, + 0xffff000000000000, 0xffff000000000001, 0xffff000000000100, 0xffff00000001ffff, + 0xffff00000001ff01, 0xffff000000010000, 0xffff0000000101ff, 0xffff000000010101, + 0xffff000001ffff00, 0xffff00000100ff00, 0xffff000001000000, 0xffff0000010001ff, + 0xffff000001000101, 0xffff00000101ff00, 0xffff0000010100ff, 0xffff000001010000, + 0xffff000001010001, 0xffff000001010100, 0xffff0001ff0000ff, 0xffff0001ff000100, + 0xffff000100ffff00, 0xffff000100ff00ff, 0xffff00010000ffff, 0xffff00010000ff01, + 0xffff000100000000, 0xffff0001000001ff, 0xffff00010001ffff, 0xffff00010001ff00, + 0xffff000100010001, 0xffff000100010100, 0xffff000101ff0000, 0xffff00010100ff00, + 0xffff0001010000ff, 0xffff000101000100, 0xffff01ffffffffff, 0xffff01ffffffff01, + 0xffff01ffffff01ff, 0xffff01ffffff0101, 0xffff01ffff000000, 0xffff01ffff01ffff, + 0xffff01ffff01ff01, 0xffff01ffff0101ff, 0xffff01ffff010101, 0xffff01ff00ff0000, + 0xffff01ff0000ff00, 0xffff01ff00000001, 0xffff01ff00010000, 0xffff01ff01ffffff, + 0xffff01ff01ffff01, 0xffff01ff01ff01ff, 0xffff01ff01ff0101, 0xffff01ff01000000, + 0xffff01ff0101ffff, 0xffff01ff0101ff01, 0xffff01ff010101ff, 0xffff01ff01010101, + 0xffff0100ffff0000, 0xffff0100ff00ff00, 0xffff0100ff0000ff, 0xffff0100ff000100, + 0xffff0100ff0100ff, 0xffff0100ff010000, 0xffff010000ffff00, 0xffff01000000ffff, + 0xffff01000000ff00, 0xffff010000000000, 0xffff01000001ff00, 0xffff0100000100ff, + 0xffff010000010100, 0xffff01000100ff00, 0xffff0100010000ff, 0xffff010001000001, + 0xffff010001000100, 0xffff010001010000, 0xffff0101ffffffff, 0xffff0101ffffff01, + 0xffff0101ffff01ff, 0xffff0101ffff0101, 0xffff0101ff000000, 0xffff0101ff01ffff, + 0xffff0101ff01ff01, 0xffff0101ff0101ff, 0xffff0101ff010101, 0xffff010100ff0000, + 0xffff01010000ff00, 0xffff010100000100, 0xffff01010001ff00, 0xffff010100010000, + 0xffff010101ffffff, 0xffff010101ffff01, 0xffff010101ff0000, 0xffff010101ff01ff, + 0xffff010101ff0101, 0xffff010101000000, 0xffff01010101ffff, 0xffff01010101ff01, + 0xffff0101010101ff, 0xffff010101010101, 0xff00ffffff00ffff, 0xff00ffffff00ff00, + 0xff00ffffff0000ff, 0xff00ffffff000100, 0xff00ffffff0100ff, 0xff00ffffff010000, + 0xff00ffff00ffff00, 0xff00ffff00ff00ff, 0xff00ffff0000ffff, 0xff00ffff00000000, + 0xff00ffff000001ff, 0xff00ffff0001ff00, 0xff00ffff000100ff, 0xff00ffff00010000, + 0xff00ffff00010100, 0xff00ffff0100ff00, 0xff00ffff010000ff, 0xff00ffff01000001, + 0xff00ffff0101ff00, 0xff00ffff01010000, 0xff00ff00ffffff00, 0xff00ff00ffff00ff, + 0xff00ff00ffff0001, 0xff00ff00ffff0100, 0xff00ff00ff00ffff, 0xff00ff00ff00ff01, + 0xff00ff00ff000000, 0xff00ff00ff0001ff, 0xff00ff00ff01ff00, 0xff00ff00ff0100ff, + 0xff00ff00ff010100, 0xff00ff0000ff0000, 0xff00ff0000ff0101, 0xff00ff000000ffff, + 0xff00ff000000ff00, 0xff00ff000000ff01, 0xff00ff00000000ff, 0xff00ff0000000000, + 0xff00ff0000000001, 0xff00ff0000000100, 0xff00ff000001ffff, 0xff00ff0000010000, + 0xff00ff0001ff00ff, 0xff00ff000100ff01, 0xff00ff0001000000, 0xff00ff000101ff00, + 0xff00ff00010100ff, 0xff00ff01ff00ff00, 0xff00ff01ff0000ff, 0xff00ff01ff000001, + 0xff00ff01ff010000, 0xff00ff0100ffffff, 0xff00ff0100ff0001, 0xff00ff0100ff0100, + 0xff00ff010000ff01, 0xff00ff0100000000, 0xff00ff01000001ff, 0xff00ff0100000101, + 0xff00ff01000100ff, 0xff00ff0100010001, 0xff00ff0101ff0000, 0xff00ff010100ff00, + 0xff00ff01010000ff, 0xff00ff0101000001, 0xff00ff0101010000, 0xff0000ffffffff00, + 0xff0000ffffff0001, 0xff0000ffffff0100, 0xff0000ffff0000ff, 0xff0000ffff000000, + 0xff0000ffff0001ff, 0xff0000ffff000100, 0xff0000ffff01ff00, 0xff0000ffff010001, + 0xff0000ff00ffff00, 0xff0000ff00ff0000, 0xff0000ff00ff0001, 0xff0000ff00ff01ff, + 0xff0000ff00ff0101, 0xff0000ff0000ff00, 0xff0000ff000000ff, 0xff0000ff00000000, + 0xff0000ff00000001, 0xff0000ff00000100, 0xff0000ff0001ff01, 0xff0000ff00010000, + 0xff0000ff000101ff, 0xff0000ff01ff00ff, 0xff0000ff01ff0100, 0xff0000ff0100ffff, + 0xff0000ff010000ff, 0xff0000ff01000000, 0xff0000ff010001ff, 0xff0000ff01000100, + 0xff0000ff01000101, 0xff0000ff0101ff00, 0xff0000ff010100ff, 0xff0000ff01010000, + 0xff0000ff01010100, 0xff000000ffffff01, 0xff000000ffff0000, 0xff000000ffff0101, + 0xff000000ff00ff00, 0xff000000ff0000ff, 0xff000000ff000000, 0xff000000ff000001, + 0xff000000ff000100, 0xff000000ff01ffff, 0xff000000ff01ff01, 0xff000000ff010000, + 0xff000000ff0101ff, 0xff000000ff010101, 0xff00000000ffff00, 0xff00000000ff00ff, + 0xff00000000ff0000, 0xff00000000ff0001, 0xff0000000000ff00, 0xff0000000000ff01, + 0xff000000000000ff, 0xff00000000000000, 0xff00000000000001, 0xff00000000000100, + 0xff00000000000101, 0xff0000000001ff00, 0xff000000000100ff, 0xff00000000010000, + 0xff00000000010001, 0xff00000000010100, 0xff00000001ffffff, 0xff00000001ffff01, + 0xff00000001ff00ff, 0xff00000001ff0000, 0xff00000001ff01ff, 0xff00000001ff0101, + 0xff0000000100ffff, 0xff0000000100ff00, 0xff000000010000ff, 0xff00000001000000, + 0xff00000001000001, 0xff00000001000100, 0xff00000001000101, 0xff0000000101ffff, + 0xff0000000101ff01, 0xff00000001010000, 0xff000001ffffff00, 0xff000001ffff00ff, + 0xff000001ffff0000, 0xff000001ffff0001, 0xff000001ff000000, 0xff000001ff000001, + 0xff000001ff0001ff, 0xff000001ff000101, 0xff000001ff01ff00, 0xff000001ff010001, + 0xff00000100ffffff, 0xff00000100ffff01, 0xff00000100ff00ff, 0xff00000100ff0000, + 0xff00000100ff01ff, 0xff00000100ff0101, 0xff0000010000ff00, 0xff00000100000000, + 0xff00000100000001, 0xff000001000001ff, 0xff00000100000100, 0xff0000010001ff00, + 0xff000001000100ff, 0xff00000100010000, 0xff000001000101ff, 0xff00000100010100, + 0xff00000100010101, 0xff00000101ff0001, 0xff00000101ff0101, 0xff0000010100ff01, + 0xff00000101000000, 0xff000001010100ff, 0xff00000101010100, 0xff0001ffff00ff00, + 0xff0001ffff000001, 0xff0001ffff010000, 0xff0001ff00ffff00, 0xff0001ff00ff00ff, + 0xff0001ff00ff0001, 0xff0001ff00ff0100, 0xff0001ff0000ffff, 0xff0001ff00000000, + 0xff0001ff000001ff, 0xff0001ff00000101, 0xff0001ff0001ffff, 0xff0001ff0001ff00, + 0xff0001ff000100ff, 0xff0001ff00010001, 0xff0001ff00010100, 0xff0001ff01ff0000, + 0xff0001ff0100ff00, 0xff0001ff010000ff, 0xff0001ff01010000, 0xff000100ff00ffff, + 0xff000100ff00ff01, 0xff000100ff000000, 0xff000100ff000101, 0xff000100ff01ff00, + 0xff000100ff010000, 0xff00010000ffff01, 0xff00010000ff00ff, 0xff00010000ff0000, + 0xff00010000ff01ff, 0xff0001000000ff00, 0xff000100000000ff, 0xff00010000000000, + 0xff00010000000001, 0xff00010000000100, 0xff00010000000101, 0xff0001000001ffff, + 0xff00010000010000, 0xff00010000010101, 0xff00010001ff0100, 0xff0001000100ff00, + 0xff0001000100ff01, 0xff00010001000000, 0xff000100010001ff, 0xff0001000101ff00, + 0xff00010001010001, 0xff00010001010100, 0xff000101ffff0100, 0xff000101ff000001, + 0xff000101ff0100ff, 0xff000101ff010001, 0xff00010100ff00ff, 0xff00010100ff0001, + 0xff00010100ff0100, 0xff0001010000ffff, 0xff0001010000ff01, 0xff00010100000000, + 0xff000101000001ff, 0xff0001010001ff00, 0xff00010100010001, 0xff00010100010100, + 0xff00010101ff0000, 0xff0001010100ff00, 0xff00010101000001, 0xff00010101000101, + 0xff01ffffffffffff, 0xff01ffffffffff01, 0xff01ffffffff01ff, 0xff01ffffffff0101, + 0xff01ffffff000000, 0xff01ffffff01ffff, 0xff01ffffff01ff01, 0xff01ffffff010000, + 0xff01ffffff0101ff, 0xff01ffffff010101, 0xff01ffff00ff0000, 0xff01ffff0000ff00, + 0xff01ffff00000100, 0xff01ffff0001ff00, 0xff01ffff00010000, 0xff01ffff01ffffff, + 0xff01ffff01ffff01, 0xff01ffff01ff01ff, 0xff01ffff01ff0101, 0xff01ffff01000000, + 0xff01ffff0101ffff, 0xff01ffff0101ff01, 0xff01ffff01010000, 0xff01ffff010101ff, + 0xff01ffff01010101, 0xff01ff00ffff0000, 0xff01ff00ff00ff00, 0xff01ff00ff0000ff, + 0xff01ff00ff000100, 0xff01ff00ff010000, 0xff01ff0000ffff01, 0xff01ff0000ff00ff, + 0xff01ff0000ff0100, 0xff01ff0000000000, 0xff01ff00000001ff, 0xff01ff0000000101, + 0xff01ff000001ff00, 0xff01ff00000100ff, 0xff01ff0000010000, 0xff01ff0000010001, + 0xff01ff0001ff0000, 0xff01ff000100ffff, 0xff01ff0001000001, 0xff01ff0001000100, + 0xff01ff0001010000, 0xff01ff01ffffff00, 0xff01ff01ffff01ff, 0xff01ff01ffff0101, + 0xff01ff01ff00ff00, 0xff01ff01ff000000, 0xff01ff01ff01ffff, 0xff01ff01ff01ff01, + 0xff01ff01ff0101ff, 0xff01ff01ff010101, 0xff01ff0100ff0000, 0xff01ff010000ff00, + 0xff01ff0100000001, 0xff01ff0100000100, 0xff01ff0100010000, 0xff01ff0101ffff00, + 0xff01ff0101ff01ff, 0xff01ff0101ff0101, 0xff01ff010100ff00, 0xff01ff0101000000, + 0xff01ff010101ffff, 0xff01ff010101ff01, 0xff01ff01010101ff, 0xff01ff0101010101, + 0xff0100ffffff0000, 0xff0100ffff0000ff, 0xff0100ffff000001, 0xff0100ffff000100, + 0xff0100ffff010000, 0xff0100ff00ff00ff, 0xff0100ff00ff0000, 0xff0100ff00ff0001, + 0xff0100ff00ff0100, 0xff0100ff0000ff01, 0xff0100ff00000000, 0xff0100ff000001ff, + 0xff0100ff00000101, 0xff0100ff00010001, 0xff0100ff01ff0000, 0xff0100ff0100ff00, + 0xff0100ff010000ff, 0xff0100ff01000100, 0xff0100ff0101ff00, 0xff0100ff01010000, + 0xff010000ffff0100, 0xff010000ff000000, 0xff010000ff01ff00, 0xff010000ff010100, + 0xff01000000ffffff, 0xff01000000ff0000, 0xff01000000ff01ff, 0xff0100000000ff00, + 0xff010000000000ff, 0xff01000000000000, 0xff01000000000100, 0xff0100000001ff01, + 0xff01000000010000, 0xff010000000101ff, 0xff01000001ff0100, 0xff0100000100ffff, + 0xff010000010000ff, 0xff01000001000000, 0xff010000010001ff, 0xff01000001000101, + 0xff0100000101ff00, 0xff010000010100ff, 0xff01000001010001, 0xff01000001010100, + 0xff010001ffff0000, 0xff010001ff00ffff, 0xff010001ff00ff01, 0xff010001ff000100, + 0xff010001ff010000, 0xff01000100ffff00, 0xff01000100ff0100, 0xff01000100000000, + 0xff0100010001ffff, 0xff0100010001ff00, 0xff01000100010100, 0xff01000101ff00ff, + 0xff01000101ff0001, 0xff0100010100ffff, 0xff01000101000101, 0xff0101ffffffffff, + 0xff0101ffffffff01, 0xff0101ffffff01ff, 0xff0101ffffff0101, 0xff0101ffff000000, + 0xff0101ffff01ffff, 0xff0101ffff01ff01, 0xff0101ffff0101ff, 0xff0101ffff010101, + 0xff0101ff00ff0000, 0xff0101ff0000ff00, 0xff0101ff000000ff, 0xff0101ff00010000, + 0xff0101ff01ffffff, 0xff0101ff01ffff01, 0xff0101ff01ff01ff, 0xff0101ff01ff0101, + 0xff0101ff0101ffff, 0xff0101ff0101ff01, 0xff0101ff010101ff, 0xff0101ff01010101, + 0xff010100ffff0100, 0xff010100ff00ff00, 0xff010100ff0000ff, 0xff010100ff000100, + 0xff010100ff010000, 0xff01010000ff0001, 0xff01010000ff0100, 0xff0101000000ff01, + 0xff01010000000000, 0xff0101000001ff00, 0xff010100000100ff, 0xff01010000010001, + 0xff01010000010100, 0xff01010001ff0000, 0xff0101000100ffff, 0xff01010001000001, + 0xff01010001000100, 0xff010100010100ff, 0xff01010001010000, 0xff010101ffffffff, + 0xff010101ffffff01, 0xff010101ffff01ff, 0xff010101ffff0101, 0xff010101ff01ffff, + 0xff010101ff01ff01, 0xff010101ff0101ff, 0xff010101ff010101, 0xff01010100ff0000, + 0xff0101010000ff00, 0xff01010100000001, 0xff01010100000100, 0xff01010100010000, + 0xff01010101ffffff, 0xff01010101ffff01, 0xff01010101ff01ff, 0xff01010101ff0101, + 0xff01010101000000, 0xff0101010101ffff, 0xff0101010101ff01, 0xff010101010101ff, + 0xff01010101010101, 0x00ffffffffff0000, 0x00ffffffff00ff00, 0x00ffffffff000001, + 0x00ffffffff010000, 0x00ffffff00ff0100, 0x00ffffff0000ff01, 0x00ffffff00000000, + 0x00ffffff000001ff, 0x00ffffff00000101, 0x00ffffff0001ff00, 0x00ffffff000100ff, + 0x00ffffff00010001, 0x00ffffff010000ff, 0x00ffffff01000100, 0x00ffffff0101ff00, + 0x00ffffff01010001, 0x00ffff00ffffffff, 0x00ffff00ffffff00, 0x00ffff00ffff00ff, + 0x00ffff00ffff0001, 0x00ffff00ffff0100, 0x00ffff00ff00ff01, 0x00ffff00ff000000, + 0x00ffff00ff000001, 0x00ffff00ff0001ff, 0x00ffff00ff000101, 0x00ffff00ff01ff00, + 0x00ffff00ff010001, 0x00ffff00ff010100, 0x00ffff0000ff0000, 0x00ffff0000ff01ff, + 0x00ffff0000ff0101, 0x00ffff000000ff00, 0x00ffff00000000ff, 0x00ffff0000000000, + 0x00ffff0000000001, 0x00ffff0000000100, 0x00ffff0000000101, 0x00ffff0000010000, + 0x00ffff00000101ff, 0x00ffff0000010101, 0x00ffff0001ffff00, 0x00ffff0001ff00ff, + 0x00ffff0001ff0001, 0x00ffff000100ffff, 0x00ffff000100ff01, 0x00ffff0001000000, + 0x00ffff000101ffff, 0x00ffff000101ff00, 0x00ffff000101ff01, 0x00ffff01ffff0000, + 0x00ffff01ff00ff00, 0x00ffff01ff0000ff, 0x00ffff01ff000001, 0x00ffff01ff010000, + 0x00ffff0100ffff00, 0x00ffff010000ff01, 0x00ffff0100000000, 0x00ffff0100000101, + 0x00ffff01000100ff, 0x00ffff0100010100, 0x00ffff0101ff0100, 0x00ffff01010000ff, + 0x00ffff0101010000, 0x00ff00ffffffff00, 0x00ff00ffff000000, 0x00ff00ffff000100, + 0x00ff00ffff010100, 0x00ff00ff00ff0000, 0x00ff00ff00ff01ff, 0x00ff00ff00ff0101, + 0x00ff00ff0000ff00, 0x00ff00ff000000ff, 0x00ff00ff00000000, 0x00ff00ff00000001, + 0x00ff00ff0001ff00, 0x00ff00ff0001ff01, 0x00ff00ff00010000, 0x00ff00ff000101ff, + 0x00ff00ff00010101, 0x00ff00ff01ffff00, 0x00ff00ff01ff0001, 0x00ff00ff01ff0100, + 0x00ff00ff0100ffff, 0x00ff00ff0100ff01, 0x00ff00ff01000000, 0x00ff00ff0101ffff, + 0x00ff00ff0101ff00, 0x00ff00ff01010100, 0x00ff0000ffffff00, 0x00ff0000ffffff01, + 0x00ff0000ffff0000, 0x00ff0000ffff0101, 0x00ff0000ff00ff00, 0x00ff0000ff0000ff, + 0x00ff0000ff000000, 0x00ff0000ff000001, 0x00ff0000ff000100, 0x00ff0000ff01ffff, + 0x00ff0000ff010000, 0x00ff0000ff010101, 0x00ff000000ffff00, 0x00ff000000ff00ff, + 0x00ff000000ff0000, 0x00ff000000ff0001, 0x00ff000000ff0100, 0x00ff00000000ffff, + 0x00ff00000000ff00, 0x00ff0000000000ff, 0x00ff000000000000, 0x00ff000000000001, + 0x00ff0000000001ff, 0x00ff000000000100, 0x00ff00000001ff00, 0x00ff0000000100ff, + 0x00ff000000010000, 0x00ff000000010001, 0x00ff000000010100, 0x00ff000001ffff01, + 0x00ff000001ff00ff, 0x00ff000001ff0000, 0x00ff000001ff01ff, 0x00ff00000100ff00, + 0x00ff0000010000ff, 0x00ff000001000000, 0x00ff000001000001, 0x00ff000001000100, + 0x00ff000001000101, 0x00ff000001010000, 0x00ff0000010101ff, 0x00ff000001010101, + 0x00ff0001ffffff00, 0x00ff0001ffff0000, 0x00ff0001ffff0100, 0x00ff0001ff0000ff, + 0x00ff0001ff000000, 0x00ff0001ff0001ff, 0x00ff0001ff000101, 0x00ff0001ff01ff00, + 0x00ff0001ff0100ff, 0x00ff0001ff010100, 0x00ff000100ffffff, 0x00ff000100ffff01, + 0x00ff000100ff0000, 0x00ff000100ff01ff, 0x00ff00010000ffff, 0x00ff00010000ff00, + 0x00ff00010000ff01, 0x00ff000100000000, 0x00ff000100000001, 0x00ff000100000100, + 0x00ff00010001ff01, 0x00ff000100010000, 0x00ff0001000101ff, 0x00ff000101ffff00, + 0x00ff000101ff0000, 0x00ff000101ff0101, 0x00ff0001010000ff, 0x00ff000101000000, + 0x00ff00010101ff00, 0x00ff0001010100ff, 0x00ff000101010001, 0x00ff01ffffff0000, + 0x00ff01ffff00ff00, 0x00ff01ffff000000, 0x00ff01ffff000101, 0x00ff01ffff010000, + 0x00ff01ff00ffff01, 0x00ff01ff00ff0100, 0x00ff01ff0000ffff, 0x00ff01ff00000000, + 0x00ff01ff000001ff, 0x00ff01ff0001ff00, 0x00ff01ff000100ff, 0x00ff01ff00010001, + 0x00ff01ff00010100, 0x00ff01ff01ff0000, 0x00ff01ff0100ff00, 0x00ff01ff010000ff, + 0x00ff01ff01000001, 0x00ff01ff01000100, 0x00ff01ff01010000, 0x00ff0100ffffff00, + 0x00ff0100ffff0000, 0x00ff0100ffff0001, 0x00ff0100ffff0101, 0x00ff0100ff00ffff, + 0x00ff0100ff0000ff, 0x00ff0100ff000000, 0x00ff0100ff0001ff, 0x00ff0100ff01ff00, + 0x00ff0100ff0100ff, 0x00ff0100ff010001, 0x00ff010000ffffff, 0x00ff010000ff0000, + 0x00ff010000ff0101, 0x00ff01000000ff00, 0x00ff01000000ff01, 0x00ff0100000000ff, + 0x00ff010000000000, 0x00ff010000000001, 0x00ff010000000100, 0x00ff01000001ffff, + 0x00ff01000001ff01, 0x00ff010000010000, 0x00ff010000010001, 0x00ff010000010101, + 0x00ff010001ff0001, 0x00ff010001ff0100, 0x00ff01000100ff01, 0x00ff010001000000, + 0x00ff010001000001, 0x00ff0100010001ff, 0x00ff01000101ff00, 0x00ff0100010100ff, + 0x00ff010001010001, 0x00ff010001010100, 0x00ff0101ff000001, 0x00ff010100ff00ff, + 0x00ff010100ff0001, 0x00ff010100ff0100, 0x00ff010100000000, 0x00ff0101000001ff, + 0x00ff010100000101, 0x00ff0101000100ff, 0x00ff010100010100, 0x00ff0101010000ff, + 0x00ff010101010000, 0x0000ffffffffff00, 0x0000ffffffff00ff, 0x0000ffffffff0000, + 0x0000ffffffff0001, 0x0000ffffffff0100, 0x0000ffffff00ff01, 0x0000ffffff000000, + 0x0000ffffff000101, 0x0000ffffff01ff00, 0x0000ffffff0100ff, 0x0000ffffff010100, + 0x0000ffff00ffffff, 0x0000ffff00ff0000, 0x0000ffff00ff01ff, 0x0000ffff0000ff00, + 0x0000ffff000000ff, 0x0000ffff00000000, 0x0000ffff00000001, 0x0000ffff00000100, + 0x0000ffff00010000, 0x0000ffff000101ff, 0x0000ffff01ff0001, 0x0000ffff01ff0100, + 0x0000ffff01000000, 0x0000ffff010001ff, 0x0000ffff0101ffff, 0x0000ffff0101ff00, + 0x0000ffff01010001, 0x0000ffff01010100, 0x0000ff00ffff0000, 0x0000ff00ffff01ff, + 0x0000ff00ffff0100, 0x0000ff00ffff0101, 0x0000ff00ff00ff00, 0x0000ff00ff0000ff, + 0x0000ff00ff000000, 0x0000ff00ff000001, 0x0000ff00ff0001ff, 0x0000ff00ff000100, + 0x0000ff00ff01ffff, 0x0000ff00ff010000, 0x0000ff00ff010001, 0x0000ff00ff0101ff, + 0x0000ff00ff010101, 0x0000ff0000ffff00, 0x0000ff0000ff00ff, 0x0000ff0000ff0000, + 0x0000ff0000ff0001, 0x0000ff0000ff0100, 0x0000ff000000ffff, 0x0000ff000000ff00, + 0x0000ff000000ff01, 0x0000ff00000000ff, 0x0000ff0000000000, 0x0000ff0000000001, + 0x0000ff00000001ff, 0x0000ff0000000100, 0x0000ff0000000101, 0x0000ff000001ff00, + 0x0000ff00000100ff, 0x0000ff0000010000, 0x0000ff0000010001, 0x0000ff0000010100, + 0x0000ff0001ffff01, 0x0000ff0001ff0000, 0x0000ff000100ff00, 0x0000ff00010000ff, + 0x0000ff0001000000, 0x0000ff0001000001, 0x0000ff0001000100, 0x0000ff000101ffff, + 0x0000ff0001010000, 0x0000ff0001010101, 0x0000ff01ffffff00, 0x0000ff01ffff0001, + 0x0000ff01ff00ff01, 0x0000ff01ff000000, 0x0000ff01ff000101, 0x0000ff01ff01ff00, + 0x0000ff01ff0100ff, 0x0000ff0100ffff01, 0x0000ff0100ff0000, 0x0000ff0100ff0101, + 0x0000ff010000ff00, 0x0000ff01000000ff, 0x0000ff0100000000, 0x0000ff0100000001, + 0x0000ff0100000100, 0x0000ff010001ff01, 0x0000ff0100010000, 0x0000ff0101ff0000, + 0x0000ff010100ffff, 0x0000ff010100ff01, 0x0000ff0101000000, 0x0000ff0101000100, + 0x0000ff0101000101, 0x0000ff01010100ff, 0x000000ffffff00ff, 0x000000ffffff0000, + 0x000000ffff00ff00, 0x000000ffff0000ff, 0x000000ffff000000, 0x000000ffff000001, + 0x000000ffff0001ff, 0x000000ffff000100, 0x000000ffff01ff00, 0x000000ffff010000, + 0x000000ffff0101ff, 0x000000ffff010101, 0x000000ff00ffff00, 0x000000ff00ff00ff, + 0x000000ff00ff0000, 0x000000ff00ff0001, 0x000000ff00ff0100, 0x000000ff00ff0101, + 0x000000ff0000ffff, 0x000000ff0000ff00, 0x000000ff000000ff, 0x000000ff00000000, + 0x000000ff00000001, 0x000000ff000001ff, 0x000000ff00000100, 0x000000ff00000101, + 0x000000ff0001ff00, 0x000000ff0001ff01, 0x000000ff000100ff, 0x000000ff00010000, + 0x000000ff00010001, 0x000000ff00010100, 0x000000ff01ffffff, 0x000000ff01ff01ff, + 0x000000ff01ff0101, 0x000000ff0100ff00, 0x000000ff010000ff, 0x000000ff01000000, + 0x000000ff01000001, 0x000000ff01000100, 0x000000ff0101ff00, 0x000000ff010100ff, + 0x000000ff01010000, 0x000000ff01010101, 0x00000000ffffff00, 0x00000000ffffff01, + 0x00000000ffff00ff, 0x00000000ffff0000, 0x00000000ffff0001, 0x00000000ffff0100, + 0x00000000ff00ffff, 0x00000000ff00ff00, 0x00000000ff00ff01, 0x00000000ff0000ff, + 0x00000000ff000000, 0x00000000ff000001, 0x00000000ff000100, 0x00000000ff000101, + 0x00000000ff01ff00, 0x00000000ff0100ff, 0x00000000ff010000, 0x00000000ff010001, + 0x00000000ff010100, 0x0000000000ffffff, 0x0000000000ffff00, 0x0000000000ffff01, + 0x0000000000ff00ff, 0x0000000000ff0000, 0x0000000000ff0001, 0x0000000000ff01ff, + 0x0000000000ff0100, 0x000000000000ffff, 0x000000000000ff00, 0x000000000000ff01, + 0x00000000000000ff, 0x0000000000000000, 0x0000000000000001, 0x00000000000001ff, + 0x0000000000000100, 0x0000000000000101, 0x000000000001ffff, 0x000000000001ff00, + 0x00000000000100ff, 0x0000000000010000, 0x0000000000010001, 0x00000000000101ff, + 0x0000000000010100, 0x0000000000010101, 0x0000000001ffff00, 0x0000000001ff00ff, + 0x0000000001ff0000, 0x0000000001ff0100, 0x0000000001ff0101, 0x000000000100ffff, + 0x000000000100ff00, 0x00000000010000ff, 0x0000000001000000, 0x0000000001000001, + 0x00000000010001ff, 0x0000000001000100, 0x000000000101ff00, 0x00000000010100ff, + 0x0000000001010000, 0x0000000001010001, 0x0000000001010100, 0x00000001ffffffff, + 0x00000001ffffff00, 0x00000001ffffff01, 0x00000001ffff00ff, 0x00000001ffff0001, + 0x00000001ffff01ff, 0x00000001ffff0100, 0x00000001ff00ff00, 0x00000001ff0000ff, + 0x00000001ff000000, 0x00000001ff0001ff, 0x00000001ff000100, 0x00000001ff01ffff, + 0x00000001ff01ff00, 0x00000001ff01ff01, 0x00000001ff0100ff, 0x00000001ff010000, + 0x00000001ff010001, 0x00000001ff0101ff, 0x00000001ff010100, 0x0000000100ffff00, + 0x0000000100ff0000, 0x0000000100ff0001, 0x0000000100ff01ff, 0x0000000100ff0100, + 0x0000000100ff0101, 0x000000010000ffff, 0x000000010000ff00, 0x000000010000ff01, + 0x00000001000000ff, 0x0000000100000000, 0x0000000100000001, 0x00000001000001ff, + 0x0000000100000100, 0x0000000100000101, 0x000000010001ff00, 0x00000001000100ff, + 0x0000000100010000, 0x0000000100010100, 0x0000000101ffff01, 0x0000000101ff0000, + 0x0000000101ff0001, 0x0000000101ff01ff, 0x0000000101ff0100, 0x0000000101ff0101, + 0x000000010100ff00, 0x0000000101000000, 0x0000000101000101, 0x000000010101ff01, + 0x0000000101010000, 0x0000000101010001, 0x00000001010101ff, 0x0000000101010100, + 0x000001ffffff00ff, 0x000001ffffff0000, 0x000001ffffff0001, 0x000001ffffff0100, + 0x000001ffff00ffff, 0x000001ffff000000, 0x000001ffff0001ff, 0x000001ffff01ff00, + 0x000001ffff010101, 0x000001ff00ff0000, 0x000001ff00ff01ff, 0x000001ff00ff0101, + 0x000001ff0000ff00, 0x000001ff000000ff, 0x000001ff00000000, 0x000001ff00000001, + 0x000001ff000001ff, 0x000001ff00000100, 0x000001ff0001ffff, 0x000001ff0001ff01, + 0x000001ff000100ff, 0x000001ff00010000, 0x000001ff01ffff01, 0x000001ff01ff0100, + 0x000001ff0100ffff, 0x000001ff0100ff01, 0x000001ff01000000, 0x000001ff010001ff, + 0x000001ff0101ff00, 0x000001ff01010100, 0x00000100ffffff00, 0x00000100ffffff01, + 0x00000100ffff0000, 0x00000100ffff0101, 0x00000100ff00ff00, 0x00000100ff0000ff, + 0x00000100ff000000, 0x00000100ff000001, 0x00000100ff000100, 0x00000100ff010000, + 0x0000010000ffff00, 0x0000010000ff00ff, 0x0000010000ff0000, 0x0000010000ff0001, + 0x0000010000ff0100, 0x000001000000ffff, 0x000001000000ff00, 0x000001000000ff01, + 0x00000100000000ff, 0x0000010000000000, 0x0000010000000001, 0x00000100000001ff, + 0x0000010000000100, 0x0000010000000101, 0x000001000001ff00, 0x00000100000100ff, + 0x0000010000010000, 0x0000010000010001, 0x0000010000010100, 0x0000010001ffff00, + 0x0000010001ff0000, 0x0000010001ff0100, 0x000001000100ff00, 0x00000100010000ff, + 0x0000010001000000, 0x0000010001000001, 0x00000100010001ff, 0x0000010001000100, + 0x0000010001010000, 0x00000101ffff00ff, 0x00000101ffff01ff, 0x00000101ff000000, + 0x00000101ff000101, 0x00000101ff01ffff, 0x00000101ff010000, 0x00000101ff010001, + 0x00000101ff010100, 0x0000010100ff0000, 0x0000010100ff01ff, 0x0000010100ff0100, + 0x000001010000ff00, 0x0000010100000000, 0x0000010100000001, 0x00000101000001ff, + 0x0000010100000100, 0x000001010001ff01, 0x0000010100010000, 0x00000101000101ff, + 0x0000010100010101, 0x0000010101ffff00, 0x0000010101ff0101, 0x000001010100ff01, + 0x0000010101000000, 0x0000010101000001, 0x00000101010001ff, 0x0000010101000101, + 0x000001010101ff00, 0x0001ffffffff0000, 0x0001ffffff0000ff, 0x0001ffffff000001, + 0x0001ffffff000100, 0x0001ffffff010000, 0x0001ffff00ff00ff, 0x0001ffff0000ffff, + 0x0001ffff00000000, 0x0001ffff00000001, 0x0001ffff000001ff, 0x0001ffff00000101, + 0x0001ffff0001ff00, 0x0001ffff000100ff, 0x0001ffff00010001, 0x0001ffff00010100, + 0x0001ffff01ffff00, 0x0001ffff01000001, 0x0001ffff01010000, 0x0001ff00ffffff00, + 0x0001ff00ffff00ff, 0x0001ff00ffff0001, 0x0001ff00ffff0100, 0x0001ff00ff00ff01, + 0x0001ff00ff000000, 0x0001ff00ff01ff00, 0x0001ff00ff01ff01, 0x0001ff00ff010001, + 0x0001ff00ff010100, 0x0001ff0000ff0000, 0x0001ff0000ff0100, 0x0001ff000000ff00, + 0x0001ff0000000000, 0x0001ff0000000001, 0x0001ff0000000100, 0x0001ff0000010000, + 0x0001ff0000010001, 0x0001ff0000010101, 0x0001ff0001ff00ff, 0x0001ff0001ff0101, + 0x0001ff000100ff01, 0x0001ff0001000000, 0x0001ff000101ff00, 0x0001ff0001010001, + 0x0001ff0001010100, 0x0001ff01ff00ff00, 0x0001ff01ff000001, 0x0001ff01ff000100, + 0x0001ff0100ffffff, 0x0001ff0100ffff00, 0x0001ff0100ff0001, 0x0001ff0100000000, + 0x0001ff0100000001, 0x0001ff01000001ff, 0x0001ff010001ffff, 0x0001ff0101ff0000, + 0x0001ff010100ff00, 0x0001ff0101000001, 0x0001ff0101010000, 0x000100ffff00ff00, + 0x000100ffff00ff01, 0x000100ffff000000, 0x000100ffff000001, 0x000100ffff000101, + 0x000100ffff01ff00, 0x000100ffff010001, 0x000100ffff010100, 0x000100ff00ffffff, + 0x000100ff00ffff01, 0x000100ff00ff0000, 0x000100ff00ff01ff, 0x000100ff00ff0101, + 0x000100ff0000ff00, 0x000100ff000000ff, 0x000100ff00000000, 0x000100ff00000001, + 0x000100ff00000100, 0x000100ff00000101, 0x000100ff0001ffff, 0x000100ff0001ff01, + 0x000100ff00010000, 0x000100ff01ff00ff, 0x000100ff01ff0000, 0x000100ff01ff0100, + 0x000100ff0100ffff, 0x000100ff0100ff01, 0x000100ff010000ff, 0x000100ff01000000, + 0x000100ff01000001, 0x000100ff010001ff, 0x000100ff01000101, 0x000100ff0101ff00, + 0x000100ff010100ff, 0x000100ff01010100, 0x00010000ffff0000, 0x00010000ffff01ff, + 0x00010000ffff0101, 0x00010000ff00ff00, 0x00010000ff000000, 0x00010000ff000001, + 0x00010000ff000100, 0x0001000000ff00ff, 0x0001000000ff0000, 0x0001000000ff0001, + 0x0001000000ff0100, 0x000100000000ffff, 0x000100000000ff00, 0x00010000000000ff, + 0x0001000000000000, 0x0001000000000001, 0x0001000000000100, 0x000100000001ff00, + 0x00010000000100ff, 0x0001000000010000, 0x0001000000010001, 0x0001000000010100, + 0x0001000001ff0001, 0x0001000001ff0100, 0x0001000001ff0101, 0x000100000100ff00, + 0x0001000001000000, 0x0001000001000001, 0x0001000001000100, 0x0001000001000101, + 0x000100000101ff01, 0x0001000001010000, 0x0001000001010001, 0x00010000010101ff, + 0x00010001ffffff01, 0x00010001ffff0100, 0x00010001ff000000, 0x00010001ff01ffff, + 0x00010001ff010001, 0x00010001ff0101ff, 0x00010001ff010100, 0x0001000100ffffff, + 0x0001000100ff0000, 0x0001000100ff01ff, 0x0001000100ff0101, 0x000100010000ff00, + 0x00010001000000ff, 0x0001000100000000, 0x0001000100000001, 0x00010001000001ff, + 0x0001000100000101, 0x000100010001ffff, 0x0001000100010000, 0x00010001000101ff, + 0x0001000101ffffff, 0x0001000101ffff01, 0x0001000101ff0000, 0x0001000101ff0101, + 0x00010001010000ff, 0x0001000101000001, 0x00010001010001ff, 0x0001000101000100, + 0x000100010101ffff, 0x00010001010100ff, 0x0001000101010001, 0x0001000101010101, + 0x000101ffff000001, 0x000101ffff000100, 0x000101ffff010000, 0x000101ff00ffff00, + 0x000101ff0000ff01, 0x000101ff00000000, 0x000101ff00000101, 0x000101ff0001ff00, + 0x000101ff00010100, 0x000101ff01ff0000, 0x000101ff0100ff00, 0x000101ff010001ff, + 0x000101ff01010001, 0x00010100ffffff00, 0x00010100ffff00ff, 0x00010100ff00ffff, + 0x00010100ff000000, 0x00010100ff01ff00, 0x00010100ff0100ff, 0x00010100ff010001, + 0x00010100ff010100, 0x0001010000ffffff, 0x0001010000ffff00, 0x0001010000ff0000, + 0x0001010000ff0001, 0x0001010000ff01ff, 0x000101000000ff00, 0x00010100000000ff, + 0x0001010000000000, 0x0001010000000001, 0x0001010000000100, 0x000101000001ffff, + 0x0001010000010000, 0x0001010000010101, 0x0001010001ffff01, 0x0001010001ff00ff, + 0x0001010001ff0101, 0x0001010001000000, 0x000101000101ff00, 0x00010100010100ff, + 0x0001010001010000, 0x0001010001010100, 0x00010101ff00ff00, 0x00010101ff000001, + 0x00010101ff0001ff, 0x0001010100ffff00, 0x0001010100ff00ff, 0x0001010100ff0100, + 0x000101010000ffff, 0x0001010100000000, 0x00010101000001ff, 0x0001010100000101, + 0x00010101000100ff, 0x0001010100010000, 0x0001010100010100, 0x0001010101ff0001, + 0x00010101010000ff, 0x00010101010001ff, 0x0001010101000101, 0x0001010101010001, + 0x01ffffffffffffff, 0x01ffffffffffff01, 0x01ffffffffff01ff, 0x01ffffffffff0101, + 0x01ffffffff01ffff, 0x01ffffffff01ff01, 0x01ffffffff0101ff, 0x01ffffffff010101, + 0x01ffffff00ff0000, 0x01ffffff0000ffff, 0x01ffffff0000ff00, 0x01ffffff000000ff, + 0x01ffffff00000001, 0x01ffffff00000100, 0x01ffffff00010000, 0x01ffffff01ffffff, + 0x01ffffff01ffff01, 0x01ffffff01ff01ff, 0x01ffffff01ff0101, 0x01ffffff01000000, + 0x01ffffff0101ffff, 0x01ffffff0101ff01, 0x01ffffff010101ff, 0x01ffffff01010101, + 0x01ffff00ffff0000, 0x01ffff00ff00ff00, 0x01ffff00ff0000ff, 0x01ffff00ff000001, + 0x01ffff00ff000100, 0x01ffff00ff010000, 0x01ffff0000ffff00, 0x01ffff0000ff00ff, + 0x01ffff0000ff0100, 0x01ffff000000ffff, 0x01ffff000000ff01, 0x01ffff0000000000, + 0x01ffff0000000001, 0x01ffff00000001ff, 0x01ffff0000000100, 0x01ffff00000100ff, + 0x01ffff0000010001, 0x01ffff0000010100, 0x01ffff0001ff0000, 0x01ffff0001ff0100, + 0x01ffff00010000ff, 0x01ffff0001000001, 0x01ffff0001000100, 0x01ffff0001010000, + 0x01ffff01ffffffff, 0x01ffff01ffffff01, 0x01ffff01ffff01ff, 0x01ffff01ffff0101, + 0x01ffff01ff000000, 0x01ffff01ff01ffff, 0x01ffff01ff01ff01, 0x01ffff01ff0101ff, + 0x01ffff01ff010101, 0x01ffff010000ff00, 0x01ffff01000000ff, 0x01ffff0100000100, + 0x01ffff0100010000, 0x01ffff0101ffffff, 0x01ffff0101ffff01, 0x01ffff0101ff01ff, + 0x01ffff0101ff0101, 0x01ffff0101000000, 0x01ffff010101ffff, 0x01ffff010101ff01, + 0x01ffff01010101ff, 0x01ffff0101010101, 0x01ff00ffff0000ff, 0x01ff00ffff000100, + 0x01ff00ff00ffff00, 0x01ff00ff00ff00ff, 0x01ff00ff0000ff00, 0x01ff00ff00000000, + 0x01ff00ff00000101, 0x01ff00ff0001ff00, 0x01ff00ff000100ff, 0x01ff00ff00010100, + 0x01ff00ff010000ff, 0x01ff00ff01000100, 0x01ff0000ffffff00, 0x01ff0000ffff0100, + 0x01ff0000ff00ff01, 0x01ff0000ff000000, 0x01ff0000ff000101, 0x01ff0000ff010001, + 0x01ff0000ff010100, 0x01ff000000ffffff, 0x01ff000000ffff00, 0x01ff000000ff0000, + 0x01ff000000ff01ff, 0x01ff00000000ff00, 0x01ff0000000000ff, 0x01ff000000000000, + 0x01ff000000000001, 0x01ff000000000100, 0x01ff000000000101, 0x01ff000000010000, + 0x01ff000000010001, 0x01ff0000000101ff, 0x01ff000000010101, 0x01ff000001ffff00, + 0x01ff000001ff00ff, 0x01ff000001ff0001, 0x01ff000001ff0100, 0x01ff00000100ffff, + 0x01ff00000100ff01, 0x01ff000001000000, 0x01ff0000010001ff, 0x01ff000001010001, + 0x01ff0001ff00ff00, 0x01ff0001ff000001, 0x01ff0001ff000100, 0x01ff0001ff010000, + 0x01ff000100ffff00, 0x01ff000100ff00ff, 0x01ff000100ff0100, 0x01ff000100ff0101, + 0x01ff00010000ffff, 0x01ff000100000000, 0x01ff000100000100, 0x01ff000100000101, + 0x01ff00010001ff00, 0x01ff000100010001, 0x01ff000100010101, 0x01ff000101ff0000, + 0x01ff00010100ff00, 0x01ff000101000101, 0x01ff0001010100ff, 0x01ff01ffffffffff, + 0x01ff01ffffffff01, 0x01ff01ffffff01ff, 0x01ff01ffffff0101, 0x01ff01ffff000000, + 0x01ff01ffff01ffff, 0x01ff01ffff01ff01, 0x01ff01ffff0101ff, 0x01ff01ffff010101, + 0x01ff01ff00ffff00, 0x01ff01ff00ff0000, 0x01ff01ff0000ff00, 0x01ff01ff000000ff, + 0x01ff01ff00000100, 0x01ff01ff00010000, 0x01ff01ff00010100, 0x01ff01ff01ffffff, + 0x01ff01ff01ffff01, 0x01ff01ff01ff01ff, 0x01ff01ff01ff0101, 0x01ff01ff01000000, + 0x01ff01ff0101ffff, 0x01ff01ff0101ff01, 0x01ff01ff010101ff, 0x01ff01ff01010101, + 0x01ff0100ffff0000, 0x01ff0100ffff0001, 0x01ff0100ff00ff00, 0x01ff0100ff0000ff, + 0x01ff0100ff000001, 0x01ff0100ff010000, 0x01ff010000ffff00, 0x01ff010000ff00ff, + 0x01ff010000ff0001, 0x01ff010000ff0100, 0x01ff01000000ffff, 0x01ff01000000ff01, + 0x01ff010000000000, 0x01ff010000000101, 0x01ff01000001ff00, 0x01ff0100000100ff, + 0x01ff010001ff0000, 0x01ff010001000001, 0x01ff010001000100, 0x01ff010001010000, + 0x01ff0101ffffffff, 0x01ff0101ffffff01, 0x01ff0101ffff01ff, 0x01ff0101ffff0101, + 0x01ff0101ff000000, 0x01ff0101ff01ffff, 0x01ff0101ff01ff01, 0x01ff0101ff0101ff, + 0x01ff0101ff010101, 0x01ff010100ff0000, 0x01ff01010000ff00, 0x01ff0101000000ff, + 0x01ff010100000001, 0x01ff010101ffffff, 0x01ff010101ffff01, 0x01ff010101ff01ff, + 0x01ff010101ff0101, 0x01ff010101000000, 0x01ff01010101ffff, 0x01ff01010101ff01, + 0x01ff0101010101ff, 0x01ff010101010101, 0x0100ffffffff0000, 0x0100ffffff00ff00, + 0x0100ffffff000001, 0x0100ffffff0001ff, 0x0100ffffff000100, 0x0100ffffff010000, + 0x0100ffff00ffff00, 0x0100ffff00ff0001, 0x0100ffff00ff0100, 0x0100ffff00000000, + 0x0100ffff000001ff, 0x0100ffff00000101, 0x0100ffff00010100, 0x0100ffff00010101, + 0x0100ffff01ff0000, 0x0100ffff0100ff00, 0x0100ffff010000ff, 0x0100ffff01000001, + 0x0100ffff01000100, 0x0100ffff01010000, 0x0100ff00ffffff00, 0x0100ff00ffff00ff, + 0x0100ff00ffff0001, 0x0100ff00ffff0100, 0x0100ff00ff00ffff, 0x0100ff00ff000000, + 0x0100ff00ff0001ff, 0x0100ff00ff000101, 0x0100ff00ff01ff00, 0x0100ff00ff0100ff, + 0x0100ff00ff010001, 0x0100ff00ff010100, 0x0100ff0000ffffff, 0x0100ff0000ff0000, + 0x0100ff000000ffff, 0x0100ff000000ff00, 0x0100ff00000000ff, 0x0100ff0000000000, + 0x0100ff0000000001, 0x0100ff0000000100, 0x0100ff000001ff01, 0x0100ff0000010000, + 0x0100ff0001ff00ff, 0x0100ff0001ff0001, 0x0100ff000100ff01, 0x0100ff0001000000, + 0x0100ff00010001ff, 0x0100ff000101ff00, 0x0100ff00010100ff, 0x0100ff0001010001, + 0x0100ff0001010100, 0x0100ff01ffff0000, 0x0100ff01ff00ff00, 0x0100ff01ff0000ff, + 0x0100ff01ff000100, 0x0100ff01ff010000, 0x0100ff0100ff00ff, 0x0100ff0100ff0001, + 0x0100ff0100ff0100, 0x0100ff010000ffff, 0x0100ff010000ff01, 0x0100ff0100000000, + 0x0100ff01000001ff, 0x0100ff0100010001, 0x0100ff0100010100, 0x0100ff0101ff0000, + 0x0100ff01010000ff, 0x0100ff0101000001, 0x0100ff0101010100, 0x010000ffffffff00, + 0x010000ffffff00ff, 0x010000ffffff0001, 0x010000ffff00ffff, 0x010000ffff000000, + 0x010000ffff0001ff, 0x010000ffff010001, 0x010000ff00ffffff, 0x010000ff00ff0101, + 0x010000ff0000ff00, 0x010000ff000000ff, 0x010000ff00000000, 0x010000ff00000001, + 0x010000ff000001ff, 0x010000ff00000100, 0x010000ff0001ffff, 0x010000ff0001ff00, + 0x010000ff0001ff01, 0x010000ff00010000, 0x010000ff01ff00ff, 0x010000ff01ff0001, + 0x010000ff0100ff01, 0x010000ff010000ff, 0x010000ff01000000, 0x010000ff010001ff, + 0x010000ff0101ff00, 0x010000ff01010100, 0x01000000ffffffff, 0x01000000ffff0000, + 0x01000000ffff01ff, 0x01000000ffff0101, 0x01000000ff00ffff, 0x01000000ff00ff00, + 0x01000000ff0000ff, 0x01000000ff000000, 0x01000000ff000001, 0x01000000ff000100, + 0x01000000ff01ff00, 0x01000000ff010000, 0x01000000ff010100, 0x01000000ff010101, + 0x0100000000ffff00, 0x0100000000ff00ff, 0x0100000000ff0000, 0x0100000000ff0001, + 0x0100000000ff0100, 0x010000000000ffff, 0x010000000000ff00, 0x010000000000ff01, + 0x01000000000000ff, 0x0100000000000000, 0x0100000000000001, 0x01000000000001ff, + 0x0100000000000100, 0x0100000000000101, 0x010000000001ff00, 0x01000000000100ff, + 0x0100000000010000, 0x0100000000010001, 0x0100000000010100, 0x0100000001ffff00, + 0x0100000001ff0000, 0x0100000001ff01ff, 0x010000000100ff00, 0x010000000100ff01, + 0x01000000010000ff, 0x0100000001000000, 0x0100000001000001, 0x0100000001000100, + 0x0100000001000101, 0x010000000101ffff, 0x010000000101ff01, 0x0100000001010000, + 0x01000000010101ff, 0x0100000001010101, 0x01000001ffffff00, 0x01000001ffff00ff, + 0x01000001ff00ffff, 0x01000001ff000000, 0x01000001ff000100, 0x01000001ff01ffff, + 0x01000001ff010001, 0x01000001ff010100, 0x0100000100ff0000, 0x0100000100ff01ff, + 0x0100000100ff0100, 0x010000010000ff00, 0x010000010000ff01, 0x0100000100000000, + 0x0100000100000001, 0x0100000100000100, 0x0100000100010000, 0x01000001000101ff, + 0x0100000101ffff01, 0x0100000101ff00ff, 0x0100000101ff0100, 0x0100000101ff0101, + 0x010000010100ff01, 0x01000001010000ff, 0x0100000101000000, 0x01000001010100ff, + 0x0100000101010001, 0x0100000101010100, 0x010001ffffff0000, 0x010001ffff000001, + 0x010001ffff000100, 0x010001ffff010000, 0x010001ff00ffff00, 0x010001ff00ff0001, + 0x010001ff0000ffff, 0x010001ff0000ff01, 0x010001ff00000000, 0x010001ff00000001, + 0x010001ff00000101, 0x010001ff000100ff, 0x010001ff00010000, 0x010001ff01ff0000, + 0x010001ff0100ff00, 0x010001ff01000001, 0x010001ff01000100, 0x010001ff01010000, + 0x01000100ffff00ff, 0x01000100ffff0001, 0x01000100ffff0100, 0x01000100ff00ffff, + 0x01000100ff00ff01, 0x01000100ff000000, 0x01000100ff0001ff, 0x01000100ff000101, + 0x01000100ff01ffff, 0x01000100ff01ff00, 0x01000100ff0100ff, 0x01000100ff010001, + 0x0100010000ffffff, 0x0100010000ffff01, 0x0100010000ff0000, 0x0100010000ff01ff, + 0x0100010000ff0101, 0x010001000000ff00, 0x01000100000000ff, 0x0100010000000000, + 0x0100010000000001, 0x0100010000000100, 0x010001000001ff01, 0x0100010000010000, + 0x0100010000010001, 0x0100010000010101, 0x0100010001ffff00, 0x0100010001ff00ff, + 0x010001000100ffff, 0x010001000100ff01, 0x0100010001000000, 0x0100010001000101, + 0x010001000101ff00, 0x0100010001010001, 0x01000101ffff0000, 0x01000101ff000000, + 0x01000101ff010000, 0x0100010100ff00ff, 0x0100010100ff0001, 0x0100010100ff0100, + 0x010001010000ffff, 0x0100010100000000, 0x01000101000001ff, 0x010001010001ff00, + 0x0100010101ff0000, 0x010001010100ff00, 0x01000101010000ff, 0x0100010101000000, + 0x0100010101000001, 0x0101ffffffffffff, 0x0101ffffffffff01, 0x0101ffffffff01ff, + 0x0101ffffffff0101, 0x0101ffffff000000, 0x0101ffffff01ffff, 0x0101ffffff01ff01, + 0x0101ffffff0101ff, 0x0101ffffff010101, 0x0101ffff00ff0000, 0x0101ffff0000ff00, + 0x0101ffff000000ff, 0x0101ffff00000001, 0x0101ffff00000100, 0x0101ffff01ffffff, + 0x0101ffff01ffff01, 0x0101ffff01ff01ff, 0x0101ffff01ff0101, 0x0101ffff01000000, + 0x0101ffff0101ffff, 0x0101ffff0101ff01, 0x0101ffff010101ff, 0x0101ffff01010101, + 0x0101ff00ffff0000, 0x0101ff00ffff0100, 0x0101ff00ff00ff00, 0x0101ff00ff0000ff, + 0x0101ff00ff000001, 0x0101ff00ff000100, 0x0101ff00ff000101, 0x0101ff0000ff0001, + 0x0101ff0000ff0100, 0x0101ff000000ff00, 0x0101ff0000000000, 0x0101ff00000001ff, + 0x0101ff0000000101, 0x0101ff000001ff00, 0x0101ff00000100ff, 0x0101ff0001ff0000, + 0x0101ff000100ffff, 0x0101ff000100ff01, 0x0101ff0001000001, 0x0101ff0001000100, + 0x0101ff01ffffff01, 0x0101ff01ffff01ff, 0x0101ff01ffff0101, 0x0101ff01ff00ffff, + 0x0101ff01ff000100, 0x0101ff01ff01ff01, 0x0101ff01ff0101ff, 0x0101ff01ff010101, + 0x0101ff0100ff0000, 0x0101ff010000ff00, 0x0101ff0100000001, 0x0101ff0100000100, + 0x0101ff0100010000, 0x0101ff0101ffffff, 0x0101ff0101ffff01, 0x0101ff0101ff01ff, + 0x0101ff0101ff0101, 0x0101ff0101000000, 0x0101ff010101ffff, 0x0101ff010101ff01, + 0x0101ff01010101ff, 0x0101ff0101010101, 0x010100ffff000100, 0x010100ffff010000, + 0x010100ff00ffff00, 0x010100ff00ff00ff, 0x010100ff0000ffff, 0x010100ff000000ff, + 0x010100ff00000000, 0x010100ff000001ff, 0x010100ff00000101, 0x010100ff0001ff00, + 0x010100ff00010000, 0x010100ff00010001, 0x010100ff000101ff, 0x010100ff00010100, + 0x010100ff01ff0000, 0x01010000ffff0001, 0x01010000ffff0100, 0x01010000ff00ffff, + 0x01010000ff00ff01, 0x01010000ff000000, 0x01010000ff0001ff, 0x01010000ff010001, + 0x01010000ff010100, 0x0101000000ffff01, 0x0101000000ff0000, 0x010100000000ff00, + 0x01010000000000ff, 0x0101000000000000, 0x0101000000000001, 0x0101000000000100, + 0x0101000000010000, 0x0101000000010101, 0x0101000001ffff00, 0x0101000001ff00ff, + 0x0101000001ff0000, 0x0101000001ff0001, 0x0101000001ff0100, 0x010100000100ff01, + 0x0101000001000000, 0x01010000010001ff, 0x01010001ffff0000, 0x01010001ff00ff00, + 0x01010001ff000001, 0x01010001ff000101, 0x01010001ff01ff00, 0x01010001ff010000, + 0x0101000100ff00ff, 0x0101000100ff0001, 0x0101000100ff0101, 0x010100010000ff01, + 0x0101000100000000, 0x0101000100000001, 0x01010001000001ff, 0x010100010001ffff, + 0x010100010001ff01, 0x0101000101ff0001, 0x010100010100ffff, 0x0101000101000000, + 0x0101000101000001, 0x0101000101000100, 0x010100010101ff00, 0x01010001010100ff, + 0x0101000101010001, 0x010101ffffffffff, 0x010101ffffffff01, 0x010101ffffff01ff, + 0x010101ffffff0101, 0x010101ffff01ffff, 0x010101ffff01ff01, 0x010101ffff0101ff, + 0x010101ffff010101, 0x010101ff0000ff00, 0x010101ff000000ff, 0x010101ff00000001, + 0x010101ff00000100, 0x010101ff01ffffff, 0x010101ff01ffff01, 0x010101ff01ff01ff, + 0x010101ff01ff0101, 0x010101ff01000000, 0x010101ff0101ffff, 0x010101ff0101ff01, + 0x010101ff010101ff, 0x010101ff01010101, 0x01010100ffff0000, 0x01010100ff0000ff, + 0x01010100ff000100, 0x01010100ff01ff00, 0x01010100ff010000, 0x0101010000ffff00, + 0x010101000000ffff, 0x0101010000000000, 0x0101010000000101, 0x010101000001ff00, + 0x0101010000010001, 0x0101010000010100, 0x010101000100ffff, 0x0101010001000001, + 0x01010101ffffffff, 0x01010101ffffff01, 0x01010101ffff01ff, 0x01010101ffff0101, + 0x01010101ff01ffff, 0x01010101ff01ff01, 0x01010101ff0101ff, 0x01010101ff010101, + 0x010101010000ff00, 0x01010101000000ff, 0x0101010100000001, 0x0101010101ffffff, + 0x0101010101ffff01, 0x0101010101ff01ff, 0x0101010101ff0101, 0x0101010101000000, + 0x010101010101ffff, 0x010101010101ff01, 0x01010101010101ff, 0x0101010101010101, +GGML_TABLE_END() +#else +GGML_TABLE_BEGIN(uint32_t, iq1s_grid_gpu, NGRID_IQ1S) + 0x00000000, 0x00000002, 0x00000101, 0x00000200, 0x00000202, 0x00010001, 0x00010101, 0x00020000, + 0x00020002, 0x00020200, 0x00020202, 0x01000101, 0x01010001, 0x01010100, 0x01010102, 0x01020101, + 0x02000000, 0x02000002, 0x02000200, 0x02000202, 0x02010101, 0x02020000, 0x02020002, 0x02020200, + 0x02020202, 0x00000110, 0x00000111, 0x00010011, 0x00010110, 0x00010112, 0x00010211, 0x00010212, + 0x00020111, 0x01000011, 0x01000112, 0x01000211, 0x01010012, 0x01010111, 0x01010212, 0x01020011, + 0x01020110, 0x01020112, 0x01020210, 0x02000111, 0x02010011, 0x02010110, 0x02010112, 0x02020111, + 0x00000020, 0x00000022, 0x00000220, 0x00000222, 0x00010121, 0x00020020, 0x00020022, 0x00020220, + 0x00020222, 0x01000121, 0x01010021, 0x01010221, 0x01020120, 0x01020221, 0x02000020, 0x02000022, + 0x02000220, 0x02000222, 0x02010021, 0x02010121, 0x02010221, 0x02020020, 0x02020022, 0x02020220, + 0x02020222, 0x00011001, 0x00011100, 0x00011102, 0x00021101, 0x01001001, 0x01001201, 0x01011101, + 0x01011202, 0x01021100, 0x01021101, 0x02011001, 0x02011201, 0x02021101, 0x00001011, 0x00001110, + 0x00001111, 0x00001112, 0x00011111, 0x00011210, 0x00011212, 0x00021211, 0x01001010, 0x01001111, + 0x01001212, 0x01011010, 0x01011011, 0x01011110, 0x01011111, 0x01011112, 0x01011211, 0x01021010, + 0x01021012, 0x01021111, 0x01021210, 0x01021212, 0x02001011, 0x02011011, 0x02011111, 0x02011210, + 0x02011212, 0x02021011, 0x02021110, 0x02021111, 0x02021112, 0x02021211, 0x00011120, 0x00011221, + 0x01001021, 0x01001120, 0x01011020, 0x01011022, 0x01011121, 0x01011220, 0x01021020, 0x01021021, + 0x01021122, 0x01021221, 0x02001121, 0x02011021, 0x02011120, 0x02011221, 0x00002000, 0x00002002, + 0x00002200, 0x00002202, 0x00012101, 0x00022000, 0x00022002, 0x00022200, 0x00022202, 0x01002101, + 0x01012001, 0x01012102, 0x01022101, 0x02002000, 0x02002002, 0x02002200, 0x02002202, 0x02012101, + 0x02022000, 0x02022002, 0x02022200, 0x02022202, 0x00002111, 0x00012011, 0x00012110, 0x00012211, + 0x00022110, 0x00022111, 0x01002011, 0x01012010, 0x01012011, 0x01012111, 0x01022011, 0x01022110, + 0x01022211, 0x02012011, 0x02012110, 0x02012112, 0x02012211, 0x02022111, 0x00002020, 0x00002022, + 0x00002220, 0x00002222, 0x00012121, 0x00022020, 0x00022022, 0x00022220, 0x00022222, 0x01002121, + 0x01012021, 0x01012221, 0x01022021, 0x01022121, 0x02002020, 0x02002022, 0x02002121, 0x02002220, + 0x02002222, 0x02012121, 0x02022020, 0x02022022, 0x02022220, 0x02022222, 0x00110000, 0x00110001, + 0x00110100, 0x00110201, 0x00120100, 0x00120101, 0x01100001, 0x01100100, 0x01110000, 0x01110101, + 0x01110200, 0x01120001, 0x01120100, 0x01120101, 0x01120201, 0x02110001, 0x02110100, 0x02110102, + 0x02120001, 0x02120101, 0x00100011, 0x00100110, 0x00100112, 0x00100211, 0x00110010, 0x00110012, + 0x00110111, 0x00110210, 0x00120011, 0x00120110, 0x00120211, 0x01100111, 0x01100212, 0x01110010, + 0x01110011, 0x01110012, 0x01110110, 0x01110111, 0x01110112, 0x01110211, 0x01120010, 0x01120111, + 0x02100110, 0x02110012, 0x02110111, 0x02120011, 0x02120110, 0x00110021, 0x00110120, 0x00110122, + 0x00120121, 0x01100020, 0x01100122, 0x01100221, 0x01110022, 0x01110121, 0x01110220, 0x01110222, + 0x01120120, 0x01120122, 0x02100121, 0x02110021, 0x02110120, 0x02110122, 0x02120121, 0x00101001, + 0x00101102, 0x00101201, 0x00111100, 0x00111101, 0x00111200, 0x00111201, 0x00121001, 0x00121102, + 0x01101001, 0x01101101, 0x01101102, 0x01101200, 0x01101202, 0x01111001, 0x01111100, 0x01111101, + 0x01111102, 0x01111201, 0x01121002, 0x01121101, 0x01121200, 0x02101100, 0x02101201, 0x02111000, + 0x02111100, 0x02111101, 0x02111200, 0x02111201, 0x02111202, 0x02121001, 0x02121100, 0x02121101, + 0x02121201, 0x00101012, 0x00101111, 0x00101212, 0x00111011, 0x00111110, 0x00111111, 0x00111112, + 0x00111211, 0x00121010, 0x00121012, 0x00121111, 0x00121210, 0x00121212, 0x01101011, 0x01101110, + 0x01101111, 0x01101112, 0x01111011, 0x01111012, 0x01111110, 0x01111111, 0x01111112, 0x01111211, + 0x01111212, 0x01121011, 0x01121110, 0x01121111, 0x01121112, 0x01121211, 0x02101010, 0x02101012, + 0x02101110, 0x02101111, 0x02101210, 0x02101212, 0x02111010, 0x02111011, 0x02111110, 0x02111111, + 0x02111112, 0x02111211, 0x02111212, 0x02121010, 0x02121012, 0x02121111, 0x00101021, 0x00101120, + 0x00101121, 0x00101122, 0x00111121, 0x00111122, 0x00111220, 0x00111222, 0x00121021, 0x00121122, + 0x01101020, 0x01101022, 0x01101120, 0x01101121, 0x01101220, 0x01101222, 0x01111021, 0x01111121, + 0x01111122, 0x01111220, 0x01111221, 0x01121021, 0x01121120, 0x01121121, 0x01121220, 0x01121221, + 0x01121222, 0x02101122, 0x02101222, 0x02111022, 0x02111121, 0x02121120, 0x02121221, 0x00112001, + 0x00112102, 0x00122101, 0x01102001, 0x01102100, 0x01102102, 0x01102201, 0x01112000, 0x01112101, + 0x01112200, 0x01112202, 0x01122000, 0x01122001, 0x01122100, 0x01122102, 0x01122201, 0x02102101, + 0x02112001, 0x02112100, 0x02122101, 0x00112010, 0x00112012, 0x00112111, 0x00112212, 0x00122011, + 0x00122111, 0x01102012, 0x01102110, 0x01102111, 0x01102210, 0x01112011, 0x01112110, 0x01112111, + 0x01112112, 0x01112211, 0x01112212, 0x01122010, 0x01122111, 0x01122212, 0x02102211, 0x02112011, + 0x02112012, 0x02112111, 0x02112210, 0x02122011, 0x02122112, 0x02122211, 0x00102221, 0x00112122, + 0x00122120, 0x00122122, 0x01102120, 0x01102122, 0x01102221, 0x01112020, 0x01112022, 0x01112121, + 0x01112220, 0x01122021, 0x01122122, 0x01122221, 0x02102121, 0x02112021, 0x02112122, 0x02112222, + 0x00200000, 0x00200002, 0x00200200, 0x00200202, 0x00210101, 0x00220000, 0x00220002, 0x00220101, + 0x00220200, 0x00220202, 0x01200101, 0x01210001, 0x01210201, 0x01220001, 0x01220101, 0x02200000, + 0x02200002, 0x02200200, 0x02200202, 0x02210101, 0x02220000, 0x02220002, 0x02220101, 0x02220200, + 0x02220202, 0x00200111, 0x00210011, 0x00210110, 0x00210211, 0x00220111, 0x01200012, 0x01200110, + 0x01200211, 0x01210111, 0x01210210, 0x01210212, 0x01220011, 0x01220110, 0x01220111, 0x01220112, + 0x02200111, 0x02210010, 0x02210112, 0x02210211, 0x02220111, 0x00200021, 0x00200220, 0x00200222, + 0x00210021, 0x00210121, 0x00220020, 0x00220022, 0x00220220, 0x00220222, 0x01200121, 0x01210021, + 0x01210122, 0x01210221, 0x01220121, 0x02200021, 0x02200220, 0x02200222, 0x02210021, 0x02210121, + 0x02220020, 0x02220022, 0x02220220, 0x02220222, 0x00201101, 0x00211100, 0x00211102, 0x00211201, + 0x00221101, 0x01201100, 0x01201101, 0x01201102, 0x01201201, 0x01211002, 0x01211101, 0x01211200, + 0x01211202, 0x01221102, 0x02201101, 0x02211001, 0x02211100, 0x02211201, 0x02221001, 0x02221101, + 0x00201211, 0x00211111, 0x00221011, 0x00221211, 0x01201010, 0x01201111, 0x01201210, 0x01211011, + 0x01211110, 0x01211111, 0x01211211, 0x01221012, 0x01221111, 0x01221210, 0x02201211, 0x02211010, + 0x02211110, 0x02211111, 0x02211210, 0x02211212, 0x02221011, 0x02221110, 0x02221112, 0x02221211, + 0x00201121, 0x00211020, 0x00211022, 0x00211221, 0x00221121, 0x01201021, 0x01201221, 0x01211121, + 0x01221020, 0x01221021, 0x01221221, 0x02201120, 0x02201122, 0x02211020, 0x02211222, 0x00202000, + 0x00202002, 0x00202200, 0x00202202, 0x00212101, 0x00222000, 0x00222002, 0x00222200, 0x00222202, + 0x01202101, 0x01212001, 0x01212100, 0x01222101, 0x02202000, 0x02202002, 0x02202200, 0x02202202, + 0x02222000, 0x02222002, 0x02222200, 0x02222202, 0x00202211, 0x00212011, 0x00212110, 0x00212211, + 0x00222111, 0x01202112, 0x01202211, 0x01212012, 0x01212111, 0x01222011, 0x01222110, 0x01222112, + 0x01222211, 0x02202111, 0x02212010, 0x02212112, 0x02212211, 0x02222110, 0x02222111, 0x00202020, + 0x00202022, 0x00202220, 0x00202222, 0x00222020, 0x00222022, 0x00222220, 0x00222222, 0x01202121, + 0x01212021, 0x01212122, 0x01212221, 0x01222121, 0x02202020, 0x02202022, 0x02202220, 0x02202222, + 0x02212121, 0x02222020, 0x02222022, 0x02222220, 0x02222222, 0x10000101, 0x10010001, 0x10010102, + 0x10020101, 0x11000201, 0x11010002, 0x11010101, 0x11010200, 0x11010202, 0x11020001, 0x11020100, + 0x11020102, 0x12010100, 0x12010201, 0x12020001, 0x12020102, 0x10000010, 0x10000011, 0x10000110, + 0x10000112, 0x10000211, 0x10010012, 0x10010111, 0x10010112, 0x10010210, 0x10010212, 0x10020011, + 0x10020112, 0x10020211, 0x11000111, 0x11000210, 0x11000212, 0x11010011, 0x11010110, 0x11010111, + 0x11010112, 0x11010211, 0x11010212, 0x11020111, 0x11020210, 0x11020212, 0x12000011, 0x12000110, + 0x12000112, 0x12010010, 0x12010012, 0x12010111, 0x12020010, 0x12020011, 0x12020012, 0x10000121, + 0x10010021, 0x10010120, 0x10010122, 0x10020121, 0x11000021, 0x11010022, 0x11010121, 0x11010222, + 0x11020120, 0x11020221, 0x12000221, 0x12010120, 0x12020121, 0x10001001, 0x10011101, 0x10011201, + 0x10021201, 0x11001101, 0x11001200, 0x11001202, 0x11011001, 0x11011100, 0x11011101, 0x11011102, + 0x11021001, 0x11021002, 0x11021101, 0x11021200, 0x11021202, 0x12001001, 0x12001102, 0x12001201, + 0x12011000, 0x12011002, 0x12011101, 0x12021000, 0x12021001, 0x12021201, 0x10001011, 0x10001012, + 0x10001111, 0x10001212, 0x10011011, 0x10011110, 0x10011111, 0x10011112, 0x10011211, 0x10021010, + 0x10021111, 0x10021212, 0x11001011, 0x11001110, 0x11001111, 0x11001112, 0x11001211, 0x11011010, + 0x11011011, 0x11011110, 0x11011111, 0x11011112, 0x11011210, 0x11011211, 0x11021011, 0x11021110, + 0x11021111, 0x11021112, 0x11021211, 0x12001012, 0x12001110, 0x12001111, 0x12001210, 0x12011011, + 0x12011110, 0x12011111, 0x12011112, 0x12011211, 0x12011212, 0x12021111, 0x12021210, 0x12021212, + 0x10001021, 0x10001121, 0x10001221, 0x10011120, 0x10011121, 0x10011220, 0x10011222, 0x10021021, + 0x10021120, 0x10021221, 0x11001020, 0x11001022, 0x11001121, 0x11001220, 0x11011020, 0x11011021, + 0x11011022, 0x11011121, 0x11011122, 0x11011221, 0x11021022, 0x11021121, 0x11021220, 0x12001021, + 0x12001121, 0x12001222, 0x12011120, 0x12011121, 0x12021021, 0x12021120, 0x12021122, 0x10002101, + 0x10012001, 0x10012101, 0x10012202, 0x10022101, 0x11002002, 0x11002201, 0x11012000, 0x11012101, + 0x11012200, 0x11022001, 0x11022100, 0x11022102, 0x11022201, 0x12002101, 0x12012001, 0x12012100, + 0x12012102, 0x12012201, 0x12022101, 0x10002011, 0x10002111, 0x10002112, 0x10002212, 0x10012010, + 0x10012110, 0x10012111, 0x10012210, 0x10022011, 0x10022110, 0x10022112, 0x11002010, 0x11002111, + 0x11002212, 0x11012011, 0x11012012, 0x11012110, 0x11012111, 0x11012112, 0x11012211, 0x11022010, + 0x11022012, 0x11022111, 0x11022112, 0x11022212, 0x12002112, 0x12002211, 0x12012012, 0x12012111, + 0x12012112, 0x12012210, 0x12022011, 0x12022110, 0x12022112, 0x12022211, 0x10012122, 0x11002120, + 0x11002122, 0x11002221, 0x11012121, 0x11012220, 0x11012222, 0x11022120, 0x11022221, 0x12012120, + 0x12022121, 0x10100001, 0x10100100, 0x10100101, 0x10100102, 0x10100201, 0x10110002, 0x10110101, + 0x10110202, 0x10120001, 0x10120100, 0x10120201, 0x11100000, 0x11100101, 0x11100200, 0x11110001, + 0x11110100, 0x11110101, 0x11110102, 0x11110201, 0x11120101, 0x11120200, 0x12100102, 0x12100201, + 0x12110101, 0x12110200, 0x12120000, 0x12120001, 0x12120102, 0x12120201, 0x10100111, 0x10100210, + 0x10100211, 0x10100212, 0x10110011, 0x10110110, 0x10110111, 0x10110112, 0x10110210, 0x10110211, + 0x10120010, 0x10120111, 0x10120112, 0x10120210, 0x10120212, 0x11100011, 0x11100110, 0x11100111, + 0x11100112, 0x11100211, 0x11110010, 0x11110011, 0x11110012, 0x11110110, 0x11110111, 0x11110112, + 0x11110210, 0x11110211, 0x11110212, 0x11120011, 0x11120110, 0x11120111, 0x11120112, 0x11120211, + 0x12100012, 0x12100111, 0x12110011, 0x12110110, 0x12110111, 0x12110112, 0x12110211, 0x12120010, + 0x12120111, 0x12120212, 0x10100021, 0x10100122, 0x10110022, 0x10110121, 0x10110222, 0x10120021, + 0x10120120, 0x11100022, 0x11100121, 0x11100222, 0x11110021, 0x11110120, 0x11110121, 0x11110122, + 0x11110221, 0x11120022, 0x11120121, 0x12100121, 0x12110020, 0x12110022, 0x12110121, 0x12110221, + 0x12110222, 0x12120120, 0x10101100, 0x10101101, 0x10111001, 0x10111100, 0x10111101, 0x10111102, + 0x10111200, 0x10111201, 0x10121001, 0x10121101, 0x10121200, 0x10121202, 0x11101001, 0x11101100, + 0x11101101, 0x11101102, 0x11101201, 0x11101202, 0x11111000, 0x11111001, 0x11111100, 0x11111101, + 0x11111102, 0x11111200, 0x11111201, 0x11111202, 0x11121001, 0x11121002, 0x11121100, 0x11121101, + 0x11121102, 0x11121201, 0x12101000, 0x12101200, 0x12101202, 0x12111001, 0x12111100, 0x12111101, + 0x12111102, 0x12111201, 0x12121001, 0x12121100, 0x12121101, 0x12121202, 0x10101011, 0x10101012, + 0x10101110, 0x10101111, 0x10101112, 0x10101211, 0x10111010, 0x10111011, 0x10111012, 0x10111110, + 0x10111111, 0x10111112, 0x10111211, 0x10111212, 0x10121011, 0x10121110, 0x10121111, 0x10121112, + 0x10121211, 0x11101010, 0x11101011, 0x11101012, 0x11101110, 0x11101111, 0x11101112, 0x11101210, + 0x11101211, 0x11111010, 0x11111011, 0x11111012, 0x11111110, 0x11111111, 0x11111112, 0x11111210, + 0x11111211, 0x11111212, 0x11121010, 0x11121011, 0x11121110, 0x11121111, 0x11121112, 0x11121210, + 0x11121211, 0x11121212, 0x12101011, 0x12101110, 0x12101111, 0x12101211, 0x12101212, 0x12111010, + 0x12111011, 0x12111110, 0x12111111, 0x12111112, 0x12111210, 0x12111211, 0x12121011, 0x12121110, + 0x12121111, 0x12121112, 0x12121211, 0x10101020, 0x10101021, 0x10101022, 0x10101120, 0x10101122, + 0x10101220, 0x10101221, 0x10111021, 0x10111120, 0x10111121, 0x10111220, 0x10111221, 0x10121020, + 0x10121021, 0x10121022, 0x10121120, 0x10121121, 0x10121122, 0x10121220, 0x10121221, 0x11101021, + 0x11101121, 0x11101122, 0x11101220, 0x11101221, 0x11101222, 0x11111020, 0x11111021, 0x11111022, + 0x11111120, 0x11111121, 0x11111122, 0x11111220, 0x11111221, 0x11111222, 0x11121021, 0x11121120, + 0x11121121, 0x11121221, 0x12101022, 0x12101121, 0x12101122, 0x12101220, 0x12101221, 0x12101222, + 0x12111021, 0x12111121, 0x12111222, 0x12121022, 0x12121121, 0x12121122, 0x12121220, 0x12121221, + 0x10102100, 0x10102101, 0x10102102, 0x10102201, 0x10112000, 0x10112101, 0x10112200, 0x10122001, + 0x10122202, 0x11102101, 0x11102200, 0x11102202, 0x11112001, 0x11112100, 0x11112101, 0x11112102, + 0x11112200, 0x11112201, 0x11122000, 0x11122002, 0x11122100, 0x11122101, 0x12102002, 0x12102201, + 0x12112000, 0x12112002, 0x12112101, 0x12112200, 0x12122001, 0x12122201, 0x10102011, 0x10102012, + 0x10102111, 0x10102212, 0x10112011, 0x10112110, 0x10112111, 0x10112112, 0x10112211, 0x10122111, + 0x11102011, 0x11102110, 0x11102111, 0x11102112, 0x11102211, 0x11112010, 0x11112011, 0x11112012, + 0x11112110, 0x11112111, 0x11112112, 0x11112210, 0x11112211, 0x11112212, 0x11122011, 0x11122110, + 0x11122111, 0x11122112, 0x11122211, 0x12102011, 0x12102111, 0x12102211, 0x12112011, 0x12112110, + 0x12112111, 0x12112112, 0x12112210, 0x12112211, 0x12122111, 0x10102120, 0x10102220, 0x10112121, + 0x10112222, 0x10122020, 0x10122121, 0x10122122, 0x10122221, 0x11102121, 0x11102220, 0x11102221, + 0x11112021, 0x11112121, 0x11112122, 0x11112220, 0x11112221, 0x11122022, 0x11122121, 0x11122220, + 0x11122222, 0x12102021, 0x12102222, 0x12112022, 0x12112121, 0x12112122, 0x12112220, 0x12112222, + 0x12122021, 0x10200101, 0x10210100, 0x10210102, 0x10210201, 0x10220101, 0x11200100, 0x11210000, + 0x11210101, 0x11210102, 0x11210200, 0x11210202, 0x11220001, 0x11220100, 0x11220102, 0x11220201, + 0x12200001, 0x12210102, 0x12220101, 0x10200011, 0x10200110, 0x10200112, 0x10200211, 0x10210012, + 0x10210111, 0x10220011, 0x10220012, 0x10220112, 0x10220211, 0x11200111, 0x11200211, 0x11210011, + 0x11210111, 0x11210112, 0x11210211, 0x11220111, 0x11220112, 0x11220212, 0x12200110, 0x12200212, + 0x12210012, 0x12210111, 0x12220011, 0x12220112, 0x12220211, 0x10210021, 0x10210122, 0x10210221, + 0x11200020, 0x11200021, 0x11200122, 0x11210121, 0x11210122, 0x11210220, 0x11220020, 0x12200121, + 0x12210021, 0x12210122, 0x12220121, 0x10211001, 0x10211002, 0x10211101, 0x10211102, 0x10211202, + 0x10221001, 0x10221102, 0x10221201, 0x11201000, 0x11201002, 0x11201101, 0x11201200, 0x11201202, + 0x11211001, 0x11211100, 0x11211101, 0x11211102, 0x11211201, 0x11211202, 0x11221000, 0x11221002, + 0x11221101, 0x12201100, 0x12201101, 0x12201201, 0x12211000, 0x12211002, 0x12211100, 0x12211101, + 0x12211102, 0x12211200, 0x12211202, 0x12221001, 0x12221100, 0x12221201, 0x10201111, 0x10201210, + 0x10201212, 0x10211011, 0x10211111, 0x10211112, 0x10211211, 0x11201110, 0x11201111, 0x11201112, + 0x11201211, 0x11211010, 0x11211011, 0x11211110, 0x11211111, 0x11211112, 0x11211211, 0x11221011, + 0x11221110, 0x11221111, 0x11221112, 0x11221211, 0x12201112, 0x12201211, 0x12201212, 0x12211011, + 0x12211111, 0x12211112, 0x12211211, 0x12211212, 0x12221012, 0x12221111, 0x12221112, 0x12221210, + 0x10201022, 0x10201221, 0x10211121, 0x10221020, 0x10221122, 0x10221220, 0x10221221, 0x11201020, + 0x11201121, 0x11201220, 0x11201222, 0x11211021, 0x11211120, 0x11211121, 0x11211122, 0x11211220, + 0x11211222, 0x11221020, 0x11221121, 0x11221220, 0x12201020, 0x12201022, 0x12201121, 0x12201222, + 0x12211120, 0x12211122, 0x12211220, 0x12211221, 0x12221020, 0x12221120, 0x12221122, 0x12221222, + 0x10212102, 0x10212201, 0x10222101, 0x11202001, 0x11212002, 0x11212101, 0x11212202, 0x11222001, + 0x11222201, 0x12202101, 0x12212001, 0x12212200, 0x12222102, 0x10202011, 0x10202110, 0x10212010, + 0x10212111, 0x10222011, 0x10222110, 0x10222112, 0x10222211, 0x11202010, 0x11202011, 0x11202111, + 0x11202112, 0x11202210, 0x11212011, 0x11212110, 0x11212111, 0x11212112, 0x11212211, 0x11222010, + 0x11222111, 0x11222212, 0x12202012, 0x12202110, 0x12202212, 0x12212111, 0x12222011, 0x12222110, + 0x12222111, 0x12222211, 0x10212021, 0x10212122, 0x10212220, 0x11202021, 0x11202120, 0x11202221, + 0x11212020, 0x11212121, 0x11212220, 0x11212222, 0x11222120, 0x11222121, 0x11222221, 0x12202122, + 0x12212120, 0x12212220, 0x12212222, 0x12222122, 0x20000000, 0x20000002, 0x20000200, 0x20000202, + 0x20020000, 0x20020002, 0x20020200, 0x20020202, 0x21000101, 0x21010000, 0x21010001, 0x21010100, + 0x21010102, 0x21010201, 0x21020101, 0x22000000, 0x22000002, 0x22000200, 0x22000202, 0x22010101, + 0x22020000, 0x22020002, 0x22020200, 0x22020202, 0x20000111, 0x20010011, 0x20010110, 0x20010112, + 0x20010211, 0x20020111, 0x21000011, 0x21000110, 0x21000211, 0x21010010, 0x21010012, 0x21010111, + 0x21010112, 0x21010210, 0x21010211, 0x21020110, 0x21020112, 0x21020211, 0x22000111, 0x22000211, + 0x22010110, 0x22010112, 0x22010211, 0x22020111, 0x20000020, 0x20000022, 0x20000220, 0x20000222, + 0x20010121, 0x20020020, 0x20020022, 0x20020220, 0x20020222, 0x21010021, 0x21010120, 0x21010221, + 0x21020121, 0x22000020, 0x22000022, 0x22000220, 0x22000222, 0x22010121, 0x22020020, 0x22020022, + 0x22020220, 0x22020222, 0x20011100, 0x20011201, 0x21001001, 0x21001100, 0x21011001, 0x21011101, + 0x21011202, 0x21021001, 0x21021100, 0x21021201, 0x22011100, 0x22011201, 0x20001011, 0x20001211, + 0x20011012, 0x20011111, 0x20011212, 0x20021112, 0x20021211, 0x21001010, 0x21001011, 0x21001111, + 0x21001210, 0x21011011, 0x21011110, 0x21011111, 0x21011112, 0x21011211, 0x21011212, 0x21021111, + 0x21021112, 0x21021210, 0x21021212, 0x22001011, 0x22001110, 0x22001112, 0x22001211, 0x22011010, + 0x22011012, 0x22011111, 0x22011210, 0x22021112, 0x20011021, 0x20011122, 0x20011221, 0x20021121, + 0x21001021, 0x21001120, 0x21001221, 0x21001222, 0x21011020, 0x21011121, 0x21011221, 0x21011222, + 0x21021021, 0x21021122, 0x21021222, 0x22001121, 0x22011021, 0x22011222, 0x22021120, 0x20002000, + 0x20002002, 0x20002200, 0x20002202, 0x20012101, 0x20022000, 0x20022002, 0x20022200, 0x20022202, + 0x21002001, 0x21002101, 0x21012001, 0x21012100, 0x21012201, 0x21022101, 0x21022201, 0x22002000, + 0x22002002, 0x22002200, 0x22002202, 0x22012101, 0x22022000, 0x22022002, 0x22022200, 0x22022202, + 0x20002111, 0x20002112, 0x20012011, 0x20012110, 0x20012112, 0x20022111, 0x21002011, 0x21002110, + 0x21002112, 0x21002211, 0x21012010, 0x21012012, 0x21012111, 0x21012212, 0x21022011, 0x21022110, + 0x22002111, 0x22012112, 0x22012211, 0x22022111, 0x20002020, 0x20002022, 0x20002220, 0x20002222, + 0x20012121, 0x20022020, 0x20022022, 0x20022220, 0x20022222, 0x21002121, 0x21012021, 0x21012120, + 0x21012122, 0x22002020, 0x22002022, 0x22002220, 0x22002222, 0x22012121, 0x22022020, 0x22022022, + 0x22022220, 0x22022222, 0x20100101, 0x20110001, 0x20110102, 0x20110200, 0x20110201, 0x20120101, + 0x21100001, 0x21100102, 0x21100201, 0x21110101, 0x21110200, 0x21110202, 0x21120201, 0x21120202, + 0x22100101, 0x22110001, 0x22110100, 0x22110102, 0x22110201, 0x22120101, 0x20100011, 0x20100110, + 0x20100112, 0x20100211, 0x20110010, 0x20110111, 0x20110210, 0x20110212, 0x20120011, 0x20120110, + 0x20120112, 0x20120211, 0x21100010, 0x21100111, 0x21110010, 0x21110011, 0x21110110, 0x21110111, + 0x21110112, 0x21110211, 0x21120012, 0x21120111, 0x22100110, 0x22100112, 0x22110012, 0x22110111, + 0x22110210, 0x22120011, 0x22120110, 0x22120112, 0x22120211, 0x20100121, 0x20110021, 0x20110120, + 0x20110221, 0x20120121, 0x21100120, 0x21100122, 0x21100221, 0x21110020, 0x21110022, 0x21110121, + 0x21110220, 0x21120122, 0x21120221, 0x22100121, 0x22110120, 0x22110122, 0x22120221, 0x20101001, + 0x20101100, 0x20101102, 0x20111000, 0x20111101, 0x20111200, 0x20121102, 0x21101000, 0x21101202, + 0x21111001, 0x21111100, 0x21111101, 0x21111102, 0x21111200, 0x21111201, 0x21121000, 0x21121001, + 0x21121002, 0x21121101, 0x22101100, 0x22101102, 0x22111002, 0x22111100, 0x22111101, 0x22111200, + 0x22121001, 0x22121201, 0x20101010, 0x20101111, 0x20101210, 0x20101212, 0x20111010, 0x20111011, + 0x20111110, 0x20111111, 0x20111112, 0x20111211, 0x20121011, 0x20121111, 0x20121211, 0x20121212, + 0x21101011, 0x21101110, 0x21101111, 0x21101112, 0x21101211, 0x21111010, 0x21111011, 0x21111012, + 0x21111110, 0x21111111, 0x21111112, 0x21111210, 0x21111211, 0x21111212, 0x21121011, 0x21121110, + 0x21121111, 0x21121112, 0x21121211, 0x22101011, 0x22101111, 0x22101210, 0x22111011, 0x22111012, + 0x22111110, 0x22111111, 0x22111112, 0x22111211, 0x22111212, 0x22121010, 0x22121012, 0x22121111, + 0x22121210, 0x22121212, 0x20101021, 0x20101120, 0x20111020, 0x20111121, 0x20111221, 0x20121020, + 0x20121122, 0x20121221, 0x21101121, 0x21101220, 0x21101221, 0x21111021, 0x21111022, 0x21111121, + 0x21111122, 0x21111221, 0x21121121, 0x21121220, 0x22101022, 0x22101120, 0x22101221, 0x22101222, + 0x22111022, 0x22111120, 0x22111121, 0x22121120, 0x22121122, 0x22121221, 0x20102101, 0x20112102, + 0x20112201, 0x20122101, 0x21102001, 0x21102102, 0x21112000, 0x21112002, 0x21112101, 0x21112102, + 0x21112202, 0x21122100, 0x21122101, 0x22102101, 0x22112001, 0x22112102, 0x22112201, 0x22122101, + 0x20102110, 0x20102112, 0x20102211, 0x20112010, 0x20112012, 0x20112111, 0x20112210, 0x20112212, + 0x20122010, 0x20122011, 0x20122110, 0x20122112, 0x21102010, 0x21102012, 0x21102111, 0x21102210, + 0x21102212, 0x21112011, 0x21112110, 0x21112111, 0x21112112, 0x21112211, 0x21122012, 0x21122111, + 0x21122112, 0x21122212, 0x22102011, 0x22102110, 0x22112010, 0x22112012, 0x22112111, 0x22112212, + 0x22122011, 0x22122112, 0x20102121, 0x20112121, 0x20122121, 0x21102120, 0x21102122, 0x21102221, + 0x21112020, 0x21112121, 0x21112220, 0x21122021, 0x22102121, 0x22112021, 0x22112120, 0x22112121, + 0x22112122, 0x20200000, 0x20200002, 0x20200200, 0x20200202, 0x20210101, 0x20220000, 0x20220002, + 0x20220200, 0x20220202, 0x21200101, 0x21210001, 0x21210100, 0x21210102, 0x21210201, 0x22200000, + 0x22200002, 0x22200200, 0x22200202, 0x22210101, 0x22220000, 0x22220002, 0x22220200, 0x22220202, + 0x20200111, 0x20200211, 0x20210011, 0x20210110, 0x20210112, 0x20210211, 0x20210212, 0x21200112, + 0x21200211, 0x21210011, 0x21210111, 0x21210210, 0x21210212, 0x21220011, 0x21220110, 0x22200111, + 0x22210010, 0x22210012, 0x22210112, 0x22210211, 0x20200022, 0x20200220, 0x20200222, 0x20210020, + 0x20210221, 0x20220022, 0x20220220, 0x20220222, 0x21200121, 0x21210021, 0x21210122, 0x21210221, + 0x21220121, 0x22200020, 0x22200022, 0x22200220, 0x22200222, 0x22210121, 0x22220020, 0x22220022, + 0x22220220, 0x22220222, 0x20211201, 0x20221101, 0x21201001, 0x21201100, 0x21211000, 0x21211100, + 0x21211101, 0x21211200, 0x21211202, 0x21221001, 0x21221101, 0x21221102, 0x21221200, 0x21221201, + 0x22201101, 0x20201112, 0x20201211, 0x20211010, 0x20211012, 0x20211111, 0x20211210, 0x20221112, + 0x20221211, 0x21201012, 0x21201111, 0x21211011, 0x21211110, 0x21211111, 0x21211112, 0x21211211, + 0x21221111, 0x21221212, 0x22201011, 0x22201110, 0x22201111, 0x22201112, 0x22201211, 0x22211012, + 0x22211111, 0x22211210, 0x20201121, 0x20211021, 0x20211122, 0x20211222, 0x20221021, 0x20221121, + 0x21201120, 0x21201122, 0x21201222, 0x21211022, 0x21211121, 0x21211122, 0x21211220, 0x21221020, + 0x21221022, 0x22201122, 0x22211020, 0x22211121, 0x22211122, 0x22211221, 0x22221021, 0x22221120, + 0x22221122, 0x20202000, 0x20202002, 0x20202200, 0x20202202, 0x20222000, 0x20222002, 0x20222200, + 0x20222202, 0x21212001, 0x21212100, 0x21212102, 0x21212201, 0x22202000, 0x22202002, 0x22202200, + 0x22202202, 0x22212101, 0x22222000, 0x22222002, 0x22222200, 0x22222202, 0x20202111, 0x20212110, + 0x20212211, 0x20222011, 0x20222111, 0x21202011, 0x21212010, 0x21212111, 0x21212212, 0x21222011, + 0x21222112, 0x21222211, 0x22212010, 0x22212112, 0x20202020, 0x20202022, 0x20202220, 0x20202222, + 0x20222020, 0x20222022, 0x20222220, 0x20222222, 0x21212021, 0x21212120, 0x21212122, 0x22202020, + 0x22202022, 0x22202220, 0x22202222, 0x22212121, 0x22222020, 0x22222022, 0x22222220, 0x22222222, +GGML_TABLE_END() +#endif + +#endif // GGML_COMMON_IMPL +#endif // GGML_COMMON_IMPL diff --git a/include/ggml/ggml-alloc.h b/include/ggml/ggml-alloc.h index 1d9085d15..434c13b34 100644 --- a/include/ggml/ggml-alloc.h +++ b/include/ggml/ggml-alloc.h @@ -11,11 +11,15 @@ typedef struct ggml_backend_buffer * ggml_backend_buffer_t; typedef struct ggml_backend * ggml_backend_t; // Tensor allocator -typedef struct ggml_tallocr * ggml_tallocr_t; +struct ggml_tallocr { + ggml_backend_buffer_t buffer; + void * base; + size_t alignment; + size_t offset; +}; -GGML_API ggml_tallocr_t ggml_tallocr_new(ggml_backend_buffer_t buffer); -GGML_API void ggml_tallocr_free(ggml_tallocr_t talloc); -GGML_API void ggml_tallocr_alloc(ggml_tallocr_t talloc, struct ggml_tensor * tensor); +GGML_API struct ggml_tallocr ggml_tallocr_new(ggml_backend_buffer_t buffer); +GGML_API void ggml_tallocr_alloc(struct ggml_tallocr * talloc, struct ggml_tensor * tensor); // Graph allocator /* @@ -50,7 +54,11 @@ GGML_API void ggml_gallocr_free(ggml_gallocr_t galloc); // not strictly required for single buffer usage: ggml_gallocr_alloc_graph will reallocate the buffers automatically if needed // returns false if the buffer allocation failed GGML_API bool ggml_gallocr_reserve(ggml_gallocr_t galloc, struct ggml_cgraph * graph); -GGML_API bool ggml_gallocr_reserve_n(ggml_gallocr_t galloc, struct ggml_cgraph * graph, const int * node_buffer_ids); +GGML_API bool ggml_gallocr_reserve_n( + ggml_gallocr_t galloc, + struct ggml_cgraph * graph, + const int * node_buffer_ids, + const int * leaf_buffer_ids); // automatic reallocation if the topology changes when using a single buffer // returns false if using multiple buffers and a re-allocation is needed (call ggml_gallocr_reserve_n first to set the node buffers) diff --git a/include/ggml/ggml-backend.h b/include/ggml/ggml-backend.h index 8bed22578..099d9c258 100644 --- a/include/ggml/ggml-backend.h +++ b/include/ggml/ggml-backend.h @@ -9,6 +9,7 @@ extern "C" { typedef struct ggml_backend_buffer_type * ggml_backend_buffer_type_t; typedef struct ggml_backend_buffer * ggml_backend_buffer_t; + typedef struct ggml_backend_event * ggml_backend_event_t; typedef struct ggml_backend * ggml_backend_t; typedef void * ggml_backend_graph_plan_t; @@ -72,11 +73,24 @@ extern "C" { GGML_API enum ggml_status ggml_backend_graph_plan_compute(ggml_backend_t backend, ggml_backend_graph_plan_t plan); GGML_API enum ggml_status ggml_backend_graph_compute (ggml_backend_t backend, struct ggml_cgraph * cgraph); + GGML_API bool ggml_backend_graph_compute_async(ggml_backend_t backend, struct ggml_cgraph * cgraph); GGML_API bool ggml_backend_supports_op(ggml_backend_t backend, const struct ggml_tensor * op); // tensor copy between different backends GGML_API void ggml_backend_tensor_copy(struct ggml_tensor * src, struct ggml_tensor * dst); - GGML_API void ggml_backend_tensor_copy_async(ggml_backend_t backend, struct ggml_tensor * src, struct ggml_tensor * dst); // automatic fallback to sync copy + + // asynchronous copy + // the copy is performed after all the currently queued operations in backend_src + // backend_dst will wait for the copy to complete before performing other operations + // automatic fallback to sync copy if async is not supported + GGML_API void ggml_backend_tensor_copy_async(ggml_backend_t backend_src, ggml_backend_t backend_dst, struct ggml_tensor * src, struct ggml_tensor * dst); + + // events + GGML_API ggml_backend_event_t ggml_backend_event_new (ggml_backend_t backend); + GGML_API void ggml_backend_event_free (ggml_backend_event_t event); + GGML_API void ggml_backend_event_record (ggml_backend_event_t event); + GGML_API void ggml_backend_event_synchronize(ggml_backend_event_t event); + GGML_API void ggml_backend_event_wait (ggml_backend_t backend, ggml_backend_event_t event); // wait async on event // // CPU backend @@ -123,27 +137,31 @@ extern "C" { /* Example usage: - sched = ggml_backend_sched_new({backend_gpu, backend_gpu2, backend_cpu}, num_backends); - // sched is initialized with measure allocators and cannot be used until allocated with a measure graph + // operations that use tensors allocated in a buffer with USAGE_WEIGHTS will be asigned + // preferrably to run on the same backend as the buffer + ggml_backend_buffer_set_usage(buf_weights, GGML_BACKEND_BUFFER_USAGE_WEIGHTS); - // initialize buffers from a measure graph - measure_graph = build_graph(sched); // use the allocr to allocate inputs as needed + sched = ggml_backend_sched_new({backend_gpu, backend_gpu2, backend_cpu}, NULL, num_backends, GGML_DEFAULT_GRAPH_SIZE, false); - // in build_graph: - build_graph(...) { - // manually assign nodes to a backend (optional, should not be needed in most cases) - struct ggml_tensor * node = ggml_mul_mat(ctx, ...); - ggml_backend_sched_set_node_backend(sched, node, backend_gpu); - } + // initialize buffers from a max size graph (optional) + reserve_graph = build_graph(sched, max_batch_size); - // allocate backend buffers from measure graph - ggml_backend_sched_init_measure(sched, measure_graph); + // manually assign nodes to a backend (optional, should not be needed in most cases) + struct ggml_tensor * node = ggml_mul_mat(ctx, ...); + ggml_backend_sched_set_tensor_backend(sched, node, backend_gpu); - // the scheduler is now ready to compute graphs + ggml_backend_sched_reserve(sched, reserve_graph); // compute graph = build_graph(sched); ggml_backend_sched_graph_compute(sched, graph); + + // if there are graph inputs: + ggml_backend_sched_reset(sched); + ggml_backend_sched_alloc_graph(sched, graph); + ggml_backend_tensor_set(input_tensor, ...); + ggml_backend_sched_graph_compute(sched, graph); + } */ struct ggml_backend_sched; @@ -158,20 +176,26 @@ extern "C" { typedef bool (*ggml_backend_sched_eval_callback)(struct ggml_tensor * t, bool ask, void * user_data); // Initialize a backend scheduler - GGML_API ggml_backend_sched_t ggml_backend_sched_new(ggml_backend_t * backends, ggml_backend_buffer_type_t * bufts, int n_backends, size_t graph_size); + GGML_API ggml_backend_sched_t ggml_backend_sched_new(ggml_backend_t * backends, ggml_backend_buffer_type_t * bufts, int n_backends, size_t graph_size, bool parallel); GGML_API void ggml_backend_sched_free(ggml_backend_sched_t sched); + // Initialize backend buffers from a measure graph GGML_API bool ggml_backend_sched_reserve(ggml_backend_sched_t sched, struct ggml_cgraph * measure_graph); + // Get the number of splits of the last graph GGML_API int ggml_backend_sched_get_n_splits(ggml_backend_sched_t sched); + GGML_API int ggml_backend_sched_get_n_copies(ggml_backend_sched_t sched); GGML_API size_t ggml_backend_sched_get_buffer_size(ggml_backend_sched_t sched, ggml_backend_t backend); - GGML_API void ggml_backend_sched_set_node_backend(ggml_backend_sched_t sched, struct ggml_tensor * node, ggml_backend_t backend); - GGML_API ggml_backend_t ggml_backend_sched_get_node_backend(ggml_backend_sched_t sched, struct ggml_tensor * node); + GGML_API void ggml_backend_sched_set_tensor_backend(ggml_backend_sched_t sched, struct ggml_tensor * node, ggml_backend_t backend); + GGML_API ggml_backend_t ggml_backend_sched_get_tensor_backend(ggml_backend_sched_t sched, struct ggml_tensor * node); // Allocate and compute graph on the backend scheduler + GGML_API bool ggml_backend_sched_alloc_graph(ggml_backend_sched_t sched, struct ggml_cgraph * graph); GGML_API enum ggml_status ggml_backend_sched_graph_compute(ggml_backend_sched_t sched, struct ggml_cgraph * graph); + GGML_API enum ggml_status ggml_backend_sched_graph_compute_async(ggml_backend_sched_t sched, struct ggml_cgraph * graph); + GGML_API void ggml_backend_sched_synchronize(ggml_backend_sched_t sched); // Reset all assignments and allocators - must be called before changing the node backends GGML_API void ggml_backend_sched_reset(ggml_backend_sched_t sched); diff --git a/include/ggml/ggml.h b/include/ggml/ggml.h index 0ea4f8847..ab26c8f59 100644 --- a/include/ggml/ggml.h +++ b/include/ggml/ggml.h @@ -337,24 +337,24 @@ extern "C" { struct ggml_object; struct ggml_context; + // NOTE: always add types at the end of the enum to keep backward compatibility enum ggml_type { - GGML_TYPE_F32 = 0, - GGML_TYPE_F16 = 1, - GGML_TYPE_Q4_0 = 2, - GGML_TYPE_Q4_1 = 3, + GGML_TYPE_F32 = 0, + GGML_TYPE_F16 = 1, + GGML_TYPE_Q4_0 = 2, + GGML_TYPE_Q4_1 = 3, // GGML_TYPE_Q4_2 = 4, support has been removed - // GGML_TYPE_Q4_3 (5) support has been removed - GGML_TYPE_Q5_0 = 6, - GGML_TYPE_Q5_1 = 7, - GGML_TYPE_Q8_0 = 8, - GGML_TYPE_Q8_1 = 9, - // k-quantizations - GGML_TYPE_Q2_K = 10, - GGML_TYPE_Q3_K = 11, - GGML_TYPE_Q4_K = 12, - GGML_TYPE_Q5_K = 13, - GGML_TYPE_Q6_K = 14, - GGML_TYPE_Q8_K = 15, + // GGML_TYPE_Q4_3 = 5, support has been removed + GGML_TYPE_Q5_0 = 6, + GGML_TYPE_Q5_1 = 7, + GGML_TYPE_Q8_0 = 8, + GGML_TYPE_Q8_1 = 9, + GGML_TYPE_Q2_K = 10, + GGML_TYPE_Q3_K = 11, + GGML_TYPE_Q4_K = 12, + GGML_TYPE_Q5_K = 13, + GGML_TYPE_Q6_K = 14, + GGML_TYPE_Q8_K = 15, GGML_TYPE_IQ2_XXS = 16, GGML_TYPE_IQ2_XS = 17, GGML_TYPE_IQ3_XXS = 18, @@ -363,9 +363,9 @@ extern "C" { GGML_TYPE_IQ3_S = 21, GGML_TYPE_IQ2_S = 22, GGML_TYPE_IQ4_XS = 23, - GGML_TYPE_I8, - GGML_TYPE_I16, - GGML_TYPE_I32, + GGML_TYPE_I8 = 24, + GGML_TYPE_I16 = 25, + GGML_TYPE_I32 = 26, GGML_TYPE_COUNT, }; @@ -383,20 +383,20 @@ extern "C" { // model file types enum ggml_ftype { - GGML_FTYPE_UNKNOWN = -1, - GGML_FTYPE_ALL_F32 = 0, - GGML_FTYPE_MOSTLY_F16 = 1, // except 1d tensors - GGML_FTYPE_MOSTLY_Q4_0 = 2, // except 1d tensors - GGML_FTYPE_MOSTLY_Q4_1 = 3, // except 1d tensors + GGML_FTYPE_UNKNOWN = -1, + GGML_FTYPE_ALL_F32 = 0, + GGML_FTYPE_MOSTLY_F16 = 1, // except 1d tensors + GGML_FTYPE_MOSTLY_Q4_0 = 2, // except 1d tensors + GGML_FTYPE_MOSTLY_Q4_1 = 3, // except 1d tensors GGML_FTYPE_MOSTLY_Q4_1_SOME_F16 = 4, // tok_embeddings.weight and output.weight are F16 - GGML_FTYPE_MOSTLY_Q8_0 = 7, // except 1d tensors - GGML_FTYPE_MOSTLY_Q5_0 = 8, // except 1d tensors - GGML_FTYPE_MOSTLY_Q5_1 = 9, // except 1d tensors - GGML_FTYPE_MOSTLY_Q2_K = 10, // except 1d tensors - GGML_FTYPE_MOSTLY_Q3_K = 11, // except 1d tensors - GGML_FTYPE_MOSTLY_Q4_K = 12, // except 1d tensors - GGML_FTYPE_MOSTLY_Q5_K = 13, // except 1d tensors - GGML_FTYPE_MOSTLY_Q6_K = 14, // except 1d tensors + GGML_FTYPE_MOSTLY_Q8_0 = 7, // except 1d tensors + GGML_FTYPE_MOSTLY_Q5_0 = 8, // except 1d tensors + GGML_FTYPE_MOSTLY_Q5_1 = 9, // except 1d tensors + GGML_FTYPE_MOSTLY_Q2_K = 10, // except 1d tensors + GGML_FTYPE_MOSTLY_Q3_K = 11, // except 1d tensors + GGML_FTYPE_MOSTLY_Q4_K = 12, // except 1d tensors + GGML_FTYPE_MOSTLY_Q5_K = 13, // except 1d tensors + GGML_FTYPE_MOSTLY_Q6_K = 14, // except 1d tensors GGML_FTYPE_MOSTLY_IQ2_XXS = 15, // except 1d tensors GGML_FTYPE_MOSTLY_IQ2_XS = 16, // except 1d tensors GGML_FTYPE_MOSTLY_IQ3_XXS = 17, // except 1d tensors @@ -472,6 +472,8 @@ extern "C" { GGML_OP_FLASH_ATTN, GGML_OP_FLASH_FF, GGML_OP_FLASH_ATTN_BACK, + GGML_OP_SSM_CONV, + GGML_OP_SSM_SCAN, GGML_OP_WIN_PART, GGML_OP_WIN_UNPART, GGML_OP_GET_REL_POS, @@ -1728,6 +1730,23 @@ extern "C" { struct ggml_tensor * c0, struct ggml_tensor * c1); + GGML_API struct ggml_tensor * ggml_ssm_conv( + struct ggml_context * ctx, + struct ggml_tensor * s, + struct ggml_tensor * x, + struct ggml_tensor * c, + struct ggml_tensor * sq); + + GGML_API struct ggml_tensor * ggml_ssm_scan( + struct ggml_context * ctx, + struct ggml_tensor * s, + struct ggml_tensor * x, + struct ggml_tensor * dt, + struct ggml_tensor * A, + struct ggml_tensor * B, + struct ggml_tensor * C, + struct ggml_tensor * sq); + // partition into non-overlapping windows with padding if needed // example: // a: 768 64 64 1 @@ -2175,25 +2194,18 @@ extern "C" { GGML_API void ggml_quantize_init(enum ggml_type type); GGML_API void ggml_quantize_free(void); - // TODO: these would probably get removed in favor of the more general ggml_quantize_chunk - GGML_API size_t ggml_quantize_q4_0(const float * src, void * dst, int n, int k, int64_t * hist); - GGML_API size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int64_t * hist); - GGML_API size_t ggml_quantize_q5_0(const float * src, void * dst, int n, int k, int64_t * hist); - GGML_API size_t ggml_quantize_q5_1(const float * src, void * dst, int n, int k, int64_t * hist); - GGML_API size_t ggml_quantize_q8_0(const float * src, void * dst, int n, int k, int64_t * hist); - - GGML_API size_t ggml_quantize_q2_K(const float * src, void * dst, int n, int k, int64_t * hist); - GGML_API size_t ggml_quantize_q3_K(const float * src, void * dst, int n, int k, int64_t * hist); - GGML_API size_t ggml_quantize_q4_K(const float * src, void * dst, int n, int k, int64_t * hist); - GGML_API size_t ggml_quantize_q5_K(const float * src, void * dst, int n, int k, int64_t * hist); - GGML_API size_t ggml_quantize_q6_K(const float * src, void * dst, int n, int k, int64_t * hist); - // some quantization type cannot be used without an importance matrix GGML_API bool ggml_quantize_requires_imatrix(enum ggml_type type); // calls ggml_quantize_init internally (i.e. can allocate memory) - GGML_API size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst, - int start, int nrows, int n_per_row, int64_t * hist, const float * imatrix); + GGML_API size_t ggml_quantize_chunk( + enum ggml_type type, + const float * src, + void * dst, + int start, + int nrows, + int n_per_row, + const float * imatrix); // // gguf diff --git a/scripts/sync-llama-am.sh b/scripts/sync-llama-am.sh index 558b17480..af6220e2a 100755 --- a/scripts/sync-llama-am.sh +++ b/scripts/sync-llama-am.sh @@ -93,6 +93,7 @@ if [ -f $SRC_GGML/llama-src.patch ]; then # ggml-alloc.c -> src/ggml-alloc.c # ggml-backend-impl.h -> src/ggml-backend-impl.h # ggml-backend.c -> src/ggml-backend.c + # ggml-common.h -> src/ggml-common.h # ggml-cuda.cu -> src/ggml-cuda.cu # ggml-cuda.h -> src/ggml-cuda.h # ggml-impl.h -> src/ggml-impl.h @@ -125,6 +126,7 @@ if [ -f $SRC_GGML/llama-src.patch ]; then -e 's/\/ggml-alloc\.c/\/src\/ggml-alloc.c/g' \ -e 's/\/ggml-backend-impl\.h/\/src\/ggml-backend-impl.h/g' \ -e 's/\/ggml-backend\.c/\/src\/ggml-backend.c/g' \ + -e 's/\/ggml-common\.h/\/src\/ggml-common.h/g' \ -e 's/\/ggml-cuda\.cu/\/src\/ggml-cuda.cu/g' \ -e 's/\/ggml-cuda\.h/\/src\/ggml-cuda.h/g' \ -e 's/\/ggml-impl\.h/\/src\/ggml-impl.h/g' \ diff --git a/scripts/sync-llama.last b/scripts/sync-llama.last index 27be41e4f..1a922001b 100644 --- a/scripts/sync-llama.last +++ b/scripts/sync-llama.last @@ -1 +1 @@ -6cdabe652695167263c8b447520987b11856f7ca +044ec4b2a567f649459ccd20af2f387c784faa51 diff --git a/scripts/sync-llama.sh b/scripts/sync-llama.sh index dba539f19..dc505b4bb 100755 --- a/scripts/sync-llama.sh +++ b/scripts/sync-llama.sh @@ -4,6 +4,7 @@ cp -rpv ../llama.cpp/ggml.c src/ggml.c cp -rpv ../llama.cpp/ggml-alloc.c src/ggml-alloc.c cp -rpv ../llama.cpp/ggml-backend-impl.h src/ggml-backend-impl.h cp -rpv ../llama.cpp/ggml-backend.c src/ggml-backend.c +cp -rpv ../llama.cpp/ggml-common.h src/ggml-common.h cp -rpv ../llama.cpp/ggml-cuda.cu src/ggml-cuda.cu cp -rpv ../llama.cpp/ggml-cuda.h src/ggml-cuda.h cp -rpv ../llama.cpp/ggml-impl.h src/ggml-impl.h diff --git a/scripts/sync-whisper-am.sh b/scripts/sync-whisper-am.sh index a6cdef06f..3fe4e380c 100755 --- a/scripts/sync-whisper-am.sh +++ b/scripts/sync-whisper-am.sh @@ -96,6 +96,7 @@ if [ -f $SRC_GGML/whisper-src.patch ]; then # ggml-alloc.c -> src/ggml-alloc.c # ggml-backend-impl.h -> src/ggml-backend-impl.h # ggml-backend.c -> src/ggml-backend.c + # ggml-common.h -> src/ggml-common.h # ggml-cuda.cu -> src/ggml-cuda.cu # ggml-cuda.h -> src/ggml-cuda.h # ggml-impl.h -> src/ggml-impl.h @@ -132,6 +133,7 @@ if [ -f $SRC_GGML/whisper-src.patch ]; then -e 's/\/ggml-alloc\.c/\/src\/ggml-alloc.c/g' \ -e 's/\/ggml-backend-impl\.h/\/src\/ggml-backend-impl.h/g' \ -e 's/\/ggml-backend\.c/\/src\/ggml-backend.c/g' \ + -e 's/\/ggml-common\.h/\/src\/ggml-common.h/g' \ -e 's/\/ggml-cuda\.cu/\/src\/ggml-cuda.cu/g' \ -e 's/\/ggml-cuda\.h/\/src\/ggml-cuda.h/g' \ -e 's/\/ggml-impl\.h/\/src\/ggml-impl.h/g' \ diff --git a/scripts/sync-whisper.sh b/scripts/sync-whisper.sh index a5633b2c9..1d2b81f12 100755 --- a/scripts/sync-whisper.sh +++ b/scripts/sync-whisper.sh @@ -5,6 +5,7 @@ cp -rpv ../whisper.cpp/ggml-impl.h src/ggml-impl.h cp -rpv ../whisper.cpp/ggml-alloc.c src/ggml-alloc.c cp -rpv ../whisper.cpp/ggml-backend-impl.h src/ggml-backend-impl.h cp -rpv ../whisper.cpp/ggml-backend.c src/ggml-backend.c +cp -rpv ../whisper.cpp/ggml-common.h src/ggml-common.h cp -rpv ../whisper.cpp/ggml-cuda.cu src/ggml-cuda.cu cp -rpv ../whisper.cpp/ggml-cuda.h src/ggml-cuda.h cp -rpv ../whisper.cpp/ggml-kompute.cpp src/ggml-kompute.cpp diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt index 8231a906c..e784fc824 100644 --- a/src/CMakeLists.txt +++ b/src/CMakeLists.txt @@ -309,7 +309,8 @@ if (GGML_METAL) # get full path to the file #add_compile_definitions(GGML_METAL_DIR_KERNELS="${CMAKE_CURRENT_SOURCE_DIR}/") - # copy ggml-metal.metal to bin directory + # copy ggml-common.h and ggml-metal.metal to bin directory + configure_file(ggml-common.h ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-common.h COPYONLY) configure_file(ggml-metal.metal ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-metal.metal COPYONLY) set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} diff --git a/src/ggml-alloc.c b/src/ggml-alloc.c index e675306c8..8ac1d3e51 100644 --- a/src/ggml-alloc.c +++ b/src/ggml-alloc.c @@ -61,7 +61,6 @@ static bool ggml_op_can_inplace(enum ggml_op op) { } } -// TODO: GGML_PAD ? static size_t aligned_offset(const void * buffer, size_t offset, size_t alignment) { assert(alignment && !(alignment & (alignment - 1))); // power of 2 size_t align = (alignment - (((uintptr_t)buffer + offset) % alignment)) % alignment; @@ -69,25 +68,14 @@ static size_t aligned_offset(const void * buffer, size_t offset, size_t alignmen } // tallocr -struct ggml_tallocr { - ggml_backend_buffer_t buffer; - void * base; - size_t alignment; - size_t offset; -}; - -ggml_tallocr_t ggml_tallocr_new(ggml_backend_buffer_t buffer) { - ggml_tallocr_t talloc = malloc(sizeof(struct ggml_tallocr)); - if (talloc == NULL) { - return NULL; - } +struct ggml_tallocr ggml_tallocr_new(ggml_backend_buffer_t buffer) { void * base = ggml_backend_buffer_get_base(buffer); size_t align = ggml_backend_buffer_get_alignment(buffer); assert(align && !(align & (align - 1))); // power of 2 - *talloc = (struct ggml_tallocr) { + struct ggml_tallocr talloc = (struct ggml_tallocr) { /*.buffer = */ buffer, /*.base = */ base, /*.alignment = */ align, @@ -96,11 +84,7 @@ ggml_tallocr_t ggml_tallocr_new(ggml_backend_buffer_t buffer) { return talloc; } -void ggml_tallocr_free(ggml_tallocr_t talloc) { - free(talloc); -} - -void ggml_tallocr_alloc(ggml_tallocr_t talloc, struct ggml_tensor * tensor) { +void ggml_tallocr_alloc(struct ggml_tallocr * talloc, struct ggml_tensor * tensor) { size_t size = ggml_backend_buffer_get_alloc_size(talloc->buffer, tensor); size = GGML_PAD(size, talloc->alignment); @@ -354,12 +338,16 @@ struct hash_node { bool allocated; }; -// struct tensor_alloc { size_t offset; size_t size_max; // 0 = pre-allocated, unused, or view }; +struct leaf_alloc { + int buffer_id; + struct tensor_alloc leaf; +}; + struct node_alloc { int buffer_id; struct tensor_alloc dst; @@ -378,7 +366,7 @@ struct ggml_gallocr { struct node_alloc * node_allocs; // [n_nodes] int n_nodes; - struct tensor_alloc * leaf_allocs; // [n_leafs] + struct leaf_alloc * leaf_allocs; // [n_leafs] int n_leafs; }; @@ -543,13 +531,20 @@ static int get_node_buffer_id(const int * node_buffer_ids, int i) { return node_buffer_ids ? node_buffer_ids[i] : 0; } -static void ggml_gallocr_alloc_graph_impl(ggml_gallocr_t galloc, struct ggml_cgraph * graph, const int * node_buffer_ids) { +static void ggml_gallocr_alloc_graph_impl(ggml_gallocr_t galloc, struct ggml_cgraph * graph, const int * node_buffer_ids, const int * leaf_buffer_ids) { // clear hash tables memset(galloc->hash_set.keys, 0, galloc->hash_set.size * sizeof(struct ggml_tensor *)); memset(galloc->hash_values, 0, galloc->hash_set.size * sizeof(struct hash_node)); + // allocate leafs + // these may be tensors that the application is not using in the graph, but may still want to allocate for other purposes + for (int i = 0; i < graph->n_leafs; i++) { + struct ggml_tensor * leaf = graph->leafs[i]; + ggml_gallocr_allocate_node(galloc, leaf, get_node_buffer_id(leaf_buffer_ids, i)); + } + // count number of children and views - // allocate all graph inputs and leafs first to avoid overwriting them + // allocate other graph inputs and leafs first to avoid overwriting them for (int i = 0; i < graph->n_nodes; i++) { struct ggml_tensor * node = graph->nodes[i]; @@ -577,19 +572,6 @@ static void ggml_gallocr_alloc_graph_impl(ggml_gallocr_t galloc, struct ggml_cgr } } - // allocate the remaining leafs that are unused on the graph - // these are effectively static tensors that the application is not using in the graph, but may still want to allocate for other purposes - for (int i = 0; i < graph->n_leafs; i++) { - struct ggml_tensor * leaf = graph->leafs[i]; - struct hash_node * hn = ggml_gallocr_hash_get(galloc, leaf); - - if (hn->n_children == 0) { - assert(!hn->allocated); - // since buffer ids are only given for nodes, these leafs are always allocated in the first buffer - ggml_gallocr_allocate_node(galloc, leaf, 0); - } - } - // allocate tensors for (int i = 0; i < graph->n_nodes; i++) { struct ggml_tensor * node = graph->nodes[i]; @@ -652,7 +634,7 @@ static void ggml_gallocr_alloc_graph_impl(ggml_gallocr_t galloc, struct ggml_cgr } } -bool ggml_gallocr_reserve_n(ggml_gallocr_t galloc, struct ggml_cgraph * graph, const int * node_buffer_ids) { +bool ggml_gallocr_reserve_n(ggml_gallocr_t galloc, struct ggml_cgraph * graph, const int * node_buffer_ids, const int * leaf_buffer_ids) { size_t hash_size = graph->visited_hash_table.size; // initialize hash table @@ -676,7 +658,7 @@ bool ggml_gallocr_reserve_n(ggml_gallocr_t galloc, struct ggml_cgraph * graph, c } // allocate in hash table - ggml_gallocr_alloc_graph_impl(galloc, graph, node_buffer_ids); + ggml_gallocr_alloc_graph_impl(galloc, graph, node_buffer_ids, leaf_buffer_ids); // set the node_allocs from the hash table if (galloc->n_nodes < graph->n_nodes) { @@ -711,15 +693,16 @@ bool ggml_gallocr_reserve_n(ggml_gallocr_t galloc, struct ggml_cgraph * graph, c } if (galloc->n_leafs < graph->n_leafs) { free(galloc->leaf_allocs); - galloc->leaf_allocs = calloc(sizeof(struct tensor_alloc), graph->n_leafs); + galloc->leaf_allocs = calloc(sizeof(galloc->leaf_allocs[0]), graph->n_leafs); GGML_ASSERT(galloc->leaf_allocs != NULL); } galloc->n_leafs = graph->n_leafs; for (int i = 0; i < graph->n_leafs; i++) { struct ggml_tensor * leaf = graph->leafs[i]; struct hash_node * hn = ggml_gallocr_hash_get(galloc, leaf); - galloc->leaf_allocs[i].offset = hn->offset; - galloc->leaf_allocs[i].size_max = ggml_backend_buft_get_alloc_size(galloc->bufts[hn->buffer_id], leaf); + galloc->leaf_allocs[i].buffer_id = hn->buffer_id; + galloc->leaf_allocs[i].leaf.offset = hn->offset; + galloc->leaf_allocs[i].leaf.size_max = ggml_backend_buft_get_alloc_size(galloc->bufts[hn->buffer_id], leaf); } // reallocate buffers if needed @@ -727,7 +710,8 @@ bool ggml_gallocr_reserve_n(ggml_gallocr_t galloc, struct ggml_cgraph * graph, c size_t cur_size = galloc->buffers[i] ? ggml_backend_buffer_get_size(galloc->buffers[i]) : 0; size_t new_size = ggml_dyn_tallocr_max_size(galloc->buf_tallocs[i]); - if (new_size > cur_size) { + // even if there are no tensors allocated in this buffer, we still need to allocate it to initialize views + if (new_size > cur_size || galloc->buffers[i] == NULL) { #ifndef NDEBUG fprintf(stderr, "%s: reallocating %s buffer from size %.02f MiB to %.02f MiB\n", __func__, ggml_backend_buft_name(galloc->bufts[i]), cur_size / 1024.0 / 1024.0, new_size / 1024.0 / 1024.0); #endif @@ -744,30 +728,30 @@ bool ggml_gallocr_reserve_n(ggml_gallocr_t galloc, struct ggml_cgraph * graph, c } bool ggml_gallocr_reserve(ggml_gallocr_t galloc, struct ggml_cgraph *graph) { - return ggml_gallocr_reserve_n(galloc, graph, NULL); + return ggml_gallocr_reserve_n(galloc, graph, NULL, NULL); } -static void ggml_gallocr_init_tensor(ggml_gallocr_t galloc, struct ggml_tensor * node, int buffer_id, struct tensor_alloc * tensor_alloc) { - assert(node->data || node->view_src || ggml_backend_buffer_get_alloc_size(galloc->buffers[buffer_id], node) <= tensor_alloc->size_max); +static void ggml_gallocr_init_tensor(ggml_gallocr_t galloc, struct ggml_tensor * tensor, int buffer_id, struct tensor_alloc * tensor_alloc) { + assert(tensor->data || tensor->view_src || ggml_backend_buffer_get_alloc_size(galloc->buffers[buffer_id], tensor) <= tensor_alloc->size_max); - if (node->view_src != NULL) { - if (node->buffer == NULL) { + if (tensor->view_src != NULL) { + if (tensor->buffer == NULL) { assert(tensor_alloc->offset == SIZE_MAX); - if (node->view_src->buffer == NULL) { + if (tensor->view_src->buffer == NULL) { // this tensor was allocated without ggml-backend return; } - ggml_backend_view_init(galloc->buffers[buffer_id], node); + ggml_backend_view_init(galloc->buffers[buffer_id], tensor); } } else { - if (node->data == NULL) { + if (tensor->data == NULL) { assert(tensor_alloc->offset != SIZE_MAX); - assert(ggml_backend_buffer_get_alloc_size(galloc->buffers[buffer_id], node) <= tensor_alloc->size_max); + assert(ggml_backend_buffer_get_alloc_size(galloc->buffers[buffer_id], tensor) <= tensor_alloc->size_max); void * base = ggml_backend_buffer_get_base(galloc->buffers[buffer_id]); void * addr = (char *)base + tensor_alloc->offset; - ggml_backend_tensor_alloc(galloc->buffers[buffer_id], node, addr); + ggml_backend_tensor_alloc(galloc->buffers[buffer_id], tensor, addr); } else { - if (node->buffer == NULL) { + if (tensor->buffer == NULL) { // this tensor was allocated without ggml-backend return; } @@ -843,13 +827,18 @@ bool ggml_gallocr_alloc_graph(ggml_gallocr_t galloc, struct ggml_cgraph * graph) // reset buffers for (int i = 0; i < galloc->n_buffers; i++) { - // zero size buffers are not allocated if (galloc->buffers[i] != NULL) { ggml_backend_buffer_reset(galloc->buffers[i]); } } // allocate the graph tensors from the previous assignments + // leafs + for (int i = 0; i < graph->n_leafs; i++) { + struct ggml_tensor * leaf = graph->leafs[i]; + struct leaf_alloc * leaf_alloc = &galloc->leaf_allocs[i]; + ggml_gallocr_init_tensor(galloc, leaf, leaf_alloc->buffer_id, &leaf_alloc->leaf); + } // nodes for (int i = 0; i < graph->n_nodes; i++) { struct ggml_tensor * node = graph->nodes[i]; @@ -863,12 +852,6 @@ bool ggml_gallocr_alloc_graph(ggml_gallocr_t galloc, struct ggml_cgraph * graph) } ggml_gallocr_init_tensor(galloc, node, node_alloc->buffer_id, &node_alloc->dst); } - // leafs - for (int i = 0; i < graph->n_leafs; i++) { - struct ggml_tensor * leaf = graph->leafs[i]; - struct tensor_alloc * leaf_alloc = &galloc->leaf_allocs[i]; - ggml_gallocr_init_tensor(galloc, leaf, 0, leaf_alloc); - } return true; } @@ -900,12 +883,12 @@ static bool alloc_tensor_range(struct ggml_context * ctx, return false; } - struct ggml_tallocr * tallocr = ggml_tallocr_new(buffer); + struct ggml_tallocr tallocr = ggml_tallocr_new(buffer); for (struct ggml_tensor * t = first; t != last; t = ggml_get_next_tensor(ctx, t)) { if (t->data == NULL) { if (t->view_src == NULL) { - ggml_tallocr_alloc(tallocr, t); + ggml_tallocr_alloc(&tallocr, t); } else if (t->buffer == NULL) { ggml_backend_view_init(buffer, t); } @@ -917,8 +900,6 @@ static bool alloc_tensor_range(struct ggml_context * ctx, } } - ggml_tallocr_free(tallocr); - *buffers = realloc(*buffers, sizeof(ggml_backend_buffer_t) * (*n_buffers + 1)); (*buffers)[(*n_buffers)++] = buffer; diff --git a/src/ggml-backend-impl.h b/src/ggml-backend-impl.h index 2e9ba58a9..e475e20e5 100644 --- a/src/ggml-backend-impl.h +++ b/src/ggml-backend-impl.h @@ -86,12 +86,12 @@ extern "C" { // (optional) asynchronous tensor data access void (*GGML_CALL set_tensor_async)(ggml_backend_t backend, struct ggml_tensor * tensor, const void * data, size_t offset, size_t size); void (*GGML_CALL get_tensor_async)(ggml_backend_t backend, const struct ggml_tensor * tensor, void * data, size_t offset, size_t size); - bool (*GGML_CALL cpy_tensor_async)(ggml_backend_t backend, const struct ggml_tensor * src, struct ggml_tensor * dst); + bool (*GGML_CALL cpy_tensor_async)(ggml_backend_t backend_src, ggml_backend_t backend_dst, const struct ggml_tensor * src, struct ggml_tensor * dst); // (optional) complete all pending operations void (*GGML_CALL synchronize)(ggml_backend_t backend); - // create a plan for ggml_cgraph and free it + // compute graph with a plan (not used currently) ggml_backend_graph_plan_t (*GGML_CALL graph_plan_create) (ggml_backend_t backend, const struct ggml_cgraph * cgraph); void (*GGML_CALL graph_plan_free) (ggml_backend_t backend, ggml_backend_graph_plan_t plan); @@ -102,16 +102,27 @@ extern "C" { // check if the backend supports an operation bool (*GGML_CALL supports_op)(ggml_backend_t backend, const struct ggml_tensor * op); + + // (optional) event synchronization + ggml_backend_event_t (*GGML_CALL event_new) (ggml_backend_t backend); + void (*GGML_CALL event_free) (ggml_backend_event_t event); + void (*GGML_CALL event_record) (ggml_backend_event_t event); + void (*GGML_CALL event_wait) (ggml_backend_t backend, ggml_backend_event_t event); + void (*GGML_CALL event_synchronize) (ggml_backend_event_t event); }; struct ggml_backend { ggml_guid_t guid; struct ggml_backend_i iface; - ggml_backend_context_t context; }; + struct ggml_backend_event { + ggml_backend_t backend; + void * context; + }; + // // Backend registry // diff --git a/src/ggml-backend.c b/src/ggml-backend.c index d60d98414..31f8d5a6d 100644 --- a/src/ggml-backend.c +++ b/src/ggml-backend.c @@ -221,29 +221,29 @@ void ggml_backend_tensor_get_async(ggml_backend_t backend, const struct ggml_ten GGML_CALL void ggml_backend_tensor_set(struct ggml_tensor * tensor, const void * data, size_t offset, size_t size) { ggml_backend_buffer_t buf = tensor->view_src ? tensor->view_src->buffer : tensor->buffer; - GGML_ASSERT(tensor->data != NULL && "tensor not allocated"); GGML_ASSERT(buf != NULL && "tensor buffer not set"); + GGML_ASSERT(tensor->data != NULL && "tensor not allocated"); GGML_ASSERT(offset + size <= ggml_nbytes(tensor) && "tensor write out of bounds"); if (!size) { return; } - tensor->buffer->iface.set_tensor(buf, tensor, data, offset, size); + buf->iface.set_tensor(buf, tensor, data, offset, size); } GGML_CALL void ggml_backend_tensor_get(const struct ggml_tensor * tensor, void * data, size_t offset, size_t size) { ggml_backend_buffer_t buf = tensor->view_src ? tensor->view_src->buffer : tensor->buffer; + GGML_ASSERT(buf != NULL && "tensor buffer not set"); GGML_ASSERT(tensor->data != NULL && "tensor not allocated"); - GGML_ASSERT(tensor->buffer != NULL && "tensor buffer not set"); GGML_ASSERT(offset + size <= ggml_nbytes(tensor) && "tensor read out of bounds"); if (!size) { return; } - tensor->buffer->iface.get_tensor(buf, tensor, data, offset, size); + buf->iface.get_tensor(buf, tensor, data, offset, size); } void ggml_backend_synchronize(ggml_backend_t backend) { @@ -255,18 +255,30 @@ void ggml_backend_synchronize(ggml_backend_t backend) { } ggml_backend_graph_plan_t ggml_backend_graph_plan_create(ggml_backend_t backend, struct ggml_cgraph * cgraph) { + GGML_ASSERT(backend->iface.graph_plan_create != NULL); + return backend->iface.graph_plan_create(backend, cgraph); } void ggml_backend_graph_plan_free(ggml_backend_t backend, ggml_backend_graph_plan_t plan) { + GGML_ASSERT(backend->iface.graph_plan_free != NULL); + backend->iface.graph_plan_free(backend, plan); } enum ggml_status ggml_backend_graph_plan_compute(ggml_backend_t backend, ggml_backend_graph_plan_t plan) { + GGML_ASSERT(backend->iface.graph_plan_compute != NULL); + return backend->iface.graph_plan_compute(backend, plan); } enum ggml_status ggml_backend_graph_compute(ggml_backend_t backend, struct ggml_cgraph * cgraph) { + enum ggml_status err = ggml_backend_graph_compute_async(backend, cgraph); + ggml_backend_synchronize(backend); + return err; +} + +bool ggml_backend_graph_compute_async(ggml_backend_t backend, struct ggml_cgraph * cgraph) { return backend->iface.graph_compute(backend, cgraph); } @@ -314,34 +326,68 @@ void ggml_backend_tensor_copy(struct ggml_tensor * src, struct ggml_tensor * dst } } -void ggml_backend_tensor_copy_async(ggml_backend_t backend, struct ggml_tensor * src, struct ggml_tensor * dst) { +void ggml_backend_tensor_copy_async(ggml_backend_t backend_src, ggml_backend_t backend_dst, struct ggml_tensor * src, struct ggml_tensor * dst) { GGML_ASSERT(ggml_are_same_layout(src, dst) && "cannot copy tensors with different layouts"); if (src == dst) { return; } - if (ggml_backend_buft_supports_backend(src->buffer->buft, backend) && ggml_backend_buft_supports_backend(dst->buffer->buft, backend)) { - if (backend->iface.cpy_tensor_async != NULL) { - if (backend->iface.cpy_tensor_async(backend, src, dst)) { - return; - } + if (backend_dst->iface.cpy_tensor_async != NULL) { + if (backend_dst->iface.cpy_tensor_async(backend_src, backend_dst, src, dst)) { + return; } } - size_t nbytes = ggml_nbytes(src); + // an async copy would normally happen after all the queued operations on both backends are completed + // sync src, set_async dst if (ggml_backend_buffer_is_host(src->buffer)) { - ggml_backend_tensor_set_async(backend, dst, src->data, 0, nbytes); - } - else { + ggml_backend_synchronize(backend_src); + ggml_backend_tensor_set_async(backend_dst, dst, src->data, 0, ggml_nbytes(src)); + } else { + ggml_backend_synchronize(backend_src); ggml_backend_tensor_copy(src, dst); + ggml_backend_synchronize(backend_dst); + } +} + +// events + +ggml_backend_event_t ggml_backend_event_new(ggml_backend_t backend) { + if (backend->iface.event_new == NULL) { + return NULL; + } + return backend->iface.event_new(backend); +} + +void ggml_backend_event_free(ggml_backend_event_t event) { + if (event == NULL) { + return; } + event->backend->iface.event_free(event); +} + +void ggml_backend_event_record(ggml_backend_event_t event) { + GGML_ASSERT(event->backend->iface.event_record != NULL); + + event->backend->iface.event_record(event); +} + +void ggml_backend_event_synchronize(ggml_backend_event_t event) { + GGML_ASSERT(event->backend->iface.event_synchronize != NULL); + + event->backend->iface.event_synchronize(event); } +void ggml_backend_event_wait(ggml_backend_t backend, ggml_backend_event_t event) { + GGML_ASSERT(backend->iface.event_wait != NULL); + + backend->iface.event_wait(backend, event); +} // backend registry -#define GGML_MAX_BACKENDS_REG 16 +#define GGML_REG_MAX_BACKENDS 16 struct ggml_backend_reg { char name[128]; @@ -350,7 +396,7 @@ struct ggml_backend_reg { void * user_data; }; -static struct ggml_backend_reg ggml_backend_registry[GGML_MAX_BACKENDS_REG]; +static struct ggml_backend_reg ggml_backend_registry[GGML_REG_MAX_BACKENDS]; static size_t ggml_backend_registry_count = 0; GGML_CALL static ggml_backend_t ggml_backend_reg_cpu_init(const char * params, void * user_data); @@ -395,7 +441,7 @@ GGML_CALL static void ggml_backend_registry_init(void) { } GGML_CALL void ggml_backend_register(const char * name, ggml_backend_init_fn init_fn, ggml_backend_buffer_type_t default_buffer_type, void * user_data) { - GGML_ASSERT(ggml_backend_registry_count < GGML_MAX_BACKENDS_REG); + GGML_ASSERT(ggml_backend_registry_count < GGML_REG_MAX_BACKENDS); size_t id = ggml_backend_registry_count; @@ -746,8 +792,12 @@ GGML_CALL static enum ggml_status ggml_backend_cpu_graph_compute(ggml_backend_t struct ggml_cplan cplan = ggml_graph_plan(cgraph, cpu_ctx->n_threads); if (cpu_ctx->work_size < cplan.work_size) { - // TODO: may be faster to free and use malloc to avoid the copy - cpu_ctx->work_data = realloc(cpu_ctx->work_data, cplan.work_size); + free(cpu_ctx->work_data); + cpu_ctx->work_data = malloc(cplan.work_size); + if (cpu_ctx->work_data == NULL) { + cpu_ctx->work_size = 0; + return GGML_STATUS_ALLOC_FAILED; + } cpu_ctx->work_size = cplan.work_size; } cplan.work_data = cpu_ctx->work_data; @@ -784,6 +834,11 @@ static struct ggml_backend_i cpu_backend_i = { /* .graph_plan_compute = */ ggml_backend_cpu_graph_plan_compute, /* .graph_compute = */ ggml_backend_cpu_graph_compute, /* .supports_op = */ ggml_backend_cpu_supports_op, + /* .event_new = */ NULL, + /* .event_free = */ NULL, + /* .event_record = */ NULL, + /* .event_wait = */ NULL, + /* .event_synchronize = */ NULL, }; static ggml_guid_t ggml_backend_cpu_guid(void) { @@ -939,15 +994,27 @@ static bool ggml_is_view_op(enum ggml_op op) { // scheduler -#define GGML_MAX_BACKENDS 16 -#define GGML_MAX_SPLITS 256 -#define GGML_MAX_SPLIT_INPUTS 16 +#ifndef GGML_SCHED_MAX_BACKENDS +#define GGML_SCHED_MAX_BACKENDS 16 +#endif + +#ifndef GGML_SCHED_MAX_SPLITS +#define GGML_SCHED_MAX_SPLITS 256 +#endif + +#ifndef GGML_SCHED_MAX_SPLIT_INPUTS +#define GGML_SCHED_MAX_SPLIT_INPUTS 16 +#endif + +#ifndef GGML_SCHED_MAX_COPIES +#define GGML_SCHED_MAX_COPIES 4 +#endif struct ggml_backend_sched_split { int backend_id; int i_start; int i_end; - struct ggml_tensor * inputs[GGML_MAX_SPLIT_INPUTS]; + struct ggml_tensor * inputs[GGML_SCHED_MAX_SPLIT_INPUTS]; int n_inputs; // graph view of this split struct ggml_cgraph graph; @@ -955,45 +1022,53 @@ struct ggml_backend_sched_split { struct ggml_backend_sched { bool is_reset; // true if the scheduler has been reset since the last graph split + bool is_alloc; int n_backends; - ggml_backend_t backends[GGML_MAX_BACKENDS]; - ggml_backend_buffer_type_t bufts[GGML_MAX_BACKENDS]; + ggml_backend_t backends[GGML_SCHED_MAX_BACKENDS]; + ggml_backend_buffer_type_t bufts[GGML_SCHED_MAX_BACKENDS]; ggml_gallocr_t galloc; // hash keys of the nodes in the graph struct ggml_hash_set hash_set; // hash values int * tensor_backend_id; - struct ggml_tensor * (* tensor_copies)[GGML_MAX_BACKENDS]; + struct ggml_tensor * (* tensor_copies)[GGML_SCHED_MAX_BACKENDS][GGML_SCHED_MAX_COPIES]; - int * node_backend_ids; // [n_nodes] - int n_nodes; + int * node_backend_ids; // [graph_size] + int * leaf_backend_ids; // [graph_size] // copy of the graph with modified inputs struct ggml_cgraph * graph; - struct ggml_backend_sched_split splits[GGML_MAX_SPLITS]; + // graph splits + struct ggml_backend_sched_split splits[GGML_SCHED_MAX_SPLITS]; int n_splits; + // pipeline parallelism support + int n_copies; + int cur_copy; + ggml_backend_event_t events[GGML_SCHED_MAX_BACKENDS][GGML_SCHED_MAX_COPIES]; + struct ggml_tensor * graph_inputs[GGML_SCHED_MAX_SPLIT_INPUTS]; + int n_graph_inputs; + struct ggml_context * ctx; ggml_backend_sched_eval_callback callback_eval; void * callback_eval_user_data; // align context_buffer to GGML_MEM_ALIGN - #ifdef _MSC_VER +#ifdef _MSC_VER __declspec(align(GGML_MEM_ALIGN)) - #else +#else __attribute__((aligned(GGML_MEM_ALIGN))) - #endif - char context_buffer[GGML_MAX_SPLITS*GGML_MAX_SPLIT_INPUTS*2*sizeof(struct ggml_tensor) + sizeof(struct ggml_cgraph)]; +#endif + char context_buffer[GGML_SCHED_MAX_SPLITS*GGML_SCHED_MAX_SPLIT_INPUTS*2*sizeof(struct ggml_tensor) + sizeof(struct ggml_cgraph)]; }; -#define hash_id(node) ggml_hash_find_or_insert(sched->hash_set, node) -#define tensor_backend_id(node) sched->tensor_backend_id[hash_id(node)] -#define tensor_backend(node) (tensor_backend_id(node) == -1 ? NULL : sched->backends[tensor_backend_id(node)]) +#define hash_id(tensor) ggml_hash_find_or_insert(sched->hash_set, tensor) +#define tensor_backend_id(tensor) sched->tensor_backend_id[hash_id(tensor)] // returns the priority of the backend, lower id is higher priority static int ggml_backend_sched_backend_id(ggml_backend_sched_t sched, ggml_backend_t backend) { @@ -1005,7 +1080,8 @@ static int ggml_backend_sched_backend_id(ggml_backend_sched_t sched, ggml_backen return -1; } -static int ggml_backend_sched_backend_from_buffer(ggml_backend_sched_t sched, ggml_backend_buffer_t buffer) { +static int ggml_backend_sched_backend_from_buffer(ggml_backend_sched_t sched, const struct ggml_tensor * tensor) { + ggml_backend_buffer_t buffer = tensor->buffer; if (buffer == NULL) { return -1; } @@ -1016,12 +1092,16 @@ static int ggml_backend_sched_backend_from_buffer(ggml_backend_sched_t sched, gg return i; } } - GGML_ASSERT(false && "tensor buffer type not supported by any backend"); - return -1; // silence warning + + fprintf(stderr, "%s: error: no backend supports buffer type %s used in tensor %s\n", + __func__, ggml_backend_buffer_name(buffer), tensor->name); + GGML_ASSERT(false); + + return -1; } #if 0 -static char causes[GGML_DEFAULT_GRAPH_SIZE*16 + GGML_MAX_SPLITS*GGML_MAX_SPLIT_INPUTS][128]; // debug only +static char causes[GGML_DEFAULT_GRAPH_SIZE*16 + GGML_SCHED_MAX_SPLITS*GGML_SCHED_MAX_SPLIT_INPUTS][128]; // debug only #define SET_CAUSE(node, ...) sprintf(causes[hash_id(node)], __VA_ARGS__) #define GET_CAUSE(node) causes[hash_id(node)] #else @@ -1035,19 +1115,28 @@ static int ggml_backend_sched_backend_id_from_cur(ggml_backend_sched_t sched, st // assign pre-allocated nodes to their backend // dst - int cur_backend = ggml_backend_sched_backend_from_buffer(sched, tensor->buffer); + int cur_backend = ggml_backend_sched_backend_from_buffer(sched, tensor); if (cur_backend != -1) { - SET_CAUSE(node, "1.dst"); + SET_CAUSE(tensor, "1.dst"); return cur_backend; } + // view_src if (tensor->view_src != NULL) { - cur_backend = ggml_backend_sched_backend_from_buffer(sched, tensor->view_src->buffer); + cur_backend = ggml_backend_sched_backend_from_buffer(sched, tensor->view_src); if (cur_backend != -1) { - SET_CAUSE(node, "1.vsrc"); + SET_CAUSE(tensor, "1.vsrc"); return cur_backend; } } + + // input + if (tensor->flags & GGML_TENSOR_FLAG_INPUT) { + cur_backend = sched->n_backends - 1; // last backend (assumed CPU) + SET_CAUSE(tensor, "1.inp"); + return cur_backend; + } + // assign nodes that use weights to the backend of the weights for (int i = 0; i < GGML_MAX_SRC; i++) { const struct ggml_tensor * src = tensor->src[i]; @@ -1055,9 +1144,9 @@ static int ggml_backend_sched_backend_id_from_cur(ggml_backend_sched_t sched, st continue; } if (src->buffer != NULL && src->buffer->usage == GGML_BACKEND_BUFFER_USAGE_WEIGHTS) { - int src_backend = ggml_backend_sched_backend_from_buffer(sched, src->buffer); + int src_backend = ggml_backend_sched_backend_from_buffer(sched, src); // operations with weights are always run on the same backend as the weights - SET_CAUSE(node, "1.wgt%d", i); + SET_CAUSE(tensor, "1.wgt%d", i); return src_backend; } } @@ -1093,7 +1182,7 @@ static void ggml_backend_sched_print_assignments(ggml_backend_sched_t sched, str if (ggml_is_view_op(node->op)) { continue; } - ggml_backend_t tensor_backend = tensor_backend(node); + ggml_backend_t tensor_backend = ggml_backend_sched_get_tensor_backend(sched, node); fprintf(stderr, "node #%3d (%10.10s): %20.20s (%5.5s) [%5.5s %8.8s]:", i, ggml_op_name(node->op), node->name, fmt_size(ggml_nbytes(node)), tensor_backend ? ggml_backend_name(tensor_backend) : "NULL", GET_CAUSE(node)); for (int j = 0; j < GGML_MAX_SRC; j++) { @@ -1101,7 +1190,7 @@ static void ggml_backend_sched_print_assignments(ggml_backend_sched_t sched, str if (src == NULL) { continue; } - ggml_backend_t src_backend = tensor_backend(src); + ggml_backend_t src_backend = ggml_backend_sched_get_tensor_backend(sched, src); fprintf(stderr, " %20.20s (%5.5s) [%5.5s %8.8s]", src->name, fmt_size(ggml_nbytes(src)), src_backend ? ggml_backend_name(src_backend) : "NULL", GET_CAUSE(src)); } @@ -1118,6 +1207,7 @@ static void ggml_backend_sched_print_assignments(ggml_backend_sched_t sched, str static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct ggml_cgraph * graph) { // reset splits sched->n_splits = 0; + sched->n_graph_inputs = 0; sched->is_reset = false; struct ggml_init_params params = { @@ -1163,7 +1253,7 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg } } #ifdef DEBUG_PASS1 - fprintf(stderr, "PASS 1 ASSIGNMENTS\n"); sched_print_assignments(sched, graph); + fprintf(stderr, "PASS 1 ASSIGNMENTS\n"); ggml_backend_sched_print_assignments(sched, graph); #endif // pass 2: expand current backend assignments @@ -1171,10 +1261,11 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg // expand gpu backends (i.e. non last prio) up and down, ignoring cpu (the lowest priority backend) // thus, cpu will never be used unless weights are on cpu, or there are no gpu ops between cpu ops - // pass 2.1 expand gpu up + + // pass 2.2 expand gpu down { int cur_backend_id = -1; - for (int i = graph->n_nodes - 1; i >= 0; i--) { + for (int i = 0; i < graph->n_nodes; i++) { struct ggml_tensor * node = graph->nodes[i]; if (ggml_is_view_op(node->op)) { continue; @@ -1189,15 +1280,15 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg } } else { tensor_backend_id(node) = cur_backend_id; - SET_CAUSE(node, "2.1"); + SET_CAUSE(node, "2.2"); } } } - // pass 2.2 expand gpu down + // pass 2.1 expand gpu up { int cur_backend_id = -1; - for (int i = 0; i < graph->n_nodes; i++) { + for (int i = graph->n_nodes - 1; i >= 0; i--) { struct ggml_tensor * node = graph->nodes[i]; if (ggml_is_view_op(node->op)) { continue; @@ -1212,15 +1303,16 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg } } else { tensor_backend_id(node) = cur_backend_id; - SET_CAUSE(node, "2.2"); + SET_CAUSE(node, "2.1"); } } } - // pass 2.3 expand rest up + + // pass 2.4 expand rest down { int cur_backend_id = -1; - for (int i = graph->n_nodes - 1; i >= 0; i--) { + for (int i = 0; i < graph->n_nodes; i++) { struct ggml_tensor * node = graph->nodes[i]; if (ggml_is_view_op(node->op)) { continue; @@ -1230,15 +1322,14 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg cur_backend_id = tensor_backend_id; } else { tensor_backend_id(node) = cur_backend_id; - SET_CAUSE(node, "2.3"); + SET_CAUSE(node, "2.4"); } } } - - // pass 2.4 expand rest down + // pass 2.3 expand rest up { int cur_backend_id = -1; - for (int i = 0; i < graph->n_nodes; i++) { + for (int i = graph->n_nodes - 1; i >= 0; i--) { struct ggml_tensor * node = graph->nodes[i]; if (ggml_is_view_op(node->op)) { continue; @@ -1248,12 +1339,13 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg cur_backend_id = tensor_backend_id; } else { tensor_backend_id(node) = cur_backend_id; - SET_CAUSE(node, "2.4"); + SET_CAUSE(node, "2.3"); } } } + #ifdef DEBUG_PASS2 - fprintf(stderr, "PASS 2 ASSIGNMENTS\n"); sched_print_assignments(sched, graph); + fprintf(stderr, "PASS 2 ASSIGNMENTS\n"); ggml_backend_sched_print_assignments(sched, graph); #endif // pass 3: assign backends to remaining src from dst and view_src @@ -1283,7 +1375,7 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg } } #ifdef DEBUG_PASS3 - fprintf(stderr, "PASS 3 ASSIGNMENTS\n"); sched_print_assignments(sched, graph); + fprintf(stderr, "PASS 3 ASSIGNMENTS\n"); ggml_backend_sched_print_assignments(sched, graph); #endif // pass 4: split graph, find tensors that need to be copied @@ -1315,7 +1407,7 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg if (tensor_backend_id != cur_backend_id) { sched->splits[cur_split].i_end = i; cur_split++; - GGML_ASSERT(cur_split < GGML_MAX_SPLITS); + GGML_ASSERT(cur_split < GGML_SCHED_MAX_SPLITS); sched->splits[cur_split].backend_id = tensor_backend_id; sched->splits[cur_split].i_start = i; sched->splits[cur_split].n_inputs = 0; @@ -1328,25 +1420,57 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg if (src == NULL) { continue; } + int src_backend_id = tensor_backend_id(src); assert(src_backend_id != -1); // all inputs should be assigned by now + + if (src->flags & GGML_TENSOR_FLAG_INPUT) { + size_t id = hash_id(src); + if (sched->tensor_copies[id][src_backend_id][0] == NULL) { + ggml_backend_t backend = sched->backends[src_backend_id]; + for (int c = 0; c < sched->n_copies; c++) { + struct ggml_tensor * tensor_copy; + if (c == sched->cur_copy) { + tensor_copy = src; // use the original tensor as the current copy + } else { + tensor_copy = ggml_dup_tensor_layout(sched->ctx, src); + ggml_format_name(tensor_copy, "%s#%s#%d", ggml_backend_name(backend), src->name, c); + } + if (sched->n_copies > 1) { + ggml_set_input(tensor_copy); + ggml_set_output(tensor_copy); // prevent ggml-alloc from overwriting the tensor + } + sched->tensor_copies[id][src_backend_id][c] = tensor_copy; + tensor_backend_id(tensor_copy) = src_backend_id; + SET_CAUSE(tensor_copy, "4.cpy"); + } + int n_graph_inputs = sched->n_graph_inputs++; + GGML_ASSERT(n_graph_inputs < GGML_SCHED_MAX_SPLIT_INPUTS); + sched->graph_inputs[n_graph_inputs] = src; + } + } + if (src_backend_id != tensor_backend_id) { // create a copy of the input in the split's backend size_t id = hash_id(src); - if (sched->tensor_copies[id][cur_backend_id] == NULL) { + if (sched->tensor_copies[id][cur_backend_id][0] == NULL) { ggml_backend_t backend = sched->backends[cur_backend_id]; - struct ggml_tensor * tensor_copy = ggml_dup_tensor_layout(sched->ctx, src); - ggml_format_name(tensor_copy, "%s#%s", ggml_backend_name(backend), src->name); - - sched->tensor_copies[id][cur_backend_id] = tensor_copy; - tensor_backend_id(tensor_copy) = cur_backend_id; - SET_CAUSE(tensor_copy, "4.cpy"); - + for (int c = 0; c < sched->n_copies; c++) { + struct ggml_tensor * tensor_copy = ggml_dup_tensor_layout(sched->ctx, src); + ggml_format_name(tensor_copy, "%s#%s#%d", ggml_backend_name(backend), src->name, c); + if (sched->n_copies > 1) { + ggml_set_input(tensor_copy); + ggml_set_output(tensor_copy); // prevent ggml-alloc from overwriting the tensor + } + sched->tensor_copies[id][cur_backend_id][c] = tensor_copy; + tensor_backend_id(tensor_copy) = cur_backend_id; + SET_CAUSE(tensor_copy, "4.cpy"); + } int n_inputs = sched->splits[cur_split].n_inputs++; - GGML_ASSERT(n_inputs < GGML_MAX_SPLIT_INPUTS); + GGML_ASSERT(n_inputs < GGML_SCHED_MAX_SPLIT_INPUTS); sched->splits[cur_split].inputs[n_inputs] = src; } - node->src[j] = sched->tensor_copies[id][cur_backend_id]; + node->src[j] = sched->tensor_copies[id][cur_backend_id][sched->cur_copy]; } } } @@ -1354,37 +1478,39 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg sched->n_splits = cur_split + 1; } #ifdef DEBUG_PASS4 - fprintf(stderr, "PASS 4 ASSIGNMENTS\n"); sched_print_assignments(sched, graph); + fprintf(stderr, "PASS 4 ASSIGNMENTS\n"); ggml_backend_sched_print_assignments(sched, graph); #endif #ifndef NDEBUG // sanity check: all sources should have the same backend as the node for (int i = 0; i < graph->n_nodes; i++) { struct ggml_tensor * node = graph->nodes[i]; - ggml_backend_t tensor_backend = tensor_backend(node); + ggml_backend_t tensor_backend = ggml_backend_sched_get_tensor_backend(sched, node); if (tensor_backend == NULL) { fprintf(stderr, "!!!!!!! %s has no backend\n", node->name); } - if (node->view_src != NULL && tensor_backend != tensor_backend(node->view_src)) { + if (node->view_src != NULL && tensor_backend != ggml_backend_sched_get_tensor_backend(sched, node->view_src)) { fprintf(stderr, "!!!!!!! %s has backend %s, view_src %s has backend %s\n", node->name, tensor_backend ? ggml_backend_name(tensor_backend) : "NULL", - node->view_src->name, tensor_backend(node->view_src) ? ggml_backend_name(tensor_backend(node->view_src)) : "NULL"); + node->view_src->name, ggml_backend_sched_get_tensor_backend(sched, node->view_src) ? + ggml_backend_name(ggml_backend_sched_get_tensor_backend(sched, node->view_src)) : "NULL"); } for (int j = 0; j < GGML_MAX_SRC; j++) { struct ggml_tensor * src = node->src[j]; if (src == NULL) { continue; } - ggml_backend_t src_backend = tensor_backend(src); + ggml_backend_t src_backend = ggml_backend_sched_get_tensor_backend(sched, src); if (src_backend != tensor_backend /* && src_backend != NULL */) { fprintf(stderr, "!!!! %s has backend %s, src %d (%s) has backend %s\n", node->name, tensor_backend ? ggml_backend_name(tensor_backend) : "NULL", j, src->name, src_backend ? ggml_backend_name(src_backend) : "NULL"); } - if (src->view_src != NULL && src_backend != tensor_backend(src->view_src)) { + if (src->view_src != NULL && src_backend != ggml_backend_sched_get_tensor_backend(sched, src->view_src)) { fprintf(stderr, "!!!!!!! [src] %s has backend %s, view_src %s has backend %s\n", src->name, src_backend ? ggml_backend_name(src_backend) : "NULL", - src->view_src->name, tensor_backend(src->view_src) ? ggml_backend_name(tensor_backend(src->view_src)) : "NULL"); + src->view_src->name, ggml_backend_sched_get_tensor_backend(sched, src->view_src) ? + ggml_backend_name(ggml_backend_sched_get_tensor_backend(sched, src->view_src)) : "NULL"); } } } @@ -1392,18 +1518,20 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg #endif // create copies of the graph for each split - // FIXME: avoid this copy, pass split inputs to ggml_gallocr_alloc_graph_n in some other way - struct ggml_cgraph * graph_copy = ggml_new_graph_custom(sched->ctx, graph->n_nodes + sched->n_splits*GGML_MAX_SPLIT_INPUTS, false); + // TODO: avoid this copy + struct ggml_cgraph * graph_copy = ggml_new_graph_custom(sched->ctx, graph->n_nodes + sched->n_splits*GGML_SCHED_MAX_SPLIT_INPUTS, false); for (int i = 0; i < sched->n_splits; i++) { struct ggml_backend_sched_split * split = &sched->splits[i]; split->graph = ggml_graph_view(graph, split->i_start, split->i_end); + // add inputs to the graph copy so that they are allocated by ggml-alloc at the start of the split for (int j = 0; j < split->n_inputs; j++) { struct ggml_tensor * input = split->inputs[j]; - struct ggml_tensor * input_cpy = sched->tensor_copies[hash_id(input)][split->backend_id]; + struct ggml_tensor * input_cpy = sched->tensor_copies[hash_id(input)][split->backend_id][sched->cur_copy]; // add a dependency to the input source so that it is not freed before the copy is done struct ggml_tensor * input_dep = ggml_view_tensor(sched->ctx, input); + input_dep->src[0] = input; sched->node_backend_ids[graph_copy->n_nodes] = tensor_backend_id(input); graph_copy->nodes[graph_copy->n_nodes++] = input_dep; @@ -1417,18 +1545,56 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg graph_copy->nodes[graph_copy->n_nodes++] = graph->nodes[j]; } } + + if (sched->n_copies > 1) { + // add input copies as leafs so that they are allocated first + for (int i = 0; i < sched->n_graph_inputs; i++) { + struct ggml_tensor * input = sched->graph_inputs[i]; + size_t id = hash_id(input); + int backend_id = tensor_backend_id(input); + for (int c = 0; c < sched->n_copies; c++) { + struct ggml_tensor * input_cpy = sched->tensor_copies[id][backend_id][c]; + sched->leaf_backend_ids[graph_copy->n_leafs] = backend_id; + graph_copy->leafs[graph_copy->n_leafs++] = input_cpy; + } + } + + for (int i = 0; i < sched->n_splits; i++) { + struct ggml_backend_sched_split * split = &sched->splits[i]; + int backend_id = split->backend_id; + for (int j = 0; j < split->n_inputs; j++) { + struct ggml_tensor * input = split->inputs[j]; + size_t id = hash_id(input); + for (int c = 0; c < sched->n_copies; c++) { + struct ggml_tensor * input_cpy = sched->tensor_copies[id][backend_id][c]; + sched->leaf_backend_ids[graph_copy->n_leafs] = backend_id; + graph_copy->leafs[graph_copy->n_leafs++] = input_cpy; + } + } + } + } + + // add leafs from the original graph + for (int i = 0; i < graph->n_leafs; i++) { + struct ggml_tensor * leaf = graph->leafs[i]; + sched->leaf_backend_ids[graph_copy->n_leafs] = tensor_backend_id(leaf); + graph_copy->leafs[graph_copy->n_leafs++] = leaf; + } + sched->graph = graph_copy; } static bool ggml_backend_sched_alloc_splits(ggml_backend_sched_t sched) { - // ggml_gallocr_reserve_n(sched->galloc, sched->graph, sched->node_backend_ids); + // allocate graph if (!ggml_gallocr_alloc_graph(sched->galloc, sched->graph)) { + // the re-allocation may cause the split inputs to be moved to a different address + ggml_backend_sched_synchronize(sched); #ifndef NDEBUG - fprintf(stderr, "ggml_backend_sched: failed to allocate graph, reserving\n"); + fprintf(stderr, "%s: failed to allocate graph, reserving\n", __func__); #endif - ggml_gallocr_reserve_n(sched->galloc, sched->graph, sched->node_backend_ids); + ggml_gallocr_reserve_n(sched->galloc, sched->graph, sched->node_backend_ids, sched->leaf_backend_ids); if (!ggml_gallocr_alloc_graph(sched->galloc, sched->graph)) { - fprintf(stderr, "ggml_backend_sched: failed to allocate graph\n"); + fprintf(stderr, "%s: failed to allocate graph\n", __func__); return false; } } @@ -1437,9 +1603,6 @@ static bool ggml_backend_sched_alloc_splits(ggml_backend_sched_t sched) { } static enum ggml_status ggml_backend_sched_compute_splits(ggml_backend_sched_t sched) { - uint64_t copy_us[GGML_MAX_BACKENDS] = {0}; - uint64_t compute_us[GGML_MAX_BACKENDS] = {0}; - struct ggml_backend_sched_split * splits = sched->splits; for (int i = 0; i < sched->n_splits; i++) { @@ -1448,34 +1611,36 @@ static enum ggml_status ggml_backend_sched_compute_splits(ggml_backend_sched_t s ggml_backend_t split_backend = sched->backends[split_backend_id]; // copy the input tensors to the split backend - uint64_t copy_start_us = ggml_time_us(); for (int j = 0; j < split->n_inputs; j++) { + ggml_backend_t input_backend = ggml_backend_sched_get_tensor_backend(sched, split->inputs[j]); struct ggml_tensor * input = split->inputs[j]; - struct ggml_tensor * input_cpy = sched->tensor_copies[hash_id(input)][split_backend_id]; + struct ggml_tensor * input_cpy = sched->tensor_copies[hash_id(input)][split_backend_id][sched->cur_copy]; - GGML_ASSERT(input->buffer != NULL); - GGML_ASSERT(input_cpy->buffer != NULL); + if (input->flags & GGML_TENSOR_FLAG_INPUT) { + // inputs from the user must be copied immediately to prevent the user overwriting the data before the copy is done + if (sched->events[split_backend_id][sched->cur_copy] != NULL) { + ggml_backend_event_synchronize(sched->events[split_backend_id][sched->cur_copy]); + } else { + ggml_backend_synchronize(split_backend); + } + ggml_backend_tensor_copy(input, input_cpy); + } else { + if (sched->events[split_backend_id][sched->cur_copy] != NULL) { + ggml_backend_event_wait(split_backend, sched->events[split_backend_id][sched->cur_copy]); + } else { + ggml_backend_synchronize(split_backend); + ggml_backend_synchronize(input_backend); + } - ggml_backend_tensor_copy_async(split_backend, input, input_cpy); + ggml_backend_tensor_copy_async(input_backend, split_backend, input, input_cpy); + } } - //ggml_backend_synchronize(split_backend); // necessary to measure copy time - int64_t copy_end_us = ggml_time_us(); - copy_us[split_backend_id] += copy_end_us - copy_start_us; -#if 0 - char split_filename[GGML_MAX_NAME]; - snprintf(split_filename, GGML_MAX_NAME, "split_%i_%s.dot", i, ggml_backend_name(split_backend)); - ggml_graph_dump_dot(split->graph, NULL, split_filename); -#endif - - - uint64_t compute_start_us = ggml_time_us(); if (!sched->callback_eval) { - enum ggml_status ec = ggml_backend_graph_compute(split_backend, &split->graph); + enum ggml_status ec = ggml_backend_graph_compute_async(split_backend, &split->graph); if (ec != GGML_STATUS_SUCCESS) { return ec; } - //ggml_backend_synchronize(split_backend); // necessary to measure compute time } else { // similar to ggml_backend_compare_graph_backend for (int j0 = 0; j0 < split->graph.n_nodes; j0++) { @@ -1494,11 +1659,14 @@ static enum ggml_status ggml_backend_sched_compute_splits(ggml_backend_sched_t s struct ggml_cgraph gv = ggml_graph_view(&split->graph, j0, j1 + 1); - enum ggml_status ec = ggml_backend_graph_compute(split_backend, &gv); + enum ggml_status ec = ggml_backend_graph_compute_async(split_backend, &gv); if (ec != GGML_STATUS_SUCCESS) { return ec; } + // TODO: pass backend to the callback, then the user can decide if they want to synchronize + ggml_backend_synchronize(split_backend); + if (need && !sched->callback_eval(t, false, sched->callback_eval_user_data)) { break; } @@ -1506,39 +1674,54 @@ static enum ggml_status ggml_backend_sched_compute_splits(ggml_backend_sched_t s j0 = j1; } } - uint64_t compute_end_us = ggml_time_us(); - compute_us[split_backend_id] += compute_end_us - compute_start_us; - } -#if 0 - // per-backend timings - fprintf(stderr, "sched_compute_splits times (%d splits):\n", sched->n_splits); - for (int i = 0; i < sched->n_backends; i++) { - if (copy_us[i] > 0 || compute_us[i] > 0) { - fprintf(stderr, "\t%5.5s: %lu us copy, %lu us compute\n", ggml_backend_name(sched->backends[i]), copy_us[i], compute_us[i]); + // record the event of this copy + if (split->n_inputs > 0) { + if (sched->events[split_backend_id][sched->cur_copy] != NULL) { + ggml_backend_event_record(sched->events[split_backend_id][sched->cur_copy]); + } } } -#endif + + sched->cur_copy = (sched->cur_copy + 1) % sched->n_copies; return GGML_STATUS_SUCCESS; } -ggml_backend_sched_t ggml_backend_sched_new(ggml_backend_t * backends, ggml_backend_buffer_type_t * bufts, int n_backends, size_t graph_size) { +ggml_backend_sched_t ggml_backend_sched_new( + ggml_backend_t * backends, + ggml_backend_buffer_type_t * bufts, + int n_backends, + size_t graph_size, + bool parallel) { GGML_ASSERT(n_backends > 0); - GGML_ASSERT(n_backends <= GGML_MAX_BACKENDS); + GGML_ASSERT(n_backends <= GGML_SCHED_MAX_BACKENDS); + GGML_ASSERT(ggml_backend_is_cpu(backends[n_backends - 1])); // last backend must be CPU struct ggml_backend_sched * sched = calloc(sizeof(struct ggml_backend_sched), 1); // initialize hash table - sched->hash_set = ggml_hash_set_new(graph_size + GGML_MAX_SPLITS*GGML_MAX_SPLIT_INPUTS); + sched->hash_set = ggml_hash_set_new(graph_size + GGML_SCHED_MAX_SPLITS*GGML_SCHED_MAX_SPLIT_INPUTS); sched->tensor_backend_id = calloc(sizeof(sched->tensor_backend_id[0]), sched->hash_set.size); sched->tensor_copies = calloc(sizeof(sched->tensor_copies[0]), sched->hash_set.size); sched->node_backend_ids = calloc(sizeof(sched->node_backend_ids[0]), graph_size); + sched->leaf_backend_ids = calloc(sizeof(sched->leaf_backend_ids[0]), graph_size); sched->n_backends = n_backends; - for (int i = 0; i < n_backends; i++) { - sched->backends[i] = backends[i]; - sched->bufts[i] = bufts ? bufts[i] : ggml_backend_get_default_buffer_type(backends[i]); + + sched->n_copies = parallel ? GGML_SCHED_MAX_COPIES : 1; + + GGML_ASSERT(sched->n_copies <= GGML_SCHED_MAX_COPIES); + + for (int b = 0; b < n_backends; b++) { + sched->backends[b] = backends[b]; + sched->bufts[b] = bufts ? bufts[b] : ggml_backend_get_default_buffer_type(backends[b]); + GGML_ASSERT(ggml_backend_buft_supports_backend(sched->bufts[b], backends[b])); + if (sched->n_copies > 1) { + for (int c = 0; c < sched->n_copies; c++) { + sched->events[b][c] = ggml_backend_event_new(backends[b]); + } + } } sched->galloc = ggml_gallocr_new_n(sched->bufts, n_backends); @@ -1552,12 +1735,18 @@ void ggml_backend_sched_free(ggml_backend_sched_t sched) { if (sched == NULL) { return; } + for (int b = 0; b < sched->n_backends; b++) { + for (int c = 0; c < sched->n_copies; c++) { + ggml_backend_event_free(sched->events[b][c]); + } + } ggml_gallocr_free(sched->galloc); ggml_free(sched->ctx); free(sched->hash_set.keys); free(sched->tensor_backend_id); free(sched->tensor_copies); free(sched->node_backend_ids); + free(sched->leaf_backend_ids); free(sched); } @@ -1569,34 +1758,63 @@ void ggml_backend_sched_reset(ggml_backend_sched_t sched) { memset(sched->tensor_copies, 0, sizeof(sched->tensor_copies[0]) * hash_size); sched->is_reset = true; + sched->is_alloc = false; } bool ggml_backend_sched_reserve(ggml_backend_sched_t sched, struct ggml_cgraph * measure_graph) { ggml_backend_sched_split_graph(sched, measure_graph); - if (!ggml_gallocr_reserve_n(sched->galloc, sched->graph, sched->node_backend_ids)) { + // TODO: extract this to a separate function + if (!ggml_gallocr_reserve_n(sched->galloc, sched->graph, sched->node_backend_ids, sched->leaf_backend_ids)) { return false; } ggml_backend_sched_reset(sched); + ggml_backend_sched_synchronize(sched); + + return true; +} + +bool ggml_backend_sched_alloc_graph(ggml_backend_sched_t sched, struct ggml_cgraph * graph) { + GGML_ASSERT((int)sched->hash_set.size >= graph->n_nodes + GGML_SCHED_MAX_SPLITS*GGML_SCHED_MAX_SPLIT_INPUTS); + + ggml_backend_sched_split_graph(sched, graph); + + if (!ggml_backend_sched_alloc_splits(sched)) { + return false; + } + + sched->is_alloc = true; + return true; } enum ggml_status ggml_backend_sched_graph_compute(ggml_backend_sched_t sched, struct ggml_cgraph * graph) { - GGML_ASSERT((int)sched->hash_set.size >= graph->n_nodes + GGML_MAX_SPLITS*GGML_MAX_SPLIT_INPUTS); + enum ggml_status err = ggml_backend_sched_graph_compute_async(sched, graph); + ggml_backend_sched_synchronize(sched); + return err; +} - if (!sched->is_reset) { +enum ggml_status ggml_backend_sched_graph_compute_async(ggml_backend_sched_t sched, struct ggml_cgraph * graph) { + if (!sched->is_reset && !sched->is_alloc) { ggml_backend_sched_reset(sched); } - ggml_backend_sched_split_graph(sched, graph); - if (!ggml_backend_sched_alloc_splits(sched)) { - return GGML_STATUS_ALLOC_FAILED; + if (!sched->is_alloc) { + if (!ggml_backend_sched_alloc_graph(sched, graph)) { + return GGML_STATUS_ALLOC_FAILED; + } } return ggml_backend_sched_compute_splits(sched); } +void ggml_backend_sched_synchronize(ggml_backend_sched_t sched) { + for (int i = 0; i < sched->n_backends; i++) { + ggml_backend_synchronize(sched->backends[i]); + } +} + void ggml_backend_sched_set_eval_callback(ggml_backend_sched_t sched, ggml_backend_sched_eval_callback callback, void * user_data) { sched->callback_eval = callback; sched->callback_eval_user_data = user_data; @@ -1606,19 +1824,24 @@ int ggml_backend_sched_get_n_splits(ggml_backend_sched_t sched) { return sched->n_splits; } +int ggml_backend_sched_get_n_copies(ggml_backend_sched_t sched) { + return sched->n_copies; +} + size_t ggml_backend_sched_get_buffer_size(ggml_backend_sched_t sched, ggml_backend_t backend) { int backend_index = ggml_backend_sched_backend_id(sched, backend); GGML_ASSERT(backend_index >= 0 && backend_index < sched->n_backends); + return ggml_gallocr_get_buffer_size(sched->galloc, backend_index); } -void ggml_backend_sched_set_node_backend(ggml_backend_sched_t sched, struct ggml_tensor * node, ggml_backend_t backend) { +void ggml_backend_sched_set_tensor_backend(ggml_backend_sched_t sched, struct ggml_tensor * node, ggml_backend_t backend) { int backend_index = ggml_backend_sched_backend_id(sched, backend); GGML_ASSERT(backend_index >= 0 && backend_index < sched->n_backends); tensor_backend_id(node) = backend_index; } -ggml_backend_t ggml_backend_sched_get_node_backend(ggml_backend_sched_t sched, struct ggml_tensor * node) { +ggml_backend_t ggml_backend_sched_get_tensor_backend(ggml_backend_sched_t sched, struct ggml_tensor * node) { int backend_index = tensor_backend_id(node); if (backend_index == -1) { return NULL; diff --git a/src/ggml-common.h b/src/ggml-common.h new file mode 100644 index 000000000..0257c928c --- /dev/null +++ b/src/ggml-common.h @@ -0,0 +1,1830 @@ +#ifndef GGML_COMMON_DECL + +#if defined(GGML_COMMON_DECL_C) +#include + +typedef uint16_t ggml_half; +typedef uint32_t ggml_half2; + +#define GGML_COMMON_AGGR + +#define GGML_COMMON_DECL +#elif defined(GGML_COMMON_DECL_METAL) +#include + +typedef half ggml_half; +typedef half2 ggml_half2; + +#define GGML_COMMON_AGGR + +#define GGML_COMMON_DECL +#elif defined(GGML_COMMON_DECL_CUDA) +#include +#include + +typedef half ggml_half; +typedef half2 ggml_half2; + +#define GGML_COMMON_AGGR data + +#define GGML_COMMON_DECL +#elif defined(GGML_COMMON_DECL_HIP) +#include +#include + +typedef half ggml_half; +typedef half2 ggml_half2; + +#define GGML_COMMON_AGGR data + +#define GGML_COMMON_DECL +#elif defined(GGML_COMMON_DECL_SYCL) +#include +#include + +typedef sycl::half ggml_half; +typedef sycl::half2 ggml_half2; + +#define GGML_COMMON_AGGR data + +#define GGML_COMMON_DECL +#endif + +#if defined(GGML_COMMON_DECL) + +#ifndef __cplusplus +#ifndef static_assert +#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 201100L) +#define static_assert(cond, msg) _Static_assert(cond, msg) +#else +#define static_assert(cond, msg) struct global_scope_noop_trick +#endif +#endif +#endif // __cplusplus + +// QK = number of values after dequantization +// QK_K = super-block size + +#ifdef GGML_QKK_64 +#define QK_K 64 +#define K_SCALE_SIZE 4 +#else +#define QK_K 256 +#define K_SCALE_SIZE 12 +#endif // GGML_QKK_64 + +#if defined(GGML_COMMON_DECL_CUDA) || defined(GGML_COMMON_DECL_HIP) || defined(GGML_COMMON_DECL_SYCL) +// QR = QK / number of values before dequantization +// QI = number of 32 bit integers before dequantization + +#define QI4_0 (QK4_0 / (4 * QR4_0)) +#define QR4_0 2 + +#define QI4_1 (QK4_1 / (4 * QR4_1)) +#define QR4_1 2 + +#define QI5_0 (QK5_0 / (4 * QR5_0)) +#define QR5_0 2 + +#define QI5_1 (QK5_1 / (4 * QR5_1)) +#define QR5_1 2 + +#define QI8_0 (QK8_0 / (4 * QR8_0)) +#define QR8_0 1 + +#define QI8_1 (QK8_1 / (4 * QR8_1)) +#define QR8_1 1 + +#define QI2_K (QK_K / (4*QR2_K)) +#define QR2_K 4 + +#define QI3_K (QK_K / (4*QR3_K)) +#define QR3_K 4 + +#define QI4_K (QK_K / (4*QR4_K)) +#define QR4_K 2 + +#define QI5_K (QK_K / (4*QR5_K)) +#define QR5_K 2 + +#define QI6_K (QK_K / (4*QR6_K)) +#define QR6_K 2 + +#define QI2_XXS (QK_K / (4*QR2_XXS)) +#define QR2_XXS 8 + +#define QI2_XS (QK_K / (4*QR2_XS)) +#define QR2_XS 8 + +#define QI2_S (QK_K / (4*QR2_S)) +#define QR2_S 8 + +#define QI3_XXS (QK_K / (4*QR3_XXS)) +#define QR3_XXS 8 + +#define QI3_XS (QK_K / (4*QR3_XS)) +#define QR3_XS 8 + +#define QI1_S (QK_K / (4*QR1_S)) +#define QR1_S 8 + +#define QI4_NL (QK4_NL / (4*QR4_NL)) +#define QR4_NL 2 + +#if QK_K == 64 +#define QI4_XS QI4_NL +#define QR4_XS QR4_NL +#else +#define QI4_XS (QK_K / (4*QR4_XS)) +#define QR4_XS 8 +#endif + +#endif // GGML_COMMON_DECL_CUDA || GGML_COMMON_DECL_HIP + +#define QK4_0 32 +typedef struct { + ggml_half d; // delta + uint8_t qs[QK4_0 / 2]; // nibbles / quants +} block_q4_0; +static_assert(sizeof(block_q4_0) == sizeof(ggml_half) + QK4_0 / 2, "wrong q4_0 block size/padding"); + +#define QK4_1 32 +typedef struct { + union { + struct { + ggml_half d; // delta + ggml_half m; // min + } GGML_COMMON_AGGR; + ggml_half2 dm; + }; + uint8_t qs[QK4_1 / 2]; // nibbles / quants +} block_q4_1; +static_assert(sizeof(block_q4_1) == 2 * sizeof(ggml_half) + QK4_1 / 2, "wrong q4_1 block size/padding"); + +#define QK5_0 32 +typedef struct { + ggml_half d; // delta + uint8_t qh[4]; // 5-th bit of quants + uint8_t qs[QK5_0 / 2]; // nibbles / quants +} block_q5_0; +static_assert(sizeof(block_q5_0) == sizeof(ggml_half) + sizeof(uint32_t) + QK5_0 / 2, "wrong q5_0 block size/padding"); + +#define QK5_1 32 +typedef struct { + union { + struct { + ggml_half d; // delta + ggml_half m; // min + } GGML_COMMON_AGGR; + ggml_half2 dm; + }; + uint8_t qh[4]; // 5-th bit of quants + uint8_t qs[QK5_1 / 2]; // nibbles / quants +} block_q5_1; +static_assert(sizeof(block_q5_1) == 2 * sizeof(ggml_half) + sizeof(uint32_t) + QK5_1 / 2, "wrong q5_1 block size/padding"); + +#define QK8_0 32 +typedef struct { + ggml_half d; // delta + int8_t qs[QK8_0]; // quants +} block_q8_0; +static_assert(sizeof(block_q8_0) == sizeof(ggml_half) + QK8_0, "wrong q8_0 block size/padding"); + +#define QK8_1 32 +typedef struct { + union { + struct { + ggml_half d; // delta + ggml_half s; // d * sum(qs[i]) + } GGML_COMMON_AGGR; + ggml_half2 ds; + }; + int8_t qs[QK8_1]; // quants +} block_q8_1; +static_assert(sizeof(block_q8_1) == 2*sizeof(ggml_half) + QK8_1, "wrong q8_1 block size/padding"); + +// +// Super-block quantization structures +// + +// 2-bit quantization +// weight is represented as x = a * q + b +// 16 blocks of 16 elements each +// Effectively 2.625 bits per weight +typedef struct { + uint8_t scales[QK_K/16]; // scales and mins, quantized with 4 bits + uint8_t qs[QK_K/4]; // quants + union { + struct { + ggml_half d; // super-block scale for quantized scales + ggml_half dmin; // super-block scale for quantized mins + } GGML_COMMON_AGGR; + ggml_half2 dm; + }; +} block_q2_K; +static_assert(sizeof(block_q2_K) == 2*sizeof(ggml_half) + QK_K/16 + QK_K/4, "wrong q2_K block size/padding"); + +// 3-bit quantization +// weight is represented as x = a * q +// 16 blocks of 16 elements each +// Effectively 3.4375 bits per weight +#ifdef GGML_QKK_64 +typedef struct { + uint8_t hmask[QK_K/8]; // quants - high bit + uint8_t qs[QK_K/4]; // quants - low 2 bits + uint8_t scales[2]; + ggml_half d; // super-block scale +} block_q3_K; +static_assert(sizeof(block_q3_K) == sizeof(ggml_half) + QK_K / 4 + QK_K / 8 + 2, "wrong q3_K block size/padding"); +#else +typedef struct { + uint8_t hmask[QK_K/8]; // quants - high bit + uint8_t qs[QK_K/4]; // quants - low 2 bits + uint8_t scales[12]; // scales, quantized with 6 bits + ggml_half d; // super-block scale +} block_q3_K; +static_assert(sizeof(block_q3_K) == sizeof(ggml_half) + QK_K / 4 + QK_K / 8 + 12, "wrong q3_K block size/padding"); +#endif + +// 4-bit quantization +// 8 blocks of 32 elements each +// weight is represented as x = a * q + b +// Effectively 4.5 bits per weight +#ifdef GGML_QKK_64 +typedef struct { + ggml_half d[2]; // super-block scales/mins + uint8_t scales[2]; // 4-bit block scales/mins + uint8_t qs[QK_K/2]; // 4--bit quants +} block_q4_K; +static_assert(sizeof(block_q4_K) == 2*sizeof(ggml_half) + QK_K/2 + 2, "wrong q4_K block size/padding"); +#else +typedef struct { + union { + struct { + ggml_half d; // super-block scale for quantized scales + ggml_half dmin; // super-block scale for quantized mins + } GGML_COMMON_AGGR; + ggml_half2 dm; + }; + uint8_t scales[K_SCALE_SIZE]; // scales and mins, quantized with 6 bits + uint8_t qs[QK_K/2]; // 4--bit quants +} block_q4_K; +static_assert(sizeof(block_q4_K) == 2*sizeof(ggml_half) + K_SCALE_SIZE + QK_K/2, "wrong q4_K block size/padding"); +#endif + +// 5-bit quantization +// 8 blocks of 32 elements each +// weight is represented as x = a * q + b +// Effectively 5.5 bits per weight +#ifdef GGML_QKK_64 +typedef struct { + ggml_half d; // super-block scale + int8_t scales[QK_K/16]; // 8-bit block scales + uint8_t qh[QK_K/8]; // quants, high bit + uint8_t qs[QK_K/2]; // quants, low 4 bits +} block_q5_K; +static_assert(sizeof(block_q5_K) == sizeof(ggml_half) + QK_K/2 + QK_K/8 + QK_K/16, "wrong q5_K block size/padding"); +#else +typedef struct { + union { + struct { + ggml_half d; // super-block scale for quantized scales + ggml_half dmin; // super-block scale for quantized mins + } GGML_COMMON_AGGR; + ggml_half2 dm; + }; + uint8_t scales[K_SCALE_SIZE]; // scales and mins, quantized with 6 bits + uint8_t qh[QK_K/8]; // quants, high bit + uint8_t qs[QK_K/2]; // quants, low 4 bits +} block_q5_K; +static_assert(sizeof(block_q5_K) == 2*sizeof(ggml_half) + K_SCALE_SIZE + QK_K/2 + QK_K/8, "wrong q5_K block size/padding"); +#endif + +// 6-bit quantization +// weight is represented as x = a * q +// 16 blocks of 16 elements each +// Effectively 6.5625 bits per weight +typedef struct { + uint8_t ql[QK_K/2]; // quants, lower 4 bits + uint8_t qh[QK_K/4]; // quants, upper 2 bits + int8_t scales[QK_K/16]; // scales, quantized with 8 bits + ggml_half d; // super-block scale +} block_q6_K; +static_assert(sizeof(block_q6_K) == sizeof(ggml_half) + QK_K / 16 + 3*QK_K/4, "wrong q6_K block size/padding"); + +// This is only used for intermediate quantization and dot products +typedef struct { + float d; // delta + int8_t qs[QK_K]; // quants + int16_t bsums[QK_K/16]; // sum of quants in groups of 16 +} block_q8_K; +static_assert(sizeof(block_q8_K) == sizeof(float) + QK_K + QK_K/16*sizeof(int16_t), "wrong q8_K block size/padding"); + +// (Almost) "true" 2-bit quantization. +// Due to the need to use blocks as per ggml design, it ends up using +// 2.0625 bpw because of the 16-bit scale for each block of 256. +typedef struct { + ggml_half d; + uint16_t qs[QK_K/8]; +} block_iq2_xxs; +static_assert(sizeof(block_iq2_xxs) == sizeof(ggml_half) + QK_K/8*sizeof(uint16_t), "wrong iq2_xxs block size/padding"); + +// 2.3125 bpw quants +typedef struct { + ggml_half d; + uint16_t qs[QK_K/8]; + uint8_t scales[QK_K/32]; +} block_iq2_xs; +static_assert(sizeof(block_iq2_xs) == sizeof(ggml_half) + QK_K/8*sizeof(uint16_t) + QK_K/32, "wrong iq2_xs block size/padding"); + +// 2.5625 bpw quants +typedef struct { + ggml_half d; + uint8_t qs[QK_K/4]; + uint8_t qh[QK_K/32]; + uint8_t scales[QK_K/32]; +} block_iq2_s; +static_assert(sizeof(block_iq2_s) == sizeof(ggml_half) + QK_K/4 + QK_K/16, "wrong iq2_s block size/padding"); + +// (Almost) "true" 3-bit quantization. +// Due to the need to use blocks as per ggml design, it ends up using +// 3.0625 bpw because of the 16-bit scale for each block of 256. +typedef struct { + ggml_half d; + uint8_t qs[3*QK_K/8]; +} block_iq3_xxs; +static_assert(sizeof(block_iq3_xxs) == sizeof(ggml_half) + 3*(QK_K/8), "wrong iq3_xxs block size/padding"); + +// 3.4375 bpw +#if QK_K == 64 +#define IQ3S_N_SCALE 2 +#else +#define IQ3S_N_SCALE QK_K/64 +#endif +typedef struct { + ggml_half d; + uint8_t qs[QK_K/4]; + uint8_t qh[QK_K/32]; + uint8_t signs[QK_K/8]; + uint8_t scales[IQ3S_N_SCALE]; +} block_iq3_s; +static_assert(sizeof(block_iq3_s) == sizeof(ggml_half) + 13*(QK_K/32) + IQ3S_N_SCALE, "wrong iq3_s block size/padding"); + +typedef struct { + ggml_half d; + uint8_t qs[QK_K/8]; + uint16_t qh[QK_K/32]; +} block_iq1_s; +static_assert(sizeof(block_iq1_s) == sizeof(ggml_half) + QK_K/8 + QK_K/16, "wrong iq1_s block size/padding"); + +// Non-linear quants +#define QK4_NL 32 +typedef struct { + ggml_half d; + uint8_t qs[QK4_NL/2]; +} block_iq4_nl; +static_assert(sizeof(block_iq4_nl) == sizeof(ggml_half) + QK4_NL/2, "wrong iq4_nl block size/padding"); + +#if QK_K == 64 +#define block_iq4_xs block_iq4_nl +#else +typedef struct { + ggml_half d; + uint16_t scales_h; + uint8_t scales_l[QK_K/64]; + uint8_t qs[QK_K/2]; +} block_iq4_xs; +static_assert(sizeof(block_iq4_xs) == sizeof(ggml_half) + sizeof(uint16_t) + QK_K/64 + QK_K/2, "wrong iq4_xs block size/padding"); +#endif + +#endif // GGML_COMMON_DECL +#endif // GGML_COMMON_DECL + +//////////////////////////////////////////////////////////////////////////////// + +#ifndef GGML_COMMON_IMPL + +#if defined(GGML_COMMON_IMPL_C) +#include + +#define GGML_TABLE_BEGIN(type, name, size) static const type name[size] = { +#define GGML_TABLE_END() }; + +#define GGML_COMMON_IMPL +#elif defined(GGML_COMMON_IMPL_METAL) +#include + +#define GGML_TABLE_BEGIN(type, name, size) static const constant type name[size] = { +#define GGML_TABLE_END() }; + +#define GGML_COMMON_IMPL +#elif defined(GGML_COMMON_IMPL_CUDA) || defined(GGML_COMMON_IMPL_HIP) +#include + +#define GGML_TABLE_BEGIN(type, name, size) static const __device__ type name[size] = { +#define GGML_TABLE_END() }; + +#define GGML_COMMON_IMPL +#elif defined(GGML_COMMON_IMPL_SYCL) +#include + +#define GGML_TABLE_BEGIN(type, name, size) static dpct::global_memory name(sycl::range<1>(size), { +#define GGML_TABLE_END() }); + +#define GGML_COMMON_IMPL +#endif + +#if defined(GGML_COMMON_IMPL) + +GGML_TABLE_BEGIN(uint8_t, kmask_iq2xs, 8) + 1, 2, 4, 8, 16, 32, 64, 128 +GGML_TABLE_END() + +GGML_TABLE_BEGIN(uint8_t, ksigns_iq2xs, 128) + 0, 129, 130, 3, 132, 5, 6, 135, 136, 9, 10, 139, 12, 141, 142, 15, + 144, 17, 18, 147, 20, 149, 150, 23, 24, 153, 154, 27, 156, 29, 30, 159, + 160, 33, 34, 163, 36, 165, 166, 39, 40, 169, 170, 43, 172, 45, 46, 175, + 48, 177, 178, 51, 180, 53, 54, 183, 184, 57, 58, 187, 60, 189, 190, 63, + 192, 65, 66, 195, 68, 197, 198, 71, 72, 201, 202, 75, 204, 77, 78, 207, + 80, 209, 210, 83, 212, 85, 86, 215, 216, 89, 90, 219, 92, 221, 222, 95, + 96, 225, 226, 99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111, + 240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255, +GGML_TABLE_END() + +//#if __CUDA_ARCH__ >= MIN_CC_DP4A // lowest compute capability for integer intrinsics +GGML_TABLE_BEGIN(uint64_t, ksigns64, 128) + 0x0000000000000000, 0xff000000000000ff, 0xff0000000000ff00, 0x000000000000ffff, + 0xff00000000ff0000, 0x0000000000ff00ff, 0x0000000000ffff00, 0xff00000000ffffff, + 0xff000000ff000000, 0x00000000ff0000ff, 0x00000000ff00ff00, 0xff000000ff00ffff, + 0x00000000ffff0000, 0xff000000ffff00ff, 0xff000000ffffff00, 0x00000000ffffffff, + 0xff0000ff00000000, 0x000000ff000000ff, 0x000000ff0000ff00, 0xff0000ff0000ffff, + 0x000000ff00ff0000, 0xff0000ff00ff00ff, 0xff0000ff00ffff00, 0x000000ff00ffffff, + 0x000000ffff000000, 0xff0000ffff0000ff, 0xff0000ffff00ff00, 0x000000ffff00ffff, + 0xff0000ffffff0000, 0x000000ffffff00ff, 0x000000ffffffff00, 0xff0000ffffffffff, + 0xff00ff0000000000, 0x0000ff00000000ff, 0x0000ff000000ff00, 0xff00ff000000ffff, + 0x0000ff0000ff0000, 0xff00ff0000ff00ff, 0xff00ff0000ffff00, 0x0000ff0000ffffff, + 0x0000ff00ff000000, 0xff00ff00ff0000ff, 0xff00ff00ff00ff00, 0x0000ff00ff00ffff, + 0xff00ff00ffff0000, 0x0000ff00ffff00ff, 0x0000ff00ffffff00, 0xff00ff00ffffffff, + 0x0000ffff00000000, 0xff00ffff000000ff, 0xff00ffff0000ff00, 0x0000ffff0000ffff, + 0xff00ffff00ff0000, 0x0000ffff00ff00ff, 0x0000ffff00ffff00, 0xff00ffff00ffffff, + 0xff00ffffff000000, 0x0000ffffff0000ff, 0x0000ffffff00ff00, 0xff00ffffff00ffff, + 0x0000ffffffff0000, 0xff00ffffffff00ff, 0xff00ffffffffff00, 0x0000ffffffffffff, + 0xffff000000000000, 0x00ff0000000000ff, 0x00ff00000000ff00, 0xffff00000000ffff, + 0x00ff000000ff0000, 0xffff000000ff00ff, 0xffff000000ffff00, 0x00ff000000ffffff, + 0x00ff0000ff000000, 0xffff0000ff0000ff, 0xffff0000ff00ff00, 0x00ff0000ff00ffff, + 0xffff0000ffff0000, 0x00ff0000ffff00ff, 0x00ff0000ffffff00, 0xffff0000ffffffff, + 0x00ff00ff00000000, 0xffff00ff000000ff, 0xffff00ff0000ff00, 0x00ff00ff0000ffff, + 0xffff00ff00ff0000, 0x00ff00ff00ff00ff, 0x00ff00ff00ffff00, 0xffff00ff00ffffff, + 0xffff00ffff000000, 0x00ff00ffff0000ff, 0x00ff00ffff00ff00, 0xffff00ffff00ffff, + 0x00ff00ffffff0000, 0xffff00ffffff00ff, 0xffff00ffffffff00, 0x00ff00ffffffffff, + 0x00ffff0000000000, 0xffffff00000000ff, 0xffffff000000ff00, 0x00ffff000000ffff, + 0xffffff0000ff0000, 0x00ffff0000ff00ff, 0x00ffff0000ffff00, 0xffffff0000ffffff, + 0xffffff00ff000000, 0x00ffff00ff0000ff, 0x00ffff00ff00ff00, 0xffffff00ff00ffff, + 0x00ffff00ffff0000, 0xffffff00ffff00ff, 0xffffff00ffffff00, 0x00ffff00ffffffff, + 0xffffffff00000000, 0x00ffffff000000ff, 0x00ffffff0000ff00, 0xffffffff0000ffff, + 0x00ffffff00ff0000, 0xffffffff00ff00ff, 0xffffffff00ffff00, 0x00ffffff00ffffff, + 0x00ffffffff000000, 0xffffffffff0000ff, 0xffffffffff00ff00, 0x00ffffffff00ffff, + 0xffffffffffff0000, 0x00ffffffffff00ff, 0x00ffffffffffff00, 0xffffffffffffffff, +GGML_TABLE_END() +//#endif + + +GGML_TABLE_BEGIN(uint64_t, iq2xxs_grid, 256) + 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, + 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808, + 0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819, + 0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819, + 0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b, + 0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808, + 0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08, + 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b, + 0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819, + 0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08, + 0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808, + 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08, + 0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808, + 0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808, + 0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919, + 0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819, + 0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08, + 0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908, + 0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819, + 0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808, + 0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808, + 0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908, + 0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808, + 0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08, + 0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819, + 0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819, + 0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819, + 0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908, + 0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19, + 0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819, + 0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b, + 0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808, + 0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908, + 0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08, + 0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08, + 0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908, + 0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819, + 0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808, + 0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808, + 0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19, + 0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819, + 0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, + 0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b, + 0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08, + 0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808, + 0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908, + 0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b, + 0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819, + 0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08, + 0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08, + 0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808, + 0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b, + 0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b, + 0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908, + 0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819, + 0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808, + 0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908, + 0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b, + 0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808, + 0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b, + 0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b, + 0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808, + 0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19, + 0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908, +GGML_TABLE_END() + +GGML_TABLE_BEGIN(uint64_t, iq2xs_grid, 512) + 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, + 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b, + 0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919, + 0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b, + 0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919, + 0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808, + 0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819, + 0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819, + 0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, + 0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b, + 0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b, + 0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908, + 0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908, + 0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919, + 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808, + 0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919, + 0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908, + 0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, + 0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, + 0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08, + 0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808, + 0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808, + 0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819, + 0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908, + 0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819, + 0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808, + 0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b, + 0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819, + 0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819, + 0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808, + 0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908, + 0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19, + 0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b, + 0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b, + 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919, + 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808, + 0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819, + 0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819, + 0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b, + 0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908, + 0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808, + 0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819, + 0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808, + 0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919, + 0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808, + 0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808, + 0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908, + 0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908, + 0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808, + 0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b, + 0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819, + 0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, + 0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908, + 0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808, + 0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908, + 0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919, + 0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08, + 0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19, + 0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b, + 0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b, + 0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808, + 0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08, + 0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b, + 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908, + 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b, + 0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908, + 0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, + 0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808, + 0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808, + 0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08, + 0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819, + 0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919, + 0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808, + 0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808, + 0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819, + 0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819, + 0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908, + 0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908, + 0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b, + 0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908, + 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908, + 0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908, + 0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808, + 0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, + 0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819, + 0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819, + 0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808, + 0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b, + 0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819, + 0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819, + 0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08, + 0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808, + 0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19, + 0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919, + 0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808, + 0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19, + 0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b, + 0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808, + 0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b, + 0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b, + 0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, + 0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b, + 0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808, + 0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819, + 0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808, + 0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808, + 0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08, + 0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b, + 0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19, + 0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08, + 0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919, + 0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08, + 0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08, + 0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908, + 0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908, + 0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b, + 0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908, + 0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808, + 0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b, + 0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808, + 0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808, + 0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19, + 0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08, + 0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808, + 0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b, + 0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808, + 0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b, + 0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b, +GGML_TABLE_END() + +GGML_TABLE_BEGIN(uint64_t, iq2s_grid, 1024) + 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, + 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b, + 0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919, + 0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b, + 0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919, + 0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x08080808192b192b, + 0x08080808192b2b19, 0x080808082b080808, 0x080808082b08082b, 0x080808082b081919, + 0x080808082b082b08, 0x080808082b190819, 0x080808082b191908, 0x080808082b2b0808, + 0x080808082b2b1919, 0x080808082b2b2b2b, 0x0808081908080819, 0x0808081908081908, + 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, 0x080808190819082b, + 0x0808081908191919, 0x0808081908192b08, 0x08080819082b0819, 0x08080819082b1908, + 0x0808081919080808, 0x080808191908082b, 0x0808081919081919, 0x0808081919082b08, + 0x0808081919190819, 0x0808081919191908, 0x080808191919192b, 0x0808081919192b19, + 0x08080819192b0808, 0x08080819192b1919, 0x08080819192b2b08, 0x080808192b080819, + 0x080808192b081908, 0x080808192b190808, 0x080808192b19082b, 0x080808192b191919, + 0x080808192b2b0819, 0x080808192b2b1908, 0x0808082b08080808, 0x0808082b0808082b, + 0x0808082b08081919, 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, + 0x0808082b082b0808, 0x0808082b082b2b2b, 0x0808082b19080819, 0x0808082b19081908, + 0x0808082b1908192b, 0x0808082b19082b19, 0x0808082b19190808, 0x0808082b19191919, + 0x0808082b2b080808, 0x0808082b2b081919, 0x0808082b2b082b2b, 0x0808082b2b191908, + 0x0808082b2b2b082b, 0x0808190808080819, 0x0808190808081908, 0x080819080808192b, + 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, 0x0808190808191919, + 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, 0x08081908082b192b, + 0x08081908082b2b19, 0x0808190819080808, 0x080819081908082b, 0x0808190819081919, + 0x0808190819082b08, 0x0808190819082b2b, 0x0808190819190819, 0x0808190819191908, + 0x080819081919192b, 0x0808190819192b19, 0x08081908192b0808, 0x08081908192b082b, + 0x08081908192b1919, 0x080819082b080819, 0x080819082b081908, 0x080819082b08192b, + 0x080819082b082b19, 0x080819082b190808, 0x080819082b191919, 0x080819082b192b08, + 0x080819082b2b0819, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, + 0x0808191908081919, 0x0808191908082b08, 0x0808191908082b2b, 0x0808191908190819, + 0x0808191908191908, 0x080819190819192b, 0x0808191908192b19, 0x08081919082b0808, + 0x08081919082b1919, 0x08081919082b2b08, 0x0808191919080819, 0x0808191919081908, + 0x080819191908192b, 0x0808191919082b19, 0x0808191919190808, 0x080819191919082b, + 0x0808191919191919, 0x0808191919192b08, 0x08081919192b0819, 0x08081919192b1908, + 0x080819192b080808, 0x080819192b08082b, 0x080819192b081919, 0x080819192b082b08, + 0x080819192b190819, 0x080819192b191908, 0x080819192b2b0808, 0x0808192b08080819, + 0x0808192b08081908, 0x0808192b0808192b, 0x0808192b08082b19, 0x0808192b08190808, + 0x0808192b08191919, 0x0808192b19080808, 0x0808192b19081919, 0x0808192b19082b08, + 0x0808192b19190819, 0x0808192b19191908, 0x0808192b192b0808, 0x0808192b2b080819, + 0x0808192b2b081908, 0x0808192b2b190808, 0x08082b0808080808, 0x08082b080808082b, + 0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808190819, 0x08082b0808191908, + 0x08082b080819192b, 0x08082b0808192b19, 0x08082b08082b0808, 0x08082b08082b1919, + 0x08082b08082b2b2b, 0x08082b0819080819, 0x08082b0819081908, 0x08082b081908192b, + 0x08082b0819082b19, 0x08082b0819190808, 0x08082b081919082b, 0x08082b0819191919, + 0x08082b0819192b08, 0x08082b08192b0819, 0x08082b08192b1908, 0x08082b082b080808, + 0x08082b082b081919, 0x08082b082b191908, 0x08082b082b2b2b2b, 0x08082b1908080819, + 0x08082b1908081908, 0x08082b1908190808, 0x08082b190819082b, 0x08082b1908191919, + 0x08082b1908192b08, 0x08082b19082b0819, 0x08082b1919080808, 0x08082b1919081919, + 0x08082b1919082b08, 0x08082b1919190819, 0x08082b1919191908, 0x08082b19192b0808, + 0x08082b192b080819, 0x08082b192b190808, 0x08082b2b08080808, 0x08082b2b08190819, + 0x08082b2b08191908, 0x08082b2b082b082b, 0x08082b2b082b2b08, 0x08082b2b082b2b2b, + 0x08082b2b19190808, 0x08082b2b2b192b19, 0x0819080808080819, 0x0819080808081908, + 0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, + 0x0819080808191919, 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, + 0x08190808082b192b, 0x0819080819080808, 0x081908081908082b, 0x0819080819081919, + 0x0819080819082b08, 0x0819080819190819, 0x0819080819191908, 0x081908081919192b, + 0x0819080819192b19, 0x08190808192b0808, 0x08190808192b082b, 0x08190808192b1919, + 0x08190808192b2b08, 0x081908082b080819, 0x081908082b081908, 0x081908082b08192b, + 0x081908082b190808, 0x081908082b191919, 0x081908082b192b08, 0x081908082b2b0819, + 0x081908082b2b1908, 0x0819081908080808, 0x081908190808082b, 0x0819081908081919, + 0x0819081908082b08, 0x0819081908082b2b, 0x0819081908190819, 0x0819081908191908, + 0x081908190819192b, 0x0819081908192b19, 0x08190819082b0808, 0x08190819082b082b, + 0x08190819082b1919, 0x08190819082b2b08, 0x0819081919080819, 0x0819081919081908, + 0x081908191908192b, 0x0819081919082b19, 0x0819081919190808, 0x081908191919082b, + 0x0819081919191919, 0x0819081919192b08, 0x08190819192b0819, 0x08190819192b1908, + 0x081908192b080808, 0x081908192b08082b, 0x081908192b081919, 0x081908192b082b08, + 0x081908192b190819, 0x081908192b191908, 0x0819082b08080819, 0x0819082b08081908, + 0x0819082b08082b19, 0x0819082b08190808, 0x0819082b08191919, 0x0819082b082b0819, + 0x0819082b082b1908, 0x0819082b19080808, 0x0819082b19081919, 0x0819082b19190819, + 0x0819082b19191908, 0x0819082b2b080819, 0x0819082b2b081908, 0x0819082b2b190808, + 0x0819190808080808, 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08, + 0x0819190808190819, 0x0819190808191908, 0x081919080819192b, 0x0819190808192b19, + 0x08191908082b0808, 0x08191908082b1919, 0x08191908082b2b08, 0x0819190819080819, + 0x0819190819081908, 0x081919081908192b, 0x0819190819082b19, 0x0819190819190808, + 0x081919081919082b, 0x0819190819191919, 0x0819190819192b08, 0x08191908192b0819, + 0x08191908192b1908, 0x081919082b080808, 0x081919082b08082b, 0x081919082b081919, + 0x081919082b082b08, 0x081919082b190819, 0x081919082b191908, 0x081919082b2b0808, + 0x0819191908080819, 0x0819191908081908, 0x081919190808192b, 0x0819191908082b19, + 0x0819191908190808, 0x081919190819082b, 0x0819191908191919, 0x0819191908192b08, + 0x08191919082b0819, 0x08191919082b1908, 0x0819191919080808, 0x081919191908082b, + 0x0819191919081919, 0x0819191919082b08, 0x0819191919190819, 0x0819191919191908, + 0x08191919192b0808, 0x081919192b080819, 0x081919192b081908, 0x081919192b190808, + 0x0819192b08080808, 0x0819192b08081919, 0x0819192b08082b08, 0x0819192b08190819, + 0x0819192b08191908, 0x0819192b082b0808, 0x0819192b19080819, 0x0819192b19081908, + 0x0819192b19190808, 0x0819192b2b080808, 0x0819192b2b2b2b2b, 0x08192b0808080819, + 0x08192b0808081908, 0x08192b080808192b, 0x08192b0808082b19, 0x08192b0808190808, + 0x08192b0808191919, 0x08192b0808192b08, 0x08192b08082b0819, 0x08192b0819080808, + 0x08192b081908082b, 0x08192b0819081919, 0x08192b0819082b08, 0x08192b0819190819, + 0x08192b0819191908, 0x08192b08192b0808, 0x08192b082b080819, 0x08192b082b081908, + 0x08192b1908080808, 0x08192b190808082b, 0x08192b1908081919, 0x08192b1908082b08, + 0x08192b1908190819, 0x08192b1908191908, 0x08192b19082b0808, 0x08192b1919080819, + 0x08192b1919081908, 0x08192b1919190808, 0x08192b19192b2b19, 0x08192b192b2b082b, + 0x08192b2b08081908, 0x08192b2b08190808, 0x08192b2b19080808, 0x08192b2b1919192b, + 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, 0x082b080808082b08, + 0x082b080808190819, 0x082b080808191908, 0x082b08080819192b, 0x082b080808192b19, + 0x082b0808082b0808, 0x082b0808082b1919, 0x082b0808082b2b2b, 0x082b080819080819, + 0x082b080819081908, 0x082b080819190808, 0x082b08081919082b, 0x082b080819191919, + 0x082b0808192b1908, 0x082b08082b080808, 0x082b08082b082b2b, 0x082b08082b191908, + 0x082b08082b2b2b2b, 0x082b081908080819, 0x082b081908081908, 0x082b081908190808, + 0x082b08190819082b, 0x082b081908191919, 0x082b0819082b0819, 0x082b081919080808, + 0x082b08191908082b, 0x082b081919081919, 0x082b081919190819, 0x082b081919191908, + 0x082b0819192b0808, 0x082b08192b080819, 0x082b08192b081908, 0x082b08192b190808, + 0x082b082b08080808, 0x082b082b08082b2b, 0x082b082b082b082b, 0x082b082b082b2b08, + 0x082b082b082b2b2b, 0x082b082b19081908, 0x082b082b19190808, 0x082b082b2b082b08, + 0x082b082b2b082b2b, 0x082b082b2b2b2b08, 0x082b190808080819, 0x082b190808081908, + 0x082b19080808192b, 0x082b190808082b19, 0x082b190808190808, 0x082b190808191919, + 0x082b190808192b08, 0x082b1908082b0819, 0x082b1908082b1908, 0x082b190819080808, + 0x082b19081908082b, 0x082b190819081919, 0x082b190819082b08, 0x082b190819190819, + 0x082b190819191908, 0x082b1908192b0808, 0x082b19082b080819, 0x082b19082b081908, + 0x082b19082b190808, 0x082b191908080808, 0x082b191908081919, 0x082b191908082b08, + 0x082b191908190819, 0x082b191908191908, 0x082b1919082b0808, 0x082b191919080819, + 0x082b191919081908, 0x082b191919190808, 0x082b1919192b192b, 0x082b19192b080808, + 0x082b192b08080819, 0x082b192b08081908, 0x082b192b08190808, 0x082b192b19080808, + 0x082b192b19192b19, 0x082b2b0808080808, 0x082b2b0808081919, 0x082b2b0808190819, + 0x082b2b0808191908, 0x082b2b0819080819, 0x082b2b0819081908, 0x082b2b0819190808, + 0x082b2b082b082b2b, 0x082b2b082b2b2b2b, 0x082b2b1908080819, 0x082b2b1908081908, + 0x082b2b1908190808, 0x082b2b192b191919, 0x082b2b2b08082b2b, 0x082b2b2b082b082b, + 0x082b2b2b192b1908, 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, + 0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, + 0x190808080819082b, 0x1908080808191919, 0x1908080808192b08, 0x1908080808192b2b, + 0x19080808082b0819, 0x19080808082b1908, 0x19080808082b192b, 0x1908080819080808, + 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, 0x1908080819082b2b, + 0x1908080819190819, 0x1908080819191908, 0x190808081919192b, 0x1908080819192b19, + 0x19080808192b0808, 0x19080808192b082b, 0x19080808192b1919, 0x190808082b080819, + 0x190808082b081908, 0x190808082b190808, 0x190808082b191919, 0x190808082b192b08, + 0x190808082b2b0819, 0x190808082b2b1908, 0x1908081908080808, 0x190808190808082b, + 0x1908081908081919, 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908, + 0x190808190819192b, 0x1908081908192b19, 0x19080819082b0808, 0x19080819082b082b, + 0x19080819082b1919, 0x1908081919080819, 0x1908081919081908, 0x190808191908192b, + 0x1908081919082b19, 0x1908081919190808, 0x190808191919082b, 0x1908081919191919, + 0x1908081919192b08, 0x19080819192b0819, 0x19080819192b1908, 0x190808192b080808, + 0x190808192b08082b, 0x190808192b081919, 0x190808192b082b08, 0x190808192b190819, + 0x190808192b191908, 0x190808192b2b0808, 0x1908082b08080819, 0x1908082b08081908, + 0x1908082b08190808, 0x1908082b0819082b, 0x1908082b08191919, 0x1908082b08192b08, + 0x1908082b082b1908, 0x1908082b19080808, 0x1908082b19081919, 0x1908082b19082b08, + 0x1908082b19190819, 0x1908082b19191908, 0x1908082b192b0808, 0x1908082b2b080819, + 0x1908082b2b081908, 0x1908190808080808, 0x190819080808082b, 0x1908190808081919, + 0x1908190808082b08, 0x1908190808082b2b, 0x1908190808190819, 0x1908190808191908, + 0x190819080819192b, 0x1908190808192b19, 0x19081908082b0808, 0x19081908082b082b, + 0x19081908082b1919, 0x19081908082b2b08, 0x1908190819080819, 0x1908190819081908, + 0x190819081908192b, 0x1908190819082b19, 0x1908190819190808, 0x190819081919082b, + 0x1908190819191919, 0x1908190819192b08, 0x19081908192b0819, 0x19081908192b1908, + 0x190819082b080808, 0x190819082b08082b, 0x190819082b081919, 0x190819082b082b08, + 0x190819082b190819, 0x190819082b191908, 0x190819082b2b0808, 0x1908191908080819, + 0x1908191908081908, 0x190819190808192b, 0x1908191908082b19, 0x1908191908190808, + 0x190819190819082b, 0x1908191908191919, 0x1908191908192b08, 0x19081919082b0819, + 0x19081919082b1908, 0x1908191919080808, 0x190819191908082b, 0x1908191919081919, + 0x1908191919082b08, 0x1908191919190819, 0x1908191919191908, 0x19081919192b0808, + 0x19081919192b2b2b, 0x190819192b080819, 0x190819192b081908, 0x190819192b190808, + 0x1908192b08080808, 0x1908192b0808082b, 0x1908192b08081919, 0x1908192b08082b08, + 0x1908192b08190819, 0x1908192b08191908, 0x1908192b082b0808, 0x1908192b19080819, + 0x1908192b19081908, 0x1908192b19190808, 0x1908192b2b080808, 0x1908192b2b2b1919, + 0x19082b0808080819, 0x19082b0808081908, 0x19082b0808082b19, 0x19082b0808190808, + 0x19082b080819082b, 0x19082b0808191919, 0x19082b0808192b08, 0x19082b08082b0819, + 0x19082b08082b1908, 0x19082b0819080808, 0x19082b081908082b, 0x19082b0819081919, + 0x19082b0819082b08, 0x19082b0819190819, 0x19082b0819191908, 0x19082b08192b0808, + 0x19082b082b081908, 0x19082b082b190808, 0x19082b1908080808, 0x19082b190808082b, + 0x19082b1908081919, 0x19082b1908082b08, 0x19082b1908190819, 0x19082b1908191908, + 0x19082b19082b0808, 0x19082b1919080819, 0x19082b1919081908, 0x19082b1919190808, + 0x19082b192b080808, 0x19082b192b19192b, 0x19082b2b08080819, 0x19082b2b08081908, + 0x19082b2b08190808, 0x19082b2b19080808, 0x1919080808080808, 0x191908080808082b, + 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, 0x1919080808191908, + 0x191908080819192b, 0x1919080808192b19, 0x19190808082b0808, 0x19190808082b082b, + 0x19190808082b1919, 0x19190808082b2b08, 0x1919080819080819, 0x1919080819081908, + 0x191908081908192b, 0x1919080819082b19, 0x1919080819190808, 0x191908081919082b, + 0x1919080819191919, 0x1919080819192b08, 0x19190808192b0819, 0x19190808192b1908, + 0x191908082b080808, 0x191908082b08082b, 0x191908082b081919, 0x191908082b082b08, + 0x191908082b190819, 0x191908082b191908, 0x1919081908080819, 0x1919081908081908, + 0x191908190808192b, 0x1919081908082b19, 0x1919081908190808, 0x191908190819082b, + 0x1919081908191919, 0x1919081908192b08, 0x19190819082b0819, 0x19190819082b1908, + 0x1919081919080808, 0x191908191908082b, 0x1919081919081919, 0x1919081919082b08, + 0x1919081919190819, 0x1919081919191908, 0x19190819192b0808, 0x191908192b080819, + 0x191908192b081908, 0x191908192b190808, 0x1919082b08080808, 0x1919082b08081919, + 0x1919082b08082b08, 0x1919082b08190819, 0x1919082b08191908, 0x1919082b082b0808, + 0x1919082b19080819, 0x1919082b19081908, 0x1919082b19190808, 0x1919082b192b2b19, + 0x1919082b2b080808, 0x1919190808080819, 0x1919190808081908, 0x191919080808192b, + 0x1919190808082b19, 0x1919190808190808, 0x191919080819082b, 0x1919190808191919, + 0x1919190808192b08, 0x19191908082b0819, 0x19191908082b1908, 0x1919190819080808, + 0x191919081908082b, 0x1919190819081919, 0x1919190819082b08, 0x1919190819190819, + 0x1919190819191908, 0x19191908192b0808, 0x191919082b080819, 0x191919082b081908, + 0x191919082b190808, 0x1919191908080808, 0x191919190808082b, 0x1919191908081919, + 0x1919191908082b08, 0x1919191908190819, 0x1919191908191908, 0x19191919082b0808, + 0x1919191919080819, 0x1919191919081908, 0x1919191919190808, 0x191919192b080808, + 0x1919192b08080819, 0x1919192b08081908, 0x1919192b08190808, 0x1919192b082b192b, + 0x1919192b19080808, 0x19192b0808080808, 0x19192b080808082b, 0x19192b0808081919, + 0x19192b0808082b08, 0x19192b0808190819, 0x19192b0808191908, 0x19192b08082b0808, + 0x19192b0819080819, 0x19192b0819081908, 0x19192b0819190808, 0x19192b0819192b2b, + 0x19192b082b080808, 0x19192b1908080819, 0x19192b1908081908, 0x19192b1908190808, + 0x19192b1919080808, 0x19192b2b08080808, 0x19192b2b08192b19, 0x19192b2b2b081919, + 0x19192b2b2b2b2b08, 0x192b080808080819, 0x192b080808081908, 0x192b08080808192b, + 0x192b080808190808, 0x192b08080819082b, 0x192b080808191919, 0x192b080808192b08, + 0x192b0808082b0819, 0x192b0808082b1908, 0x192b080819080808, 0x192b080819081919, + 0x192b080819082b08, 0x192b080819190819, 0x192b080819191908, 0x192b0808192b0808, + 0x192b08082b081908, 0x192b08082b190808, 0x192b081908080808, 0x192b08190808082b, + 0x192b081908081919, 0x192b081908082b08, 0x192b081908190819, 0x192b081908191908, + 0x192b0819082b0808, 0x192b081919080819, 0x192b081919081908, 0x192b081919190808, + 0x192b08192b080808, 0x192b08192b192b19, 0x192b082b08081908, 0x192b082b08190808, + 0x192b082b19080808, 0x192b082b1919192b, 0x192b082b2b2b0819, 0x192b190808080808, + 0x192b190808081919, 0x192b190808082b08, 0x192b190808190819, 0x192b190808191908, + 0x192b1908082b0808, 0x192b190819080819, 0x192b190819081908, 0x192b190819190808, + 0x192b19082b080808, 0x192b191908080819, 0x192b191908081908, 0x192b191908190808, + 0x192b191919080808, 0x192b191919082b2b, 0x192b1919192b2b08, 0x192b19192b19082b, + 0x192b192b08080808, 0x192b192b2b191908, 0x192b2b0808080819, 0x192b2b0808081908, + 0x192b2b0808190808, 0x192b2b08192b1919, 0x192b2b082b192b08, 0x192b2b1908080808, + 0x192b2b19082b2b2b, 0x192b2b2b1908082b, 0x192b2b2b2b2b0819, 0x2b08080808080808, + 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819, + 0x2b08080808191908, 0x2b08080808192b19, 0x2b080808082b0808, 0x2b080808082b1919, + 0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808081919082b, + 0x2b08080819191919, 0x2b08080819192b08, 0x2b080808192b0819, 0x2b0808082b080808, + 0x2b0808082b081919, 0x2b0808082b190819, 0x2b0808082b191908, 0x2b08081908080819, + 0x2b08081908081908, 0x2b08081908082b19, 0x2b08081908190808, 0x2b0808190819082b, + 0x2b08081908191919, 0x2b08081908192b08, 0x2b080819082b0819, 0x2b080819082b1908, + 0x2b08081919080808, 0x2b0808191908082b, 0x2b08081919081919, 0x2b08081919082b08, + 0x2b08081919190819, 0x2b08081919191908, 0x2b0808192b080819, 0x2b0808192b081908, + 0x2b0808192b190808, 0x2b0808192b2b2b19, 0x2b08082b08080808, 0x2b08082b08081919, + 0x2b08082b08082b2b, 0x2b08082b08190819, 0x2b08082b08191908, 0x2b08082b19080819, + 0x2b08082b19081908, 0x2b08082b19190808, 0x2b08190808080819, 0x2b08190808081908, + 0x2b0819080808192b, 0x2b08190808082b19, 0x2b08190808190808, 0x2b0819080819082b, + 0x2b08190808191919, 0x2b08190808192b08, 0x2b081908082b0819, 0x2b08190819080808, + 0x2b0819081908082b, 0x2b08190819081919, 0x2b08190819082b08, 0x2b08190819190819, + 0x2b08190819191908, 0x2b081908192b0808, 0x2b0819082b080819, 0x2b0819082b081908, + 0x2b0819082b190808, 0x2b08191908080808, 0x2b0819190808082b, 0x2b08191908081919, + 0x2b08191908082b08, 0x2b08191908190819, 0x2b08191908191908, 0x2b081919082b0808, + 0x2b08191919080819, 0x2b08191919081908, 0x2b08191919190808, 0x2b0819192b080808, + 0x2b0819192b082b2b, 0x2b08192b08080819, 0x2b08192b08081908, 0x2b08192b08190808, + 0x2b08192b082b2b19, 0x2b08192b19080808, 0x2b082b0808080808, 0x2b082b0808081919, + 0x2b082b0808190819, 0x2b082b0808191908, 0x2b082b0819080819, 0x2b082b0819081908, + 0x2b082b0819190808, 0x2b082b082b2b082b, 0x2b082b1908080819, 0x2b082b1908081908, + 0x2b082b1919080808, 0x2b082b19192b1919, 0x2b082b2b082b082b, 0x2b082b2b19192b08, + 0x2b082b2b19192b2b, 0x2b082b2b2b08082b, 0x2b082b2b2b2b082b, 0x2b19080808080819, + 0x2b19080808081908, 0x2b19080808082b19, 0x2b19080808190808, 0x2b1908080819082b, + 0x2b19080808191919, 0x2b19080808192b08, 0x2b190808082b1908, 0x2b19080819080808, + 0x2b1908081908082b, 0x2b19080819081919, 0x2b19080819082b08, 0x2b19080819190819, + 0x2b19080819191908, 0x2b190808192b0808, 0x2b1908082b080819, 0x2b1908082b081908, + 0x2b1908082b190808, 0x2b19081908080808, 0x2b19081908081919, 0x2b19081908190819, + 0x2b19081908191908, 0x2b19081919080819, 0x2b19081919081908, 0x2b19081919190808, + 0x2b19081919192b2b, 0x2b19082b08080819, 0x2b19082b08081908, 0x2b19082b08190808, + 0x2b19082b19080808, 0x2b19082b2b2b192b, 0x2b19190808080808, 0x2b1919080808082b, + 0x2b19190808081919, 0x2b19190808082b08, 0x2b19190808190819, 0x2b19190808191908, + 0x2b191908082b0808, 0x2b19190819080819, 0x2b19190819081908, 0x2b19190819190808, + 0x2b1919082b080808, 0x2b1919082b19192b, 0x2b19191908080819, 0x2b19191908081908, + 0x2b19191908190808, 0x2b19191919080808, 0x2b1919192b192b08, 0x2b1919192b2b0819, + 0x2b19192b08080808, 0x2b19192b1908192b, 0x2b19192b192b1908, 0x2b192b0808080819, + 0x2b192b0808081908, 0x2b192b0808190808, 0x2b192b08082b192b, 0x2b192b0819080808, + 0x2b192b082b2b2b19, 0x2b192b1908080808, 0x2b192b1919082b19, 0x2b192b191919082b, + 0x2b192b2b2b190808, 0x2b2b080808080808, 0x2b2b080808081919, 0x2b2b080808082b2b, + 0x2b2b080808191908, 0x2b2b0808082b082b, 0x2b2b0808082b2b2b, 0x2b2b080819080819, + 0x2b2b080819081908, 0x2b2b080819190808, 0x2b2b08082b2b082b, 0x2b2b08082b2b2b2b, + 0x2b2b081919080808, 0x2b2b0819192b1919, 0x2b2b082b0808082b, 0x2b2b082b08082b2b, + 0x2b2b082b082b082b, 0x2b2b082b082b2b08, 0x2b2b082b082b2b2b, 0x2b2b082b2b08082b, + 0x2b2b082b2b082b08, 0x2b2b082b2b082b2b, 0x2b2b082b2b2b2b08, 0x2b2b190808080819, + 0x2b2b190808081908, 0x2b2b190808190808, 0x2b2b190819080808, 0x2b2b19082b082b19, + 0x2b2b19082b2b1908, 0x2b2b191908080808, 0x2b2b191908192b19, 0x2b2b192b19190819, + 0x2b2b2b0808082b2b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b082b, 0x2b2b2b1919191908, + 0x2b2b2b192b08192b, 0x2b2b2b2b08082b08, 0x2b2b2b2b08082b2b, 0x2b2b2b2b082b0808, + 0x2b2b2b2b082b082b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b2b082b08, 0x2b2b2b2b2b2b2b2b, +GGML_TABLE_END() + +GGML_TABLE_BEGIN(uint32_t, iq3xxs_grid, 256) + 0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, 0x04041404, 0x04041414, + 0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14, + 0x040c140c, 0x040c142c, 0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404, + 0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c, 0x04141c1c, 0x04141c3e, + 0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c, 0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c, + 0x041c3e04, 0x04240c1c, 0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c, + 0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04, 0x043e0c24, 0x043e0c34, + 0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c, 0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c, + 0x0c041c04, 0x0c041c14, 0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c, + 0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14, 0x0c14140c, 0x0c141c04, + 0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404, 0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c, + 0x0c24042c, 0x0c242c04, 0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414, + 0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404, 0x14041414, 0x14041434, + 0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c, 0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c, + 0x140c1c04, 0x140c341c, 0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e, + 0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c, 0x141c0c04, 0x141c0c24, + 0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c, 0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24, + 0x143e040c, 0x143e041c, 0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c, + 0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414, 0x1c0c1404, 0x1c0c1c0c, + 0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c, 0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14, + 0x1c1c0c0c, 0x1c1c1c1c, 0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414, + 0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404, 0x24040424, 0x24040c3e, + 0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e, 0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404, + 0x24143404, 0x24143434, 0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c, + 0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04, 0x2c040c14, 0x2c04240c, + 0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434, 0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14, + 0x2c1c0414, 0x2c1c2c1c, 0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c, + 0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434, 0x34043424, 0x340c140c, + 0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04, 0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14, + 0x34341c1c, 0x343e041c, 0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14, + 0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14, 0x3e1c0404, 0x3e1c0c2c, + 0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c, 0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04, +GGML_TABLE_END() + +GGML_TABLE_BEGIN(uint32_t, iq3s_grid, 512) + 0x01010101, 0x01010103, 0x01010105, 0x0101010b, 0x0101010f, 0x01010301, 0x01010303, 0x01010305, + 0x01010309, 0x0101030d, 0x01010501, 0x01010503, 0x0101050b, 0x01010707, 0x01010901, 0x01010905, + 0x0101090b, 0x0101090f, 0x01010b03, 0x01010b07, 0x01010d01, 0x01010d05, 0x01010f03, 0x01010f09, + 0x01010f0f, 0x01030101, 0x01030103, 0x01030105, 0x01030109, 0x01030301, 0x01030303, 0x0103030b, + 0x01030501, 0x01030507, 0x0103050f, 0x01030703, 0x0103070b, 0x01030909, 0x01030d03, 0x01030d0b, + 0x01030f05, 0x01050101, 0x01050103, 0x0105010b, 0x0105010f, 0x01050301, 0x01050307, 0x0105030d, + 0x01050503, 0x0105050b, 0x01050701, 0x01050709, 0x01050905, 0x0105090b, 0x0105090f, 0x01050b03, + 0x01050b07, 0x01050f01, 0x01050f07, 0x01070107, 0x01070303, 0x0107030b, 0x01070501, 0x01070505, + 0x01070703, 0x01070707, 0x0107070d, 0x01070909, 0x01070b01, 0x01070b05, 0x01070d0f, 0x01070f03, + 0x01070f0b, 0x01090101, 0x01090307, 0x0109030f, 0x01090503, 0x01090509, 0x01090705, 0x01090901, + 0x01090907, 0x01090b03, 0x01090f01, 0x010b0105, 0x010b0109, 0x010b0501, 0x010b0505, 0x010b050d, + 0x010b0707, 0x010b0903, 0x010b090b, 0x010b090f, 0x010b0d0d, 0x010b0f07, 0x010d010d, 0x010d0303, + 0x010d0307, 0x010d0703, 0x010d0b05, 0x010d0f03, 0x010f0101, 0x010f0105, 0x010f0109, 0x010f0501, + 0x010f0505, 0x010f050d, 0x010f0707, 0x010f0b01, 0x010f0b09, 0x03010101, 0x03010103, 0x03010105, + 0x03010109, 0x03010301, 0x03010303, 0x03010307, 0x0301030b, 0x0301030f, 0x03010501, 0x03010505, + 0x03010703, 0x03010709, 0x0301070d, 0x03010b09, 0x03010b0d, 0x03010d03, 0x03010f05, 0x03030101, + 0x03030103, 0x03030107, 0x0303010d, 0x03030301, 0x03030309, 0x03030503, 0x03030701, 0x03030707, + 0x03030903, 0x03030b01, 0x03030b05, 0x03030f01, 0x03030f0d, 0x03050101, 0x03050305, 0x0305030b, + 0x0305030f, 0x03050501, 0x03050509, 0x03050705, 0x03050901, 0x03050907, 0x03050b0b, 0x03050d01, + 0x03050f05, 0x03070103, 0x03070109, 0x0307010f, 0x03070301, 0x03070307, 0x03070503, 0x0307050f, + 0x03070701, 0x03070709, 0x03070903, 0x03070d05, 0x03070f01, 0x03090107, 0x0309010b, 0x03090305, + 0x03090309, 0x03090703, 0x03090707, 0x03090905, 0x0309090d, 0x03090b01, 0x03090b09, 0x030b0103, + 0x030b0301, 0x030b0307, 0x030b0503, 0x030b0701, 0x030b0705, 0x030b0b03, 0x030d0501, 0x030d0509, + 0x030d050f, 0x030d0909, 0x030d090d, 0x030f0103, 0x030f0107, 0x030f0301, 0x030f0305, 0x030f0503, + 0x030f070b, 0x030f0903, 0x030f0d05, 0x030f0f01, 0x05010101, 0x05010103, 0x05010107, 0x0501010b, + 0x0501010f, 0x05010301, 0x05010305, 0x05010309, 0x0501030d, 0x05010503, 0x05010507, 0x0501050f, + 0x05010701, 0x05010705, 0x05010903, 0x05010907, 0x0501090b, 0x05010b01, 0x05010b05, 0x05010d0f, + 0x05010f01, 0x05010f07, 0x05010f0b, 0x05030101, 0x05030105, 0x05030301, 0x05030307, 0x0503030f, + 0x05030505, 0x0503050b, 0x05030703, 0x05030709, 0x05030905, 0x05030b03, 0x05050103, 0x05050109, + 0x0505010f, 0x05050503, 0x05050507, 0x05050701, 0x0505070f, 0x05050903, 0x05050b07, 0x05050b0f, + 0x05050f03, 0x05050f09, 0x05070101, 0x05070105, 0x0507010b, 0x05070303, 0x05070505, 0x05070509, + 0x05070703, 0x05070707, 0x05070905, 0x05070b01, 0x05070d0d, 0x05090103, 0x0509010f, 0x05090501, + 0x05090507, 0x05090705, 0x0509070b, 0x05090903, 0x05090f05, 0x05090f0b, 0x050b0109, 0x050b0303, + 0x050b0505, 0x050b070f, 0x050b0901, 0x050b0b07, 0x050b0f01, 0x050d0101, 0x050d0105, 0x050d010f, + 0x050d0503, 0x050d0b0b, 0x050d0d03, 0x050f010b, 0x050f0303, 0x050f050d, 0x050f0701, 0x050f0907, + 0x050f0b01, 0x07010105, 0x07010303, 0x07010307, 0x0701030b, 0x0701030f, 0x07010505, 0x07010703, + 0x07010707, 0x0701070b, 0x07010905, 0x07010909, 0x0701090f, 0x07010b03, 0x07010d07, 0x07010f03, + 0x07030103, 0x07030107, 0x0703010b, 0x07030309, 0x07030503, 0x07030507, 0x07030901, 0x07030d01, + 0x07030f05, 0x07030f0d, 0x07050101, 0x07050305, 0x07050501, 0x07050705, 0x07050709, 0x07050b01, + 0x07070103, 0x07070301, 0x07070309, 0x07070503, 0x07070507, 0x0707050f, 0x07070701, 0x07070903, + 0x07070907, 0x0707090f, 0x07070b0b, 0x07070f07, 0x07090107, 0x07090303, 0x0709030d, 0x07090505, + 0x07090703, 0x07090b05, 0x07090d01, 0x07090d09, 0x070b0103, 0x070b0301, 0x070b0305, 0x070b050b, + 0x070b0705, 0x070b0909, 0x070b0b0d, 0x070b0f07, 0x070d030d, 0x070d0903, 0x070f0103, 0x070f0107, + 0x070f0501, 0x070f0505, 0x070f070b, 0x09010101, 0x09010109, 0x09010305, 0x09010501, 0x09010509, + 0x0901050f, 0x09010705, 0x09010903, 0x09010b01, 0x09010f01, 0x09030105, 0x0903010f, 0x09030303, + 0x09030307, 0x09030505, 0x09030701, 0x0903070b, 0x09030907, 0x09030b03, 0x09030b0b, 0x09050103, + 0x09050107, 0x09050301, 0x0905030b, 0x09050503, 0x09050707, 0x09050901, 0x09050b0f, 0x09050d05, + 0x09050f01, 0x09070109, 0x09070303, 0x09070307, 0x09070501, 0x09070505, 0x09070703, 0x0907070b, + 0x09090101, 0x09090105, 0x09090509, 0x0909070f, 0x09090901, 0x09090f03, 0x090b010b, 0x090b010f, + 0x090b0503, 0x090b0d05, 0x090d0307, 0x090d0709, 0x090d0d01, 0x090f0301, 0x090f030b, 0x090f0701, + 0x090f0907, 0x090f0b03, 0x0b010105, 0x0b010301, 0x0b010309, 0x0b010505, 0x0b010901, 0x0b010909, + 0x0b01090f, 0x0b010b05, 0x0b010d0d, 0x0b010f09, 0x0b030103, 0x0b030107, 0x0b03010b, 0x0b030305, + 0x0b030503, 0x0b030705, 0x0b030f05, 0x0b050101, 0x0b050303, 0x0b050507, 0x0b050701, 0x0b05070d, + 0x0b050b07, 0x0b070105, 0x0b07010f, 0x0b070301, 0x0b07050f, 0x0b070909, 0x0b070b03, 0x0b070d0b, + 0x0b070f07, 0x0b090103, 0x0b090109, 0x0b090501, 0x0b090705, 0x0b09090d, 0x0b0b0305, 0x0b0b050d, + 0x0b0b0b03, 0x0b0b0b07, 0x0b0d0905, 0x0b0f0105, 0x0b0f0109, 0x0b0f0505, 0x0d010303, 0x0d010307, + 0x0d01030b, 0x0d010703, 0x0d010707, 0x0d010d01, 0x0d030101, 0x0d030501, 0x0d03050f, 0x0d030d09, + 0x0d050305, 0x0d050709, 0x0d050905, 0x0d050b0b, 0x0d050d05, 0x0d050f01, 0x0d070101, 0x0d070309, + 0x0d070503, 0x0d070901, 0x0d09050b, 0x0d090907, 0x0d090d05, 0x0d0b0101, 0x0d0b0107, 0x0d0b0709, + 0x0d0b0d01, 0x0d0d010b, 0x0d0d0901, 0x0d0f0303, 0x0d0f0307, 0x0f010101, 0x0f010109, 0x0f01010f, + 0x0f010501, 0x0f010505, 0x0f01070d, 0x0f010901, 0x0f010b09, 0x0f010d05, 0x0f030105, 0x0f030303, + 0x0f030509, 0x0f030907, 0x0f03090b, 0x0f050103, 0x0f050109, 0x0f050301, 0x0f05030d, 0x0f050503, + 0x0f050701, 0x0f050b03, 0x0f070105, 0x0f070705, 0x0f07070b, 0x0f070b07, 0x0f090103, 0x0f09010b, + 0x0f090307, 0x0f090501, 0x0f090b01, 0x0f0b0505, 0x0f0b0905, 0x0f0d0105, 0x0f0d0703, 0x0f0f0101, +GGML_TABLE_END() + +#define NGRID_IQ1S 2048 +#define IQ1S_DELTA 0.125f +#if defined(GGML_COMMON_IMPL_C) +GGML_TABLE_BEGIN(uint64_t, iq1s_grid, NGRID_IQ1S) + 0xffffffffffffffff, 0xffffffffffffff01, 0xffffffffffff0000, 0xffffffffffff01ff, + 0xffffffffffff0101, 0xffffffffff00ff00, 0xffffffffff000000, 0xffffffffff01ffff, + 0xffffffffff01ff01, 0xffffffffff0101ff, 0xffffffffff010101, 0xffffffff00ff0000, + 0xffffffff0000ff00, 0xffffffff000000ff, 0xffffffff00000001, 0xffffffff00010000, + 0xffffffff01ffffff, 0xffffffff01ffff01, 0xffffffff01ff01ff, 0xffffffff01ff0101, + 0xffffffff01000000, 0xffffffff0101ffff, 0xffffffff0101ff01, 0xffffffff010101ff, + 0xffffffff01010101, 0xffffff00ffff00ff, 0xffffff00ffff0000, 0xffffff00ff00ff00, + 0xffffff00ff0000ff, 0xffffff00ff000001, 0xffffff00ff000100, 0xffffff00ff000101, + 0xffffff00ff010000, 0xffffff0000ffff00, 0xffffff0000ff0001, 0xffffff0000ff0100, + 0xffffff000000ff01, 0xffffff0000000000, 0xffffff0000000101, 0xffffff000001ff00, + 0xffffff00000100ff, 0xffffff0000010001, 0xffffff00000101ff, 0xffffff0001ff0000, + 0xffffff000100ff00, 0xffffff00010000ff, 0xffffff0001000001, 0xffffff0001010000, + 0xffffff01ffffffff, 0xffffff01ffffff01, 0xffffff01ffff01ff, 0xffffff01ffff0101, + 0xffffff01ff000000, 0xffffff01ff01ffff, 0xffffff01ff01ff01, 0xffffff01ff0101ff, + 0xffffff01ff010101, 0xffffff0100ff0000, 0xffffff010000ff00, 0xffffff0100000100, + 0xffffff01000100ff, 0xffffff0100010100, 0xffffff0101ffffff, 0xffffff0101ffff01, + 0xffffff0101ff01ff, 0xffffff0101ff0101, 0xffffff010100ff00, 0xffffff0101000000, + 0xffffff0101000100, 0xffffff010101ffff, 0xffffff010101ff01, 0xffffff01010101ff, + 0xffffff0101010101, 0xffff00ffff00ff00, 0xffff00ffff0000ff, 0xffff00ffff000001, + 0xffff00ffff010000, 0xffff00ff00ffff00, 0xffff00ff00ff0100, 0xffff00ff00000000, + 0xffff00ff00000101, 0xffff00ff000100ff, 0xffff00ff00010000, 0xffff00ff0100ff00, + 0xffff00ff01000100, 0xffff00ff01010000, 0xffff0000ffffff00, 0xffff0000ffff00ff, + 0xffff0000ffff0000, 0xffff0000ffff0001, 0xffff0000ff000000, 0xffff0000ff0001ff, + 0xffff0000ff000101, 0xffff0000ff010100, 0xffff000000ffffff, 0xffff000000ff0000, + 0xffff000000ff0101, 0xffff00000000ffff, 0xffff00000000ff00, 0xffff0000000000ff, + 0xffff000000000000, 0xffff000000000001, 0xffff000000000100, 0xffff00000001ffff, + 0xffff00000001ff01, 0xffff000000010000, 0xffff0000000101ff, 0xffff000000010101, + 0xffff000001ffff00, 0xffff00000100ff00, 0xffff000001000000, 0xffff0000010001ff, + 0xffff000001000101, 0xffff00000101ff00, 0xffff0000010100ff, 0xffff000001010000, + 0xffff000001010001, 0xffff000001010100, 0xffff0001ff0000ff, 0xffff0001ff000100, + 0xffff000100ffff00, 0xffff000100ff00ff, 0xffff00010000ffff, 0xffff00010000ff01, + 0xffff000100000000, 0xffff0001000001ff, 0xffff00010001ffff, 0xffff00010001ff00, + 0xffff000100010001, 0xffff000100010100, 0xffff000101ff0000, 0xffff00010100ff00, + 0xffff0001010000ff, 0xffff000101000100, 0xffff01ffffffffff, 0xffff01ffffffff01, + 0xffff01ffffff01ff, 0xffff01ffffff0101, 0xffff01ffff000000, 0xffff01ffff01ffff, + 0xffff01ffff01ff01, 0xffff01ffff0101ff, 0xffff01ffff010101, 0xffff01ff00ff0000, + 0xffff01ff0000ff00, 0xffff01ff00000001, 0xffff01ff00010000, 0xffff01ff01ffffff, + 0xffff01ff01ffff01, 0xffff01ff01ff01ff, 0xffff01ff01ff0101, 0xffff01ff01000000, + 0xffff01ff0101ffff, 0xffff01ff0101ff01, 0xffff01ff010101ff, 0xffff01ff01010101, + 0xffff0100ffff0000, 0xffff0100ff00ff00, 0xffff0100ff0000ff, 0xffff0100ff000100, + 0xffff0100ff0100ff, 0xffff0100ff010000, 0xffff010000ffff00, 0xffff01000000ffff, + 0xffff01000000ff00, 0xffff010000000000, 0xffff01000001ff00, 0xffff0100000100ff, + 0xffff010000010100, 0xffff01000100ff00, 0xffff0100010000ff, 0xffff010001000001, + 0xffff010001000100, 0xffff010001010000, 0xffff0101ffffffff, 0xffff0101ffffff01, + 0xffff0101ffff01ff, 0xffff0101ffff0101, 0xffff0101ff000000, 0xffff0101ff01ffff, + 0xffff0101ff01ff01, 0xffff0101ff0101ff, 0xffff0101ff010101, 0xffff010100ff0000, + 0xffff01010000ff00, 0xffff010100000100, 0xffff01010001ff00, 0xffff010100010000, + 0xffff010101ffffff, 0xffff010101ffff01, 0xffff010101ff0000, 0xffff010101ff01ff, + 0xffff010101ff0101, 0xffff010101000000, 0xffff01010101ffff, 0xffff01010101ff01, + 0xffff0101010101ff, 0xffff010101010101, 0xff00ffffff00ffff, 0xff00ffffff00ff00, + 0xff00ffffff0000ff, 0xff00ffffff000100, 0xff00ffffff0100ff, 0xff00ffffff010000, + 0xff00ffff00ffff00, 0xff00ffff00ff00ff, 0xff00ffff0000ffff, 0xff00ffff00000000, + 0xff00ffff000001ff, 0xff00ffff0001ff00, 0xff00ffff000100ff, 0xff00ffff00010000, + 0xff00ffff00010100, 0xff00ffff0100ff00, 0xff00ffff010000ff, 0xff00ffff01000001, + 0xff00ffff0101ff00, 0xff00ffff01010000, 0xff00ff00ffffff00, 0xff00ff00ffff00ff, + 0xff00ff00ffff0001, 0xff00ff00ffff0100, 0xff00ff00ff00ffff, 0xff00ff00ff00ff01, + 0xff00ff00ff000000, 0xff00ff00ff0001ff, 0xff00ff00ff01ff00, 0xff00ff00ff0100ff, + 0xff00ff00ff010100, 0xff00ff0000ff0000, 0xff00ff0000ff0101, 0xff00ff000000ffff, + 0xff00ff000000ff00, 0xff00ff000000ff01, 0xff00ff00000000ff, 0xff00ff0000000000, + 0xff00ff0000000001, 0xff00ff0000000100, 0xff00ff000001ffff, 0xff00ff0000010000, + 0xff00ff0001ff00ff, 0xff00ff000100ff01, 0xff00ff0001000000, 0xff00ff000101ff00, + 0xff00ff00010100ff, 0xff00ff01ff00ff00, 0xff00ff01ff0000ff, 0xff00ff01ff000001, + 0xff00ff01ff010000, 0xff00ff0100ffffff, 0xff00ff0100ff0001, 0xff00ff0100ff0100, + 0xff00ff010000ff01, 0xff00ff0100000000, 0xff00ff01000001ff, 0xff00ff0100000101, + 0xff00ff01000100ff, 0xff00ff0100010001, 0xff00ff0101ff0000, 0xff00ff010100ff00, + 0xff00ff01010000ff, 0xff00ff0101000001, 0xff00ff0101010000, 0xff0000ffffffff00, + 0xff0000ffffff0001, 0xff0000ffffff0100, 0xff0000ffff0000ff, 0xff0000ffff000000, + 0xff0000ffff0001ff, 0xff0000ffff000100, 0xff0000ffff01ff00, 0xff0000ffff010001, + 0xff0000ff00ffff00, 0xff0000ff00ff0000, 0xff0000ff00ff0001, 0xff0000ff00ff01ff, + 0xff0000ff00ff0101, 0xff0000ff0000ff00, 0xff0000ff000000ff, 0xff0000ff00000000, + 0xff0000ff00000001, 0xff0000ff00000100, 0xff0000ff0001ff01, 0xff0000ff00010000, + 0xff0000ff000101ff, 0xff0000ff01ff00ff, 0xff0000ff01ff0100, 0xff0000ff0100ffff, + 0xff0000ff010000ff, 0xff0000ff01000000, 0xff0000ff010001ff, 0xff0000ff01000100, + 0xff0000ff01000101, 0xff0000ff0101ff00, 0xff0000ff010100ff, 0xff0000ff01010000, + 0xff0000ff01010100, 0xff000000ffffff01, 0xff000000ffff0000, 0xff000000ffff0101, + 0xff000000ff00ff00, 0xff000000ff0000ff, 0xff000000ff000000, 0xff000000ff000001, + 0xff000000ff000100, 0xff000000ff01ffff, 0xff000000ff01ff01, 0xff000000ff010000, + 0xff000000ff0101ff, 0xff000000ff010101, 0xff00000000ffff00, 0xff00000000ff00ff, + 0xff00000000ff0000, 0xff00000000ff0001, 0xff0000000000ff00, 0xff0000000000ff01, + 0xff000000000000ff, 0xff00000000000000, 0xff00000000000001, 0xff00000000000100, + 0xff00000000000101, 0xff0000000001ff00, 0xff000000000100ff, 0xff00000000010000, + 0xff00000000010001, 0xff00000000010100, 0xff00000001ffffff, 0xff00000001ffff01, + 0xff00000001ff00ff, 0xff00000001ff0000, 0xff00000001ff01ff, 0xff00000001ff0101, + 0xff0000000100ffff, 0xff0000000100ff00, 0xff000000010000ff, 0xff00000001000000, + 0xff00000001000001, 0xff00000001000100, 0xff00000001000101, 0xff0000000101ffff, + 0xff0000000101ff01, 0xff00000001010000, 0xff000001ffffff00, 0xff000001ffff00ff, + 0xff000001ffff0000, 0xff000001ffff0001, 0xff000001ff000000, 0xff000001ff000001, + 0xff000001ff0001ff, 0xff000001ff000101, 0xff000001ff01ff00, 0xff000001ff010001, + 0xff00000100ffffff, 0xff00000100ffff01, 0xff00000100ff00ff, 0xff00000100ff0000, + 0xff00000100ff01ff, 0xff00000100ff0101, 0xff0000010000ff00, 0xff00000100000000, + 0xff00000100000001, 0xff000001000001ff, 0xff00000100000100, 0xff0000010001ff00, + 0xff000001000100ff, 0xff00000100010000, 0xff000001000101ff, 0xff00000100010100, + 0xff00000100010101, 0xff00000101ff0001, 0xff00000101ff0101, 0xff0000010100ff01, + 0xff00000101000000, 0xff000001010100ff, 0xff00000101010100, 0xff0001ffff00ff00, + 0xff0001ffff000001, 0xff0001ffff010000, 0xff0001ff00ffff00, 0xff0001ff00ff00ff, + 0xff0001ff00ff0001, 0xff0001ff00ff0100, 0xff0001ff0000ffff, 0xff0001ff00000000, + 0xff0001ff000001ff, 0xff0001ff00000101, 0xff0001ff0001ffff, 0xff0001ff0001ff00, + 0xff0001ff000100ff, 0xff0001ff00010001, 0xff0001ff00010100, 0xff0001ff01ff0000, + 0xff0001ff0100ff00, 0xff0001ff010000ff, 0xff0001ff01010000, 0xff000100ff00ffff, + 0xff000100ff00ff01, 0xff000100ff000000, 0xff000100ff000101, 0xff000100ff01ff00, + 0xff000100ff010000, 0xff00010000ffff01, 0xff00010000ff00ff, 0xff00010000ff0000, + 0xff00010000ff01ff, 0xff0001000000ff00, 0xff000100000000ff, 0xff00010000000000, + 0xff00010000000001, 0xff00010000000100, 0xff00010000000101, 0xff0001000001ffff, + 0xff00010000010000, 0xff00010000010101, 0xff00010001ff0100, 0xff0001000100ff00, + 0xff0001000100ff01, 0xff00010001000000, 0xff000100010001ff, 0xff0001000101ff00, + 0xff00010001010001, 0xff00010001010100, 0xff000101ffff0100, 0xff000101ff000001, + 0xff000101ff0100ff, 0xff000101ff010001, 0xff00010100ff00ff, 0xff00010100ff0001, + 0xff00010100ff0100, 0xff0001010000ffff, 0xff0001010000ff01, 0xff00010100000000, + 0xff000101000001ff, 0xff0001010001ff00, 0xff00010100010001, 0xff00010100010100, + 0xff00010101ff0000, 0xff0001010100ff00, 0xff00010101000001, 0xff00010101000101, + 0xff01ffffffffffff, 0xff01ffffffffff01, 0xff01ffffffff01ff, 0xff01ffffffff0101, + 0xff01ffffff000000, 0xff01ffffff01ffff, 0xff01ffffff01ff01, 0xff01ffffff010000, + 0xff01ffffff0101ff, 0xff01ffffff010101, 0xff01ffff00ff0000, 0xff01ffff0000ff00, + 0xff01ffff00000100, 0xff01ffff0001ff00, 0xff01ffff00010000, 0xff01ffff01ffffff, + 0xff01ffff01ffff01, 0xff01ffff01ff01ff, 0xff01ffff01ff0101, 0xff01ffff01000000, + 0xff01ffff0101ffff, 0xff01ffff0101ff01, 0xff01ffff01010000, 0xff01ffff010101ff, + 0xff01ffff01010101, 0xff01ff00ffff0000, 0xff01ff00ff00ff00, 0xff01ff00ff0000ff, + 0xff01ff00ff000100, 0xff01ff00ff010000, 0xff01ff0000ffff01, 0xff01ff0000ff00ff, + 0xff01ff0000ff0100, 0xff01ff0000000000, 0xff01ff00000001ff, 0xff01ff0000000101, + 0xff01ff000001ff00, 0xff01ff00000100ff, 0xff01ff0000010000, 0xff01ff0000010001, + 0xff01ff0001ff0000, 0xff01ff000100ffff, 0xff01ff0001000001, 0xff01ff0001000100, + 0xff01ff0001010000, 0xff01ff01ffffff00, 0xff01ff01ffff01ff, 0xff01ff01ffff0101, + 0xff01ff01ff00ff00, 0xff01ff01ff000000, 0xff01ff01ff01ffff, 0xff01ff01ff01ff01, + 0xff01ff01ff0101ff, 0xff01ff01ff010101, 0xff01ff0100ff0000, 0xff01ff010000ff00, + 0xff01ff0100000001, 0xff01ff0100000100, 0xff01ff0100010000, 0xff01ff0101ffff00, + 0xff01ff0101ff01ff, 0xff01ff0101ff0101, 0xff01ff010100ff00, 0xff01ff0101000000, + 0xff01ff010101ffff, 0xff01ff010101ff01, 0xff01ff01010101ff, 0xff01ff0101010101, + 0xff0100ffffff0000, 0xff0100ffff0000ff, 0xff0100ffff000001, 0xff0100ffff000100, + 0xff0100ffff010000, 0xff0100ff00ff00ff, 0xff0100ff00ff0000, 0xff0100ff00ff0001, + 0xff0100ff00ff0100, 0xff0100ff0000ff01, 0xff0100ff00000000, 0xff0100ff000001ff, + 0xff0100ff00000101, 0xff0100ff00010001, 0xff0100ff01ff0000, 0xff0100ff0100ff00, + 0xff0100ff010000ff, 0xff0100ff01000100, 0xff0100ff0101ff00, 0xff0100ff01010000, + 0xff010000ffff0100, 0xff010000ff000000, 0xff010000ff01ff00, 0xff010000ff010100, + 0xff01000000ffffff, 0xff01000000ff0000, 0xff01000000ff01ff, 0xff0100000000ff00, + 0xff010000000000ff, 0xff01000000000000, 0xff01000000000100, 0xff0100000001ff01, + 0xff01000000010000, 0xff010000000101ff, 0xff01000001ff0100, 0xff0100000100ffff, + 0xff010000010000ff, 0xff01000001000000, 0xff010000010001ff, 0xff01000001000101, + 0xff0100000101ff00, 0xff010000010100ff, 0xff01000001010001, 0xff01000001010100, + 0xff010001ffff0000, 0xff010001ff00ffff, 0xff010001ff00ff01, 0xff010001ff000100, + 0xff010001ff010000, 0xff01000100ffff00, 0xff01000100ff0100, 0xff01000100000000, + 0xff0100010001ffff, 0xff0100010001ff00, 0xff01000100010100, 0xff01000101ff00ff, + 0xff01000101ff0001, 0xff0100010100ffff, 0xff01000101000101, 0xff0101ffffffffff, + 0xff0101ffffffff01, 0xff0101ffffff01ff, 0xff0101ffffff0101, 0xff0101ffff000000, + 0xff0101ffff01ffff, 0xff0101ffff01ff01, 0xff0101ffff0101ff, 0xff0101ffff010101, + 0xff0101ff00ff0000, 0xff0101ff0000ff00, 0xff0101ff000000ff, 0xff0101ff00010000, + 0xff0101ff01ffffff, 0xff0101ff01ffff01, 0xff0101ff01ff01ff, 0xff0101ff01ff0101, + 0xff0101ff0101ffff, 0xff0101ff0101ff01, 0xff0101ff010101ff, 0xff0101ff01010101, + 0xff010100ffff0100, 0xff010100ff00ff00, 0xff010100ff0000ff, 0xff010100ff000100, + 0xff010100ff010000, 0xff01010000ff0001, 0xff01010000ff0100, 0xff0101000000ff01, + 0xff01010000000000, 0xff0101000001ff00, 0xff010100000100ff, 0xff01010000010001, + 0xff01010000010100, 0xff01010001ff0000, 0xff0101000100ffff, 0xff01010001000001, + 0xff01010001000100, 0xff010100010100ff, 0xff01010001010000, 0xff010101ffffffff, + 0xff010101ffffff01, 0xff010101ffff01ff, 0xff010101ffff0101, 0xff010101ff01ffff, + 0xff010101ff01ff01, 0xff010101ff0101ff, 0xff010101ff010101, 0xff01010100ff0000, + 0xff0101010000ff00, 0xff01010100000001, 0xff01010100000100, 0xff01010100010000, + 0xff01010101ffffff, 0xff01010101ffff01, 0xff01010101ff01ff, 0xff01010101ff0101, + 0xff01010101000000, 0xff0101010101ffff, 0xff0101010101ff01, 0xff010101010101ff, + 0xff01010101010101, 0x00ffffffffff0000, 0x00ffffffff00ff00, 0x00ffffffff000001, + 0x00ffffffff010000, 0x00ffffff00ff0100, 0x00ffffff0000ff01, 0x00ffffff00000000, + 0x00ffffff000001ff, 0x00ffffff00000101, 0x00ffffff0001ff00, 0x00ffffff000100ff, + 0x00ffffff00010001, 0x00ffffff010000ff, 0x00ffffff01000100, 0x00ffffff0101ff00, + 0x00ffffff01010001, 0x00ffff00ffffffff, 0x00ffff00ffffff00, 0x00ffff00ffff00ff, + 0x00ffff00ffff0001, 0x00ffff00ffff0100, 0x00ffff00ff00ff01, 0x00ffff00ff000000, + 0x00ffff00ff000001, 0x00ffff00ff0001ff, 0x00ffff00ff000101, 0x00ffff00ff01ff00, + 0x00ffff00ff010001, 0x00ffff00ff010100, 0x00ffff0000ff0000, 0x00ffff0000ff01ff, + 0x00ffff0000ff0101, 0x00ffff000000ff00, 0x00ffff00000000ff, 0x00ffff0000000000, + 0x00ffff0000000001, 0x00ffff0000000100, 0x00ffff0000000101, 0x00ffff0000010000, + 0x00ffff00000101ff, 0x00ffff0000010101, 0x00ffff0001ffff00, 0x00ffff0001ff00ff, + 0x00ffff0001ff0001, 0x00ffff000100ffff, 0x00ffff000100ff01, 0x00ffff0001000000, + 0x00ffff000101ffff, 0x00ffff000101ff00, 0x00ffff000101ff01, 0x00ffff01ffff0000, + 0x00ffff01ff00ff00, 0x00ffff01ff0000ff, 0x00ffff01ff000001, 0x00ffff01ff010000, + 0x00ffff0100ffff00, 0x00ffff010000ff01, 0x00ffff0100000000, 0x00ffff0100000101, + 0x00ffff01000100ff, 0x00ffff0100010100, 0x00ffff0101ff0100, 0x00ffff01010000ff, + 0x00ffff0101010000, 0x00ff00ffffffff00, 0x00ff00ffff000000, 0x00ff00ffff000100, + 0x00ff00ffff010100, 0x00ff00ff00ff0000, 0x00ff00ff00ff01ff, 0x00ff00ff00ff0101, + 0x00ff00ff0000ff00, 0x00ff00ff000000ff, 0x00ff00ff00000000, 0x00ff00ff00000001, + 0x00ff00ff0001ff00, 0x00ff00ff0001ff01, 0x00ff00ff00010000, 0x00ff00ff000101ff, + 0x00ff00ff00010101, 0x00ff00ff01ffff00, 0x00ff00ff01ff0001, 0x00ff00ff01ff0100, + 0x00ff00ff0100ffff, 0x00ff00ff0100ff01, 0x00ff00ff01000000, 0x00ff00ff0101ffff, + 0x00ff00ff0101ff00, 0x00ff00ff01010100, 0x00ff0000ffffff00, 0x00ff0000ffffff01, + 0x00ff0000ffff0000, 0x00ff0000ffff0101, 0x00ff0000ff00ff00, 0x00ff0000ff0000ff, + 0x00ff0000ff000000, 0x00ff0000ff000001, 0x00ff0000ff000100, 0x00ff0000ff01ffff, + 0x00ff0000ff010000, 0x00ff0000ff010101, 0x00ff000000ffff00, 0x00ff000000ff00ff, + 0x00ff000000ff0000, 0x00ff000000ff0001, 0x00ff000000ff0100, 0x00ff00000000ffff, + 0x00ff00000000ff00, 0x00ff0000000000ff, 0x00ff000000000000, 0x00ff000000000001, + 0x00ff0000000001ff, 0x00ff000000000100, 0x00ff00000001ff00, 0x00ff0000000100ff, + 0x00ff000000010000, 0x00ff000000010001, 0x00ff000000010100, 0x00ff000001ffff01, + 0x00ff000001ff00ff, 0x00ff000001ff0000, 0x00ff000001ff01ff, 0x00ff00000100ff00, + 0x00ff0000010000ff, 0x00ff000001000000, 0x00ff000001000001, 0x00ff000001000100, + 0x00ff000001000101, 0x00ff000001010000, 0x00ff0000010101ff, 0x00ff000001010101, + 0x00ff0001ffffff00, 0x00ff0001ffff0000, 0x00ff0001ffff0100, 0x00ff0001ff0000ff, + 0x00ff0001ff000000, 0x00ff0001ff0001ff, 0x00ff0001ff000101, 0x00ff0001ff01ff00, + 0x00ff0001ff0100ff, 0x00ff0001ff010100, 0x00ff000100ffffff, 0x00ff000100ffff01, + 0x00ff000100ff0000, 0x00ff000100ff01ff, 0x00ff00010000ffff, 0x00ff00010000ff00, + 0x00ff00010000ff01, 0x00ff000100000000, 0x00ff000100000001, 0x00ff000100000100, + 0x00ff00010001ff01, 0x00ff000100010000, 0x00ff0001000101ff, 0x00ff000101ffff00, + 0x00ff000101ff0000, 0x00ff000101ff0101, 0x00ff0001010000ff, 0x00ff000101000000, + 0x00ff00010101ff00, 0x00ff0001010100ff, 0x00ff000101010001, 0x00ff01ffffff0000, + 0x00ff01ffff00ff00, 0x00ff01ffff000000, 0x00ff01ffff000101, 0x00ff01ffff010000, + 0x00ff01ff00ffff01, 0x00ff01ff00ff0100, 0x00ff01ff0000ffff, 0x00ff01ff00000000, + 0x00ff01ff000001ff, 0x00ff01ff0001ff00, 0x00ff01ff000100ff, 0x00ff01ff00010001, + 0x00ff01ff00010100, 0x00ff01ff01ff0000, 0x00ff01ff0100ff00, 0x00ff01ff010000ff, + 0x00ff01ff01000001, 0x00ff01ff01000100, 0x00ff01ff01010000, 0x00ff0100ffffff00, + 0x00ff0100ffff0000, 0x00ff0100ffff0001, 0x00ff0100ffff0101, 0x00ff0100ff00ffff, + 0x00ff0100ff0000ff, 0x00ff0100ff000000, 0x00ff0100ff0001ff, 0x00ff0100ff01ff00, + 0x00ff0100ff0100ff, 0x00ff0100ff010001, 0x00ff010000ffffff, 0x00ff010000ff0000, + 0x00ff010000ff0101, 0x00ff01000000ff00, 0x00ff01000000ff01, 0x00ff0100000000ff, + 0x00ff010000000000, 0x00ff010000000001, 0x00ff010000000100, 0x00ff01000001ffff, + 0x00ff01000001ff01, 0x00ff010000010000, 0x00ff010000010001, 0x00ff010000010101, + 0x00ff010001ff0001, 0x00ff010001ff0100, 0x00ff01000100ff01, 0x00ff010001000000, + 0x00ff010001000001, 0x00ff0100010001ff, 0x00ff01000101ff00, 0x00ff0100010100ff, + 0x00ff010001010001, 0x00ff010001010100, 0x00ff0101ff000001, 0x00ff010100ff00ff, + 0x00ff010100ff0001, 0x00ff010100ff0100, 0x00ff010100000000, 0x00ff0101000001ff, + 0x00ff010100000101, 0x00ff0101000100ff, 0x00ff010100010100, 0x00ff0101010000ff, + 0x00ff010101010000, 0x0000ffffffffff00, 0x0000ffffffff00ff, 0x0000ffffffff0000, + 0x0000ffffffff0001, 0x0000ffffffff0100, 0x0000ffffff00ff01, 0x0000ffffff000000, + 0x0000ffffff000101, 0x0000ffffff01ff00, 0x0000ffffff0100ff, 0x0000ffffff010100, + 0x0000ffff00ffffff, 0x0000ffff00ff0000, 0x0000ffff00ff01ff, 0x0000ffff0000ff00, + 0x0000ffff000000ff, 0x0000ffff00000000, 0x0000ffff00000001, 0x0000ffff00000100, + 0x0000ffff00010000, 0x0000ffff000101ff, 0x0000ffff01ff0001, 0x0000ffff01ff0100, + 0x0000ffff01000000, 0x0000ffff010001ff, 0x0000ffff0101ffff, 0x0000ffff0101ff00, + 0x0000ffff01010001, 0x0000ffff01010100, 0x0000ff00ffff0000, 0x0000ff00ffff01ff, + 0x0000ff00ffff0100, 0x0000ff00ffff0101, 0x0000ff00ff00ff00, 0x0000ff00ff0000ff, + 0x0000ff00ff000000, 0x0000ff00ff000001, 0x0000ff00ff0001ff, 0x0000ff00ff000100, + 0x0000ff00ff01ffff, 0x0000ff00ff010000, 0x0000ff00ff010001, 0x0000ff00ff0101ff, + 0x0000ff00ff010101, 0x0000ff0000ffff00, 0x0000ff0000ff00ff, 0x0000ff0000ff0000, + 0x0000ff0000ff0001, 0x0000ff0000ff0100, 0x0000ff000000ffff, 0x0000ff000000ff00, + 0x0000ff000000ff01, 0x0000ff00000000ff, 0x0000ff0000000000, 0x0000ff0000000001, + 0x0000ff00000001ff, 0x0000ff0000000100, 0x0000ff0000000101, 0x0000ff000001ff00, + 0x0000ff00000100ff, 0x0000ff0000010000, 0x0000ff0000010001, 0x0000ff0000010100, + 0x0000ff0001ffff01, 0x0000ff0001ff0000, 0x0000ff000100ff00, 0x0000ff00010000ff, + 0x0000ff0001000000, 0x0000ff0001000001, 0x0000ff0001000100, 0x0000ff000101ffff, + 0x0000ff0001010000, 0x0000ff0001010101, 0x0000ff01ffffff00, 0x0000ff01ffff0001, + 0x0000ff01ff00ff01, 0x0000ff01ff000000, 0x0000ff01ff000101, 0x0000ff01ff01ff00, + 0x0000ff01ff0100ff, 0x0000ff0100ffff01, 0x0000ff0100ff0000, 0x0000ff0100ff0101, + 0x0000ff010000ff00, 0x0000ff01000000ff, 0x0000ff0100000000, 0x0000ff0100000001, + 0x0000ff0100000100, 0x0000ff010001ff01, 0x0000ff0100010000, 0x0000ff0101ff0000, + 0x0000ff010100ffff, 0x0000ff010100ff01, 0x0000ff0101000000, 0x0000ff0101000100, + 0x0000ff0101000101, 0x0000ff01010100ff, 0x000000ffffff00ff, 0x000000ffffff0000, + 0x000000ffff00ff00, 0x000000ffff0000ff, 0x000000ffff000000, 0x000000ffff000001, + 0x000000ffff0001ff, 0x000000ffff000100, 0x000000ffff01ff00, 0x000000ffff010000, + 0x000000ffff0101ff, 0x000000ffff010101, 0x000000ff00ffff00, 0x000000ff00ff00ff, + 0x000000ff00ff0000, 0x000000ff00ff0001, 0x000000ff00ff0100, 0x000000ff00ff0101, + 0x000000ff0000ffff, 0x000000ff0000ff00, 0x000000ff000000ff, 0x000000ff00000000, + 0x000000ff00000001, 0x000000ff000001ff, 0x000000ff00000100, 0x000000ff00000101, + 0x000000ff0001ff00, 0x000000ff0001ff01, 0x000000ff000100ff, 0x000000ff00010000, + 0x000000ff00010001, 0x000000ff00010100, 0x000000ff01ffffff, 0x000000ff01ff01ff, + 0x000000ff01ff0101, 0x000000ff0100ff00, 0x000000ff010000ff, 0x000000ff01000000, + 0x000000ff01000001, 0x000000ff01000100, 0x000000ff0101ff00, 0x000000ff010100ff, + 0x000000ff01010000, 0x000000ff01010101, 0x00000000ffffff00, 0x00000000ffffff01, + 0x00000000ffff00ff, 0x00000000ffff0000, 0x00000000ffff0001, 0x00000000ffff0100, + 0x00000000ff00ffff, 0x00000000ff00ff00, 0x00000000ff00ff01, 0x00000000ff0000ff, + 0x00000000ff000000, 0x00000000ff000001, 0x00000000ff000100, 0x00000000ff000101, + 0x00000000ff01ff00, 0x00000000ff0100ff, 0x00000000ff010000, 0x00000000ff010001, + 0x00000000ff010100, 0x0000000000ffffff, 0x0000000000ffff00, 0x0000000000ffff01, + 0x0000000000ff00ff, 0x0000000000ff0000, 0x0000000000ff0001, 0x0000000000ff01ff, + 0x0000000000ff0100, 0x000000000000ffff, 0x000000000000ff00, 0x000000000000ff01, + 0x00000000000000ff, 0x0000000000000000, 0x0000000000000001, 0x00000000000001ff, + 0x0000000000000100, 0x0000000000000101, 0x000000000001ffff, 0x000000000001ff00, + 0x00000000000100ff, 0x0000000000010000, 0x0000000000010001, 0x00000000000101ff, + 0x0000000000010100, 0x0000000000010101, 0x0000000001ffff00, 0x0000000001ff00ff, + 0x0000000001ff0000, 0x0000000001ff0100, 0x0000000001ff0101, 0x000000000100ffff, + 0x000000000100ff00, 0x00000000010000ff, 0x0000000001000000, 0x0000000001000001, + 0x00000000010001ff, 0x0000000001000100, 0x000000000101ff00, 0x00000000010100ff, + 0x0000000001010000, 0x0000000001010001, 0x0000000001010100, 0x00000001ffffffff, + 0x00000001ffffff00, 0x00000001ffffff01, 0x00000001ffff00ff, 0x00000001ffff0001, + 0x00000001ffff01ff, 0x00000001ffff0100, 0x00000001ff00ff00, 0x00000001ff0000ff, + 0x00000001ff000000, 0x00000001ff0001ff, 0x00000001ff000100, 0x00000001ff01ffff, + 0x00000001ff01ff00, 0x00000001ff01ff01, 0x00000001ff0100ff, 0x00000001ff010000, + 0x00000001ff010001, 0x00000001ff0101ff, 0x00000001ff010100, 0x0000000100ffff00, + 0x0000000100ff0000, 0x0000000100ff0001, 0x0000000100ff01ff, 0x0000000100ff0100, + 0x0000000100ff0101, 0x000000010000ffff, 0x000000010000ff00, 0x000000010000ff01, + 0x00000001000000ff, 0x0000000100000000, 0x0000000100000001, 0x00000001000001ff, + 0x0000000100000100, 0x0000000100000101, 0x000000010001ff00, 0x00000001000100ff, + 0x0000000100010000, 0x0000000100010100, 0x0000000101ffff01, 0x0000000101ff0000, + 0x0000000101ff0001, 0x0000000101ff01ff, 0x0000000101ff0100, 0x0000000101ff0101, + 0x000000010100ff00, 0x0000000101000000, 0x0000000101000101, 0x000000010101ff01, + 0x0000000101010000, 0x0000000101010001, 0x00000001010101ff, 0x0000000101010100, + 0x000001ffffff00ff, 0x000001ffffff0000, 0x000001ffffff0001, 0x000001ffffff0100, + 0x000001ffff00ffff, 0x000001ffff000000, 0x000001ffff0001ff, 0x000001ffff01ff00, + 0x000001ffff010101, 0x000001ff00ff0000, 0x000001ff00ff01ff, 0x000001ff00ff0101, + 0x000001ff0000ff00, 0x000001ff000000ff, 0x000001ff00000000, 0x000001ff00000001, + 0x000001ff000001ff, 0x000001ff00000100, 0x000001ff0001ffff, 0x000001ff0001ff01, + 0x000001ff000100ff, 0x000001ff00010000, 0x000001ff01ffff01, 0x000001ff01ff0100, + 0x000001ff0100ffff, 0x000001ff0100ff01, 0x000001ff01000000, 0x000001ff010001ff, + 0x000001ff0101ff00, 0x000001ff01010100, 0x00000100ffffff00, 0x00000100ffffff01, + 0x00000100ffff0000, 0x00000100ffff0101, 0x00000100ff00ff00, 0x00000100ff0000ff, + 0x00000100ff000000, 0x00000100ff000001, 0x00000100ff000100, 0x00000100ff010000, + 0x0000010000ffff00, 0x0000010000ff00ff, 0x0000010000ff0000, 0x0000010000ff0001, + 0x0000010000ff0100, 0x000001000000ffff, 0x000001000000ff00, 0x000001000000ff01, + 0x00000100000000ff, 0x0000010000000000, 0x0000010000000001, 0x00000100000001ff, + 0x0000010000000100, 0x0000010000000101, 0x000001000001ff00, 0x00000100000100ff, + 0x0000010000010000, 0x0000010000010001, 0x0000010000010100, 0x0000010001ffff00, + 0x0000010001ff0000, 0x0000010001ff0100, 0x000001000100ff00, 0x00000100010000ff, + 0x0000010001000000, 0x0000010001000001, 0x00000100010001ff, 0x0000010001000100, + 0x0000010001010000, 0x00000101ffff00ff, 0x00000101ffff01ff, 0x00000101ff000000, + 0x00000101ff000101, 0x00000101ff01ffff, 0x00000101ff010000, 0x00000101ff010001, + 0x00000101ff010100, 0x0000010100ff0000, 0x0000010100ff01ff, 0x0000010100ff0100, + 0x000001010000ff00, 0x0000010100000000, 0x0000010100000001, 0x00000101000001ff, + 0x0000010100000100, 0x000001010001ff01, 0x0000010100010000, 0x00000101000101ff, + 0x0000010100010101, 0x0000010101ffff00, 0x0000010101ff0101, 0x000001010100ff01, + 0x0000010101000000, 0x0000010101000001, 0x00000101010001ff, 0x0000010101000101, + 0x000001010101ff00, 0x0001ffffffff0000, 0x0001ffffff0000ff, 0x0001ffffff000001, + 0x0001ffffff000100, 0x0001ffffff010000, 0x0001ffff00ff00ff, 0x0001ffff0000ffff, + 0x0001ffff00000000, 0x0001ffff00000001, 0x0001ffff000001ff, 0x0001ffff00000101, + 0x0001ffff0001ff00, 0x0001ffff000100ff, 0x0001ffff00010001, 0x0001ffff00010100, + 0x0001ffff01ffff00, 0x0001ffff01000001, 0x0001ffff01010000, 0x0001ff00ffffff00, + 0x0001ff00ffff00ff, 0x0001ff00ffff0001, 0x0001ff00ffff0100, 0x0001ff00ff00ff01, + 0x0001ff00ff000000, 0x0001ff00ff01ff00, 0x0001ff00ff01ff01, 0x0001ff00ff010001, + 0x0001ff00ff010100, 0x0001ff0000ff0000, 0x0001ff0000ff0100, 0x0001ff000000ff00, + 0x0001ff0000000000, 0x0001ff0000000001, 0x0001ff0000000100, 0x0001ff0000010000, + 0x0001ff0000010001, 0x0001ff0000010101, 0x0001ff0001ff00ff, 0x0001ff0001ff0101, + 0x0001ff000100ff01, 0x0001ff0001000000, 0x0001ff000101ff00, 0x0001ff0001010001, + 0x0001ff0001010100, 0x0001ff01ff00ff00, 0x0001ff01ff000001, 0x0001ff01ff000100, + 0x0001ff0100ffffff, 0x0001ff0100ffff00, 0x0001ff0100ff0001, 0x0001ff0100000000, + 0x0001ff0100000001, 0x0001ff01000001ff, 0x0001ff010001ffff, 0x0001ff0101ff0000, + 0x0001ff010100ff00, 0x0001ff0101000001, 0x0001ff0101010000, 0x000100ffff00ff00, + 0x000100ffff00ff01, 0x000100ffff000000, 0x000100ffff000001, 0x000100ffff000101, + 0x000100ffff01ff00, 0x000100ffff010001, 0x000100ffff010100, 0x000100ff00ffffff, + 0x000100ff00ffff01, 0x000100ff00ff0000, 0x000100ff00ff01ff, 0x000100ff00ff0101, + 0x000100ff0000ff00, 0x000100ff000000ff, 0x000100ff00000000, 0x000100ff00000001, + 0x000100ff00000100, 0x000100ff00000101, 0x000100ff0001ffff, 0x000100ff0001ff01, + 0x000100ff00010000, 0x000100ff01ff00ff, 0x000100ff01ff0000, 0x000100ff01ff0100, + 0x000100ff0100ffff, 0x000100ff0100ff01, 0x000100ff010000ff, 0x000100ff01000000, + 0x000100ff01000001, 0x000100ff010001ff, 0x000100ff01000101, 0x000100ff0101ff00, + 0x000100ff010100ff, 0x000100ff01010100, 0x00010000ffff0000, 0x00010000ffff01ff, + 0x00010000ffff0101, 0x00010000ff00ff00, 0x00010000ff000000, 0x00010000ff000001, + 0x00010000ff000100, 0x0001000000ff00ff, 0x0001000000ff0000, 0x0001000000ff0001, + 0x0001000000ff0100, 0x000100000000ffff, 0x000100000000ff00, 0x00010000000000ff, + 0x0001000000000000, 0x0001000000000001, 0x0001000000000100, 0x000100000001ff00, + 0x00010000000100ff, 0x0001000000010000, 0x0001000000010001, 0x0001000000010100, + 0x0001000001ff0001, 0x0001000001ff0100, 0x0001000001ff0101, 0x000100000100ff00, + 0x0001000001000000, 0x0001000001000001, 0x0001000001000100, 0x0001000001000101, + 0x000100000101ff01, 0x0001000001010000, 0x0001000001010001, 0x00010000010101ff, + 0x00010001ffffff01, 0x00010001ffff0100, 0x00010001ff000000, 0x00010001ff01ffff, + 0x00010001ff010001, 0x00010001ff0101ff, 0x00010001ff010100, 0x0001000100ffffff, + 0x0001000100ff0000, 0x0001000100ff01ff, 0x0001000100ff0101, 0x000100010000ff00, + 0x00010001000000ff, 0x0001000100000000, 0x0001000100000001, 0x00010001000001ff, + 0x0001000100000101, 0x000100010001ffff, 0x0001000100010000, 0x00010001000101ff, + 0x0001000101ffffff, 0x0001000101ffff01, 0x0001000101ff0000, 0x0001000101ff0101, + 0x00010001010000ff, 0x0001000101000001, 0x00010001010001ff, 0x0001000101000100, + 0x000100010101ffff, 0x00010001010100ff, 0x0001000101010001, 0x0001000101010101, + 0x000101ffff000001, 0x000101ffff000100, 0x000101ffff010000, 0x000101ff00ffff00, + 0x000101ff0000ff01, 0x000101ff00000000, 0x000101ff00000101, 0x000101ff0001ff00, + 0x000101ff00010100, 0x000101ff01ff0000, 0x000101ff0100ff00, 0x000101ff010001ff, + 0x000101ff01010001, 0x00010100ffffff00, 0x00010100ffff00ff, 0x00010100ff00ffff, + 0x00010100ff000000, 0x00010100ff01ff00, 0x00010100ff0100ff, 0x00010100ff010001, + 0x00010100ff010100, 0x0001010000ffffff, 0x0001010000ffff00, 0x0001010000ff0000, + 0x0001010000ff0001, 0x0001010000ff01ff, 0x000101000000ff00, 0x00010100000000ff, + 0x0001010000000000, 0x0001010000000001, 0x0001010000000100, 0x000101000001ffff, + 0x0001010000010000, 0x0001010000010101, 0x0001010001ffff01, 0x0001010001ff00ff, + 0x0001010001ff0101, 0x0001010001000000, 0x000101000101ff00, 0x00010100010100ff, + 0x0001010001010000, 0x0001010001010100, 0x00010101ff00ff00, 0x00010101ff000001, + 0x00010101ff0001ff, 0x0001010100ffff00, 0x0001010100ff00ff, 0x0001010100ff0100, + 0x000101010000ffff, 0x0001010100000000, 0x00010101000001ff, 0x0001010100000101, + 0x00010101000100ff, 0x0001010100010000, 0x0001010100010100, 0x0001010101ff0001, + 0x00010101010000ff, 0x00010101010001ff, 0x0001010101000101, 0x0001010101010001, + 0x01ffffffffffffff, 0x01ffffffffffff01, 0x01ffffffffff01ff, 0x01ffffffffff0101, + 0x01ffffffff01ffff, 0x01ffffffff01ff01, 0x01ffffffff0101ff, 0x01ffffffff010101, + 0x01ffffff00ff0000, 0x01ffffff0000ffff, 0x01ffffff0000ff00, 0x01ffffff000000ff, + 0x01ffffff00000001, 0x01ffffff00000100, 0x01ffffff00010000, 0x01ffffff01ffffff, + 0x01ffffff01ffff01, 0x01ffffff01ff01ff, 0x01ffffff01ff0101, 0x01ffffff01000000, + 0x01ffffff0101ffff, 0x01ffffff0101ff01, 0x01ffffff010101ff, 0x01ffffff01010101, + 0x01ffff00ffff0000, 0x01ffff00ff00ff00, 0x01ffff00ff0000ff, 0x01ffff00ff000001, + 0x01ffff00ff000100, 0x01ffff00ff010000, 0x01ffff0000ffff00, 0x01ffff0000ff00ff, + 0x01ffff0000ff0100, 0x01ffff000000ffff, 0x01ffff000000ff01, 0x01ffff0000000000, + 0x01ffff0000000001, 0x01ffff00000001ff, 0x01ffff0000000100, 0x01ffff00000100ff, + 0x01ffff0000010001, 0x01ffff0000010100, 0x01ffff0001ff0000, 0x01ffff0001ff0100, + 0x01ffff00010000ff, 0x01ffff0001000001, 0x01ffff0001000100, 0x01ffff0001010000, + 0x01ffff01ffffffff, 0x01ffff01ffffff01, 0x01ffff01ffff01ff, 0x01ffff01ffff0101, + 0x01ffff01ff000000, 0x01ffff01ff01ffff, 0x01ffff01ff01ff01, 0x01ffff01ff0101ff, + 0x01ffff01ff010101, 0x01ffff010000ff00, 0x01ffff01000000ff, 0x01ffff0100000100, + 0x01ffff0100010000, 0x01ffff0101ffffff, 0x01ffff0101ffff01, 0x01ffff0101ff01ff, + 0x01ffff0101ff0101, 0x01ffff0101000000, 0x01ffff010101ffff, 0x01ffff010101ff01, + 0x01ffff01010101ff, 0x01ffff0101010101, 0x01ff00ffff0000ff, 0x01ff00ffff000100, + 0x01ff00ff00ffff00, 0x01ff00ff00ff00ff, 0x01ff00ff0000ff00, 0x01ff00ff00000000, + 0x01ff00ff00000101, 0x01ff00ff0001ff00, 0x01ff00ff000100ff, 0x01ff00ff00010100, + 0x01ff00ff010000ff, 0x01ff00ff01000100, 0x01ff0000ffffff00, 0x01ff0000ffff0100, + 0x01ff0000ff00ff01, 0x01ff0000ff000000, 0x01ff0000ff000101, 0x01ff0000ff010001, + 0x01ff0000ff010100, 0x01ff000000ffffff, 0x01ff000000ffff00, 0x01ff000000ff0000, + 0x01ff000000ff01ff, 0x01ff00000000ff00, 0x01ff0000000000ff, 0x01ff000000000000, + 0x01ff000000000001, 0x01ff000000000100, 0x01ff000000000101, 0x01ff000000010000, + 0x01ff000000010001, 0x01ff0000000101ff, 0x01ff000000010101, 0x01ff000001ffff00, + 0x01ff000001ff00ff, 0x01ff000001ff0001, 0x01ff000001ff0100, 0x01ff00000100ffff, + 0x01ff00000100ff01, 0x01ff000001000000, 0x01ff0000010001ff, 0x01ff000001010001, + 0x01ff0001ff00ff00, 0x01ff0001ff000001, 0x01ff0001ff000100, 0x01ff0001ff010000, + 0x01ff000100ffff00, 0x01ff000100ff00ff, 0x01ff000100ff0100, 0x01ff000100ff0101, + 0x01ff00010000ffff, 0x01ff000100000000, 0x01ff000100000100, 0x01ff000100000101, + 0x01ff00010001ff00, 0x01ff000100010001, 0x01ff000100010101, 0x01ff000101ff0000, + 0x01ff00010100ff00, 0x01ff000101000101, 0x01ff0001010100ff, 0x01ff01ffffffffff, + 0x01ff01ffffffff01, 0x01ff01ffffff01ff, 0x01ff01ffffff0101, 0x01ff01ffff000000, + 0x01ff01ffff01ffff, 0x01ff01ffff01ff01, 0x01ff01ffff0101ff, 0x01ff01ffff010101, + 0x01ff01ff00ffff00, 0x01ff01ff00ff0000, 0x01ff01ff0000ff00, 0x01ff01ff000000ff, + 0x01ff01ff00000100, 0x01ff01ff00010000, 0x01ff01ff00010100, 0x01ff01ff01ffffff, + 0x01ff01ff01ffff01, 0x01ff01ff01ff01ff, 0x01ff01ff01ff0101, 0x01ff01ff01000000, + 0x01ff01ff0101ffff, 0x01ff01ff0101ff01, 0x01ff01ff010101ff, 0x01ff01ff01010101, + 0x01ff0100ffff0000, 0x01ff0100ffff0001, 0x01ff0100ff00ff00, 0x01ff0100ff0000ff, + 0x01ff0100ff000001, 0x01ff0100ff010000, 0x01ff010000ffff00, 0x01ff010000ff00ff, + 0x01ff010000ff0001, 0x01ff010000ff0100, 0x01ff01000000ffff, 0x01ff01000000ff01, + 0x01ff010000000000, 0x01ff010000000101, 0x01ff01000001ff00, 0x01ff0100000100ff, + 0x01ff010001ff0000, 0x01ff010001000001, 0x01ff010001000100, 0x01ff010001010000, + 0x01ff0101ffffffff, 0x01ff0101ffffff01, 0x01ff0101ffff01ff, 0x01ff0101ffff0101, + 0x01ff0101ff000000, 0x01ff0101ff01ffff, 0x01ff0101ff01ff01, 0x01ff0101ff0101ff, + 0x01ff0101ff010101, 0x01ff010100ff0000, 0x01ff01010000ff00, 0x01ff0101000000ff, + 0x01ff010100000001, 0x01ff010101ffffff, 0x01ff010101ffff01, 0x01ff010101ff01ff, + 0x01ff010101ff0101, 0x01ff010101000000, 0x01ff01010101ffff, 0x01ff01010101ff01, + 0x01ff0101010101ff, 0x01ff010101010101, 0x0100ffffffff0000, 0x0100ffffff00ff00, + 0x0100ffffff000001, 0x0100ffffff0001ff, 0x0100ffffff000100, 0x0100ffffff010000, + 0x0100ffff00ffff00, 0x0100ffff00ff0001, 0x0100ffff00ff0100, 0x0100ffff00000000, + 0x0100ffff000001ff, 0x0100ffff00000101, 0x0100ffff00010100, 0x0100ffff00010101, + 0x0100ffff01ff0000, 0x0100ffff0100ff00, 0x0100ffff010000ff, 0x0100ffff01000001, + 0x0100ffff01000100, 0x0100ffff01010000, 0x0100ff00ffffff00, 0x0100ff00ffff00ff, + 0x0100ff00ffff0001, 0x0100ff00ffff0100, 0x0100ff00ff00ffff, 0x0100ff00ff000000, + 0x0100ff00ff0001ff, 0x0100ff00ff000101, 0x0100ff00ff01ff00, 0x0100ff00ff0100ff, + 0x0100ff00ff010001, 0x0100ff00ff010100, 0x0100ff0000ffffff, 0x0100ff0000ff0000, + 0x0100ff000000ffff, 0x0100ff000000ff00, 0x0100ff00000000ff, 0x0100ff0000000000, + 0x0100ff0000000001, 0x0100ff0000000100, 0x0100ff000001ff01, 0x0100ff0000010000, + 0x0100ff0001ff00ff, 0x0100ff0001ff0001, 0x0100ff000100ff01, 0x0100ff0001000000, + 0x0100ff00010001ff, 0x0100ff000101ff00, 0x0100ff00010100ff, 0x0100ff0001010001, + 0x0100ff0001010100, 0x0100ff01ffff0000, 0x0100ff01ff00ff00, 0x0100ff01ff0000ff, + 0x0100ff01ff000100, 0x0100ff01ff010000, 0x0100ff0100ff00ff, 0x0100ff0100ff0001, + 0x0100ff0100ff0100, 0x0100ff010000ffff, 0x0100ff010000ff01, 0x0100ff0100000000, + 0x0100ff01000001ff, 0x0100ff0100010001, 0x0100ff0100010100, 0x0100ff0101ff0000, + 0x0100ff01010000ff, 0x0100ff0101000001, 0x0100ff0101010100, 0x010000ffffffff00, + 0x010000ffffff00ff, 0x010000ffffff0001, 0x010000ffff00ffff, 0x010000ffff000000, + 0x010000ffff0001ff, 0x010000ffff010001, 0x010000ff00ffffff, 0x010000ff00ff0101, + 0x010000ff0000ff00, 0x010000ff000000ff, 0x010000ff00000000, 0x010000ff00000001, + 0x010000ff000001ff, 0x010000ff00000100, 0x010000ff0001ffff, 0x010000ff0001ff00, + 0x010000ff0001ff01, 0x010000ff00010000, 0x010000ff01ff00ff, 0x010000ff01ff0001, + 0x010000ff0100ff01, 0x010000ff010000ff, 0x010000ff01000000, 0x010000ff010001ff, + 0x010000ff0101ff00, 0x010000ff01010100, 0x01000000ffffffff, 0x01000000ffff0000, + 0x01000000ffff01ff, 0x01000000ffff0101, 0x01000000ff00ffff, 0x01000000ff00ff00, + 0x01000000ff0000ff, 0x01000000ff000000, 0x01000000ff000001, 0x01000000ff000100, + 0x01000000ff01ff00, 0x01000000ff010000, 0x01000000ff010100, 0x01000000ff010101, + 0x0100000000ffff00, 0x0100000000ff00ff, 0x0100000000ff0000, 0x0100000000ff0001, + 0x0100000000ff0100, 0x010000000000ffff, 0x010000000000ff00, 0x010000000000ff01, + 0x01000000000000ff, 0x0100000000000000, 0x0100000000000001, 0x01000000000001ff, + 0x0100000000000100, 0x0100000000000101, 0x010000000001ff00, 0x01000000000100ff, + 0x0100000000010000, 0x0100000000010001, 0x0100000000010100, 0x0100000001ffff00, + 0x0100000001ff0000, 0x0100000001ff01ff, 0x010000000100ff00, 0x010000000100ff01, + 0x01000000010000ff, 0x0100000001000000, 0x0100000001000001, 0x0100000001000100, + 0x0100000001000101, 0x010000000101ffff, 0x010000000101ff01, 0x0100000001010000, + 0x01000000010101ff, 0x0100000001010101, 0x01000001ffffff00, 0x01000001ffff00ff, + 0x01000001ff00ffff, 0x01000001ff000000, 0x01000001ff000100, 0x01000001ff01ffff, + 0x01000001ff010001, 0x01000001ff010100, 0x0100000100ff0000, 0x0100000100ff01ff, + 0x0100000100ff0100, 0x010000010000ff00, 0x010000010000ff01, 0x0100000100000000, + 0x0100000100000001, 0x0100000100000100, 0x0100000100010000, 0x01000001000101ff, + 0x0100000101ffff01, 0x0100000101ff00ff, 0x0100000101ff0100, 0x0100000101ff0101, + 0x010000010100ff01, 0x01000001010000ff, 0x0100000101000000, 0x01000001010100ff, + 0x0100000101010001, 0x0100000101010100, 0x010001ffffff0000, 0x010001ffff000001, + 0x010001ffff000100, 0x010001ffff010000, 0x010001ff00ffff00, 0x010001ff00ff0001, + 0x010001ff0000ffff, 0x010001ff0000ff01, 0x010001ff00000000, 0x010001ff00000001, + 0x010001ff00000101, 0x010001ff000100ff, 0x010001ff00010000, 0x010001ff01ff0000, + 0x010001ff0100ff00, 0x010001ff01000001, 0x010001ff01000100, 0x010001ff01010000, + 0x01000100ffff00ff, 0x01000100ffff0001, 0x01000100ffff0100, 0x01000100ff00ffff, + 0x01000100ff00ff01, 0x01000100ff000000, 0x01000100ff0001ff, 0x01000100ff000101, + 0x01000100ff01ffff, 0x01000100ff01ff00, 0x01000100ff0100ff, 0x01000100ff010001, + 0x0100010000ffffff, 0x0100010000ffff01, 0x0100010000ff0000, 0x0100010000ff01ff, + 0x0100010000ff0101, 0x010001000000ff00, 0x01000100000000ff, 0x0100010000000000, + 0x0100010000000001, 0x0100010000000100, 0x010001000001ff01, 0x0100010000010000, + 0x0100010000010001, 0x0100010000010101, 0x0100010001ffff00, 0x0100010001ff00ff, + 0x010001000100ffff, 0x010001000100ff01, 0x0100010001000000, 0x0100010001000101, + 0x010001000101ff00, 0x0100010001010001, 0x01000101ffff0000, 0x01000101ff000000, + 0x01000101ff010000, 0x0100010100ff00ff, 0x0100010100ff0001, 0x0100010100ff0100, + 0x010001010000ffff, 0x0100010100000000, 0x01000101000001ff, 0x010001010001ff00, + 0x0100010101ff0000, 0x010001010100ff00, 0x01000101010000ff, 0x0100010101000000, + 0x0100010101000001, 0x0101ffffffffffff, 0x0101ffffffffff01, 0x0101ffffffff01ff, + 0x0101ffffffff0101, 0x0101ffffff000000, 0x0101ffffff01ffff, 0x0101ffffff01ff01, + 0x0101ffffff0101ff, 0x0101ffffff010101, 0x0101ffff00ff0000, 0x0101ffff0000ff00, + 0x0101ffff000000ff, 0x0101ffff00000001, 0x0101ffff00000100, 0x0101ffff01ffffff, + 0x0101ffff01ffff01, 0x0101ffff01ff01ff, 0x0101ffff01ff0101, 0x0101ffff01000000, + 0x0101ffff0101ffff, 0x0101ffff0101ff01, 0x0101ffff010101ff, 0x0101ffff01010101, + 0x0101ff00ffff0000, 0x0101ff00ffff0100, 0x0101ff00ff00ff00, 0x0101ff00ff0000ff, + 0x0101ff00ff000001, 0x0101ff00ff000100, 0x0101ff00ff000101, 0x0101ff0000ff0001, + 0x0101ff0000ff0100, 0x0101ff000000ff00, 0x0101ff0000000000, 0x0101ff00000001ff, + 0x0101ff0000000101, 0x0101ff000001ff00, 0x0101ff00000100ff, 0x0101ff0001ff0000, + 0x0101ff000100ffff, 0x0101ff000100ff01, 0x0101ff0001000001, 0x0101ff0001000100, + 0x0101ff01ffffff01, 0x0101ff01ffff01ff, 0x0101ff01ffff0101, 0x0101ff01ff00ffff, + 0x0101ff01ff000100, 0x0101ff01ff01ff01, 0x0101ff01ff0101ff, 0x0101ff01ff010101, + 0x0101ff0100ff0000, 0x0101ff010000ff00, 0x0101ff0100000001, 0x0101ff0100000100, + 0x0101ff0100010000, 0x0101ff0101ffffff, 0x0101ff0101ffff01, 0x0101ff0101ff01ff, + 0x0101ff0101ff0101, 0x0101ff0101000000, 0x0101ff010101ffff, 0x0101ff010101ff01, + 0x0101ff01010101ff, 0x0101ff0101010101, 0x010100ffff000100, 0x010100ffff010000, + 0x010100ff00ffff00, 0x010100ff00ff00ff, 0x010100ff0000ffff, 0x010100ff000000ff, + 0x010100ff00000000, 0x010100ff000001ff, 0x010100ff00000101, 0x010100ff0001ff00, + 0x010100ff00010000, 0x010100ff00010001, 0x010100ff000101ff, 0x010100ff00010100, + 0x010100ff01ff0000, 0x01010000ffff0001, 0x01010000ffff0100, 0x01010000ff00ffff, + 0x01010000ff00ff01, 0x01010000ff000000, 0x01010000ff0001ff, 0x01010000ff010001, + 0x01010000ff010100, 0x0101000000ffff01, 0x0101000000ff0000, 0x010100000000ff00, + 0x01010000000000ff, 0x0101000000000000, 0x0101000000000001, 0x0101000000000100, + 0x0101000000010000, 0x0101000000010101, 0x0101000001ffff00, 0x0101000001ff00ff, + 0x0101000001ff0000, 0x0101000001ff0001, 0x0101000001ff0100, 0x010100000100ff01, + 0x0101000001000000, 0x01010000010001ff, 0x01010001ffff0000, 0x01010001ff00ff00, + 0x01010001ff000001, 0x01010001ff000101, 0x01010001ff01ff00, 0x01010001ff010000, + 0x0101000100ff00ff, 0x0101000100ff0001, 0x0101000100ff0101, 0x010100010000ff01, + 0x0101000100000000, 0x0101000100000001, 0x01010001000001ff, 0x010100010001ffff, + 0x010100010001ff01, 0x0101000101ff0001, 0x010100010100ffff, 0x0101000101000000, + 0x0101000101000001, 0x0101000101000100, 0x010100010101ff00, 0x01010001010100ff, + 0x0101000101010001, 0x010101ffffffffff, 0x010101ffffffff01, 0x010101ffffff01ff, + 0x010101ffffff0101, 0x010101ffff01ffff, 0x010101ffff01ff01, 0x010101ffff0101ff, + 0x010101ffff010101, 0x010101ff0000ff00, 0x010101ff000000ff, 0x010101ff00000001, + 0x010101ff00000100, 0x010101ff01ffffff, 0x010101ff01ffff01, 0x010101ff01ff01ff, + 0x010101ff01ff0101, 0x010101ff01000000, 0x010101ff0101ffff, 0x010101ff0101ff01, + 0x010101ff010101ff, 0x010101ff01010101, 0x01010100ffff0000, 0x01010100ff0000ff, + 0x01010100ff000100, 0x01010100ff01ff00, 0x01010100ff010000, 0x0101010000ffff00, + 0x010101000000ffff, 0x0101010000000000, 0x0101010000000101, 0x010101000001ff00, + 0x0101010000010001, 0x0101010000010100, 0x010101000100ffff, 0x0101010001000001, + 0x01010101ffffffff, 0x01010101ffffff01, 0x01010101ffff01ff, 0x01010101ffff0101, + 0x01010101ff01ffff, 0x01010101ff01ff01, 0x01010101ff0101ff, 0x01010101ff010101, + 0x010101010000ff00, 0x01010101000000ff, 0x0101010100000001, 0x0101010101ffffff, + 0x0101010101ffff01, 0x0101010101ff01ff, 0x0101010101ff0101, 0x0101010101000000, + 0x010101010101ffff, 0x010101010101ff01, 0x01010101010101ff, 0x0101010101010101, +GGML_TABLE_END() +#else +GGML_TABLE_BEGIN(uint32_t, iq1s_grid_gpu, NGRID_IQ1S) + 0x00000000, 0x00000002, 0x00000101, 0x00000200, 0x00000202, 0x00010001, 0x00010101, 0x00020000, + 0x00020002, 0x00020200, 0x00020202, 0x01000101, 0x01010001, 0x01010100, 0x01010102, 0x01020101, + 0x02000000, 0x02000002, 0x02000200, 0x02000202, 0x02010101, 0x02020000, 0x02020002, 0x02020200, + 0x02020202, 0x00000110, 0x00000111, 0x00010011, 0x00010110, 0x00010112, 0x00010211, 0x00010212, + 0x00020111, 0x01000011, 0x01000112, 0x01000211, 0x01010012, 0x01010111, 0x01010212, 0x01020011, + 0x01020110, 0x01020112, 0x01020210, 0x02000111, 0x02010011, 0x02010110, 0x02010112, 0x02020111, + 0x00000020, 0x00000022, 0x00000220, 0x00000222, 0x00010121, 0x00020020, 0x00020022, 0x00020220, + 0x00020222, 0x01000121, 0x01010021, 0x01010221, 0x01020120, 0x01020221, 0x02000020, 0x02000022, + 0x02000220, 0x02000222, 0x02010021, 0x02010121, 0x02010221, 0x02020020, 0x02020022, 0x02020220, + 0x02020222, 0x00011001, 0x00011100, 0x00011102, 0x00021101, 0x01001001, 0x01001201, 0x01011101, + 0x01011202, 0x01021100, 0x01021101, 0x02011001, 0x02011201, 0x02021101, 0x00001011, 0x00001110, + 0x00001111, 0x00001112, 0x00011111, 0x00011210, 0x00011212, 0x00021211, 0x01001010, 0x01001111, + 0x01001212, 0x01011010, 0x01011011, 0x01011110, 0x01011111, 0x01011112, 0x01011211, 0x01021010, + 0x01021012, 0x01021111, 0x01021210, 0x01021212, 0x02001011, 0x02011011, 0x02011111, 0x02011210, + 0x02011212, 0x02021011, 0x02021110, 0x02021111, 0x02021112, 0x02021211, 0x00011120, 0x00011221, + 0x01001021, 0x01001120, 0x01011020, 0x01011022, 0x01011121, 0x01011220, 0x01021020, 0x01021021, + 0x01021122, 0x01021221, 0x02001121, 0x02011021, 0x02011120, 0x02011221, 0x00002000, 0x00002002, + 0x00002200, 0x00002202, 0x00012101, 0x00022000, 0x00022002, 0x00022200, 0x00022202, 0x01002101, + 0x01012001, 0x01012102, 0x01022101, 0x02002000, 0x02002002, 0x02002200, 0x02002202, 0x02012101, + 0x02022000, 0x02022002, 0x02022200, 0x02022202, 0x00002111, 0x00012011, 0x00012110, 0x00012211, + 0x00022110, 0x00022111, 0x01002011, 0x01012010, 0x01012011, 0x01012111, 0x01022011, 0x01022110, + 0x01022211, 0x02012011, 0x02012110, 0x02012112, 0x02012211, 0x02022111, 0x00002020, 0x00002022, + 0x00002220, 0x00002222, 0x00012121, 0x00022020, 0x00022022, 0x00022220, 0x00022222, 0x01002121, + 0x01012021, 0x01012221, 0x01022021, 0x01022121, 0x02002020, 0x02002022, 0x02002121, 0x02002220, + 0x02002222, 0x02012121, 0x02022020, 0x02022022, 0x02022220, 0x02022222, 0x00110000, 0x00110001, + 0x00110100, 0x00110201, 0x00120100, 0x00120101, 0x01100001, 0x01100100, 0x01110000, 0x01110101, + 0x01110200, 0x01120001, 0x01120100, 0x01120101, 0x01120201, 0x02110001, 0x02110100, 0x02110102, + 0x02120001, 0x02120101, 0x00100011, 0x00100110, 0x00100112, 0x00100211, 0x00110010, 0x00110012, + 0x00110111, 0x00110210, 0x00120011, 0x00120110, 0x00120211, 0x01100111, 0x01100212, 0x01110010, + 0x01110011, 0x01110012, 0x01110110, 0x01110111, 0x01110112, 0x01110211, 0x01120010, 0x01120111, + 0x02100110, 0x02110012, 0x02110111, 0x02120011, 0x02120110, 0x00110021, 0x00110120, 0x00110122, + 0x00120121, 0x01100020, 0x01100122, 0x01100221, 0x01110022, 0x01110121, 0x01110220, 0x01110222, + 0x01120120, 0x01120122, 0x02100121, 0x02110021, 0x02110120, 0x02110122, 0x02120121, 0x00101001, + 0x00101102, 0x00101201, 0x00111100, 0x00111101, 0x00111200, 0x00111201, 0x00121001, 0x00121102, + 0x01101001, 0x01101101, 0x01101102, 0x01101200, 0x01101202, 0x01111001, 0x01111100, 0x01111101, + 0x01111102, 0x01111201, 0x01121002, 0x01121101, 0x01121200, 0x02101100, 0x02101201, 0x02111000, + 0x02111100, 0x02111101, 0x02111200, 0x02111201, 0x02111202, 0x02121001, 0x02121100, 0x02121101, + 0x02121201, 0x00101012, 0x00101111, 0x00101212, 0x00111011, 0x00111110, 0x00111111, 0x00111112, + 0x00111211, 0x00121010, 0x00121012, 0x00121111, 0x00121210, 0x00121212, 0x01101011, 0x01101110, + 0x01101111, 0x01101112, 0x01111011, 0x01111012, 0x01111110, 0x01111111, 0x01111112, 0x01111211, + 0x01111212, 0x01121011, 0x01121110, 0x01121111, 0x01121112, 0x01121211, 0x02101010, 0x02101012, + 0x02101110, 0x02101111, 0x02101210, 0x02101212, 0x02111010, 0x02111011, 0x02111110, 0x02111111, + 0x02111112, 0x02111211, 0x02111212, 0x02121010, 0x02121012, 0x02121111, 0x00101021, 0x00101120, + 0x00101121, 0x00101122, 0x00111121, 0x00111122, 0x00111220, 0x00111222, 0x00121021, 0x00121122, + 0x01101020, 0x01101022, 0x01101120, 0x01101121, 0x01101220, 0x01101222, 0x01111021, 0x01111121, + 0x01111122, 0x01111220, 0x01111221, 0x01121021, 0x01121120, 0x01121121, 0x01121220, 0x01121221, + 0x01121222, 0x02101122, 0x02101222, 0x02111022, 0x02111121, 0x02121120, 0x02121221, 0x00112001, + 0x00112102, 0x00122101, 0x01102001, 0x01102100, 0x01102102, 0x01102201, 0x01112000, 0x01112101, + 0x01112200, 0x01112202, 0x01122000, 0x01122001, 0x01122100, 0x01122102, 0x01122201, 0x02102101, + 0x02112001, 0x02112100, 0x02122101, 0x00112010, 0x00112012, 0x00112111, 0x00112212, 0x00122011, + 0x00122111, 0x01102012, 0x01102110, 0x01102111, 0x01102210, 0x01112011, 0x01112110, 0x01112111, + 0x01112112, 0x01112211, 0x01112212, 0x01122010, 0x01122111, 0x01122212, 0x02102211, 0x02112011, + 0x02112012, 0x02112111, 0x02112210, 0x02122011, 0x02122112, 0x02122211, 0x00102221, 0x00112122, + 0x00122120, 0x00122122, 0x01102120, 0x01102122, 0x01102221, 0x01112020, 0x01112022, 0x01112121, + 0x01112220, 0x01122021, 0x01122122, 0x01122221, 0x02102121, 0x02112021, 0x02112122, 0x02112222, + 0x00200000, 0x00200002, 0x00200200, 0x00200202, 0x00210101, 0x00220000, 0x00220002, 0x00220101, + 0x00220200, 0x00220202, 0x01200101, 0x01210001, 0x01210201, 0x01220001, 0x01220101, 0x02200000, + 0x02200002, 0x02200200, 0x02200202, 0x02210101, 0x02220000, 0x02220002, 0x02220101, 0x02220200, + 0x02220202, 0x00200111, 0x00210011, 0x00210110, 0x00210211, 0x00220111, 0x01200012, 0x01200110, + 0x01200211, 0x01210111, 0x01210210, 0x01210212, 0x01220011, 0x01220110, 0x01220111, 0x01220112, + 0x02200111, 0x02210010, 0x02210112, 0x02210211, 0x02220111, 0x00200021, 0x00200220, 0x00200222, + 0x00210021, 0x00210121, 0x00220020, 0x00220022, 0x00220220, 0x00220222, 0x01200121, 0x01210021, + 0x01210122, 0x01210221, 0x01220121, 0x02200021, 0x02200220, 0x02200222, 0x02210021, 0x02210121, + 0x02220020, 0x02220022, 0x02220220, 0x02220222, 0x00201101, 0x00211100, 0x00211102, 0x00211201, + 0x00221101, 0x01201100, 0x01201101, 0x01201102, 0x01201201, 0x01211002, 0x01211101, 0x01211200, + 0x01211202, 0x01221102, 0x02201101, 0x02211001, 0x02211100, 0x02211201, 0x02221001, 0x02221101, + 0x00201211, 0x00211111, 0x00221011, 0x00221211, 0x01201010, 0x01201111, 0x01201210, 0x01211011, + 0x01211110, 0x01211111, 0x01211211, 0x01221012, 0x01221111, 0x01221210, 0x02201211, 0x02211010, + 0x02211110, 0x02211111, 0x02211210, 0x02211212, 0x02221011, 0x02221110, 0x02221112, 0x02221211, + 0x00201121, 0x00211020, 0x00211022, 0x00211221, 0x00221121, 0x01201021, 0x01201221, 0x01211121, + 0x01221020, 0x01221021, 0x01221221, 0x02201120, 0x02201122, 0x02211020, 0x02211222, 0x00202000, + 0x00202002, 0x00202200, 0x00202202, 0x00212101, 0x00222000, 0x00222002, 0x00222200, 0x00222202, + 0x01202101, 0x01212001, 0x01212100, 0x01222101, 0x02202000, 0x02202002, 0x02202200, 0x02202202, + 0x02222000, 0x02222002, 0x02222200, 0x02222202, 0x00202211, 0x00212011, 0x00212110, 0x00212211, + 0x00222111, 0x01202112, 0x01202211, 0x01212012, 0x01212111, 0x01222011, 0x01222110, 0x01222112, + 0x01222211, 0x02202111, 0x02212010, 0x02212112, 0x02212211, 0x02222110, 0x02222111, 0x00202020, + 0x00202022, 0x00202220, 0x00202222, 0x00222020, 0x00222022, 0x00222220, 0x00222222, 0x01202121, + 0x01212021, 0x01212122, 0x01212221, 0x01222121, 0x02202020, 0x02202022, 0x02202220, 0x02202222, + 0x02212121, 0x02222020, 0x02222022, 0x02222220, 0x02222222, 0x10000101, 0x10010001, 0x10010102, + 0x10020101, 0x11000201, 0x11010002, 0x11010101, 0x11010200, 0x11010202, 0x11020001, 0x11020100, + 0x11020102, 0x12010100, 0x12010201, 0x12020001, 0x12020102, 0x10000010, 0x10000011, 0x10000110, + 0x10000112, 0x10000211, 0x10010012, 0x10010111, 0x10010112, 0x10010210, 0x10010212, 0x10020011, + 0x10020112, 0x10020211, 0x11000111, 0x11000210, 0x11000212, 0x11010011, 0x11010110, 0x11010111, + 0x11010112, 0x11010211, 0x11010212, 0x11020111, 0x11020210, 0x11020212, 0x12000011, 0x12000110, + 0x12000112, 0x12010010, 0x12010012, 0x12010111, 0x12020010, 0x12020011, 0x12020012, 0x10000121, + 0x10010021, 0x10010120, 0x10010122, 0x10020121, 0x11000021, 0x11010022, 0x11010121, 0x11010222, + 0x11020120, 0x11020221, 0x12000221, 0x12010120, 0x12020121, 0x10001001, 0x10011101, 0x10011201, + 0x10021201, 0x11001101, 0x11001200, 0x11001202, 0x11011001, 0x11011100, 0x11011101, 0x11011102, + 0x11021001, 0x11021002, 0x11021101, 0x11021200, 0x11021202, 0x12001001, 0x12001102, 0x12001201, + 0x12011000, 0x12011002, 0x12011101, 0x12021000, 0x12021001, 0x12021201, 0x10001011, 0x10001012, + 0x10001111, 0x10001212, 0x10011011, 0x10011110, 0x10011111, 0x10011112, 0x10011211, 0x10021010, + 0x10021111, 0x10021212, 0x11001011, 0x11001110, 0x11001111, 0x11001112, 0x11001211, 0x11011010, + 0x11011011, 0x11011110, 0x11011111, 0x11011112, 0x11011210, 0x11011211, 0x11021011, 0x11021110, + 0x11021111, 0x11021112, 0x11021211, 0x12001012, 0x12001110, 0x12001111, 0x12001210, 0x12011011, + 0x12011110, 0x12011111, 0x12011112, 0x12011211, 0x12011212, 0x12021111, 0x12021210, 0x12021212, + 0x10001021, 0x10001121, 0x10001221, 0x10011120, 0x10011121, 0x10011220, 0x10011222, 0x10021021, + 0x10021120, 0x10021221, 0x11001020, 0x11001022, 0x11001121, 0x11001220, 0x11011020, 0x11011021, + 0x11011022, 0x11011121, 0x11011122, 0x11011221, 0x11021022, 0x11021121, 0x11021220, 0x12001021, + 0x12001121, 0x12001222, 0x12011120, 0x12011121, 0x12021021, 0x12021120, 0x12021122, 0x10002101, + 0x10012001, 0x10012101, 0x10012202, 0x10022101, 0x11002002, 0x11002201, 0x11012000, 0x11012101, + 0x11012200, 0x11022001, 0x11022100, 0x11022102, 0x11022201, 0x12002101, 0x12012001, 0x12012100, + 0x12012102, 0x12012201, 0x12022101, 0x10002011, 0x10002111, 0x10002112, 0x10002212, 0x10012010, + 0x10012110, 0x10012111, 0x10012210, 0x10022011, 0x10022110, 0x10022112, 0x11002010, 0x11002111, + 0x11002212, 0x11012011, 0x11012012, 0x11012110, 0x11012111, 0x11012112, 0x11012211, 0x11022010, + 0x11022012, 0x11022111, 0x11022112, 0x11022212, 0x12002112, 0x12002211, 0x12012012, 0x12012111, + 0x12012112, 0x12012210, 0x12022011, 0x12022110, 0x12022112, 0x12022211, 0x10012122, 0x11002120, + 0x11002122, 0x11002221, 0x11012121, 0x11012220, 0x11012222, 0x11022120, 0x11022221, 0x12012120, + 0x12022121, 0x10100001, 0x10100100, 0x10100101, 0x10100102, 0x10100201, 0x10110002, 0x10110101, + 0x10110202, 0x10120001, 0x10120100, 0x10120201, 0x11100000, 0x11100101, 0x11100200, 0x11110001, + 0x11110100, 0x11110101, 0x11110102, 0x11110201, 0x11120101, 0x11120200, 0x12100102, 0x12100201, + 0x12110101, 0x12110200, 0x12120000, 0x12120001, 0x12120102, 0x12120201, 0x10100111, 0x10100210, + 0x10100211, 0x10100212, 0x10110011, 0x10110110, 0x10110111, 0x10110112, 0x10110210, 0x10110211, + 0x10120010, 0x10120111, 0x10120112, 0x10120210, 0x10120212, 0x11100011, 0x11100110, 0x11100111, + 0x11100112, 0x11100211, 0x11110010, 0x11110011, 0x11110012, 0x11110110, 0x11110111, 0x11110112, + 0x11110210, 0x11110211, 0x11110212, 0x11120011, 0x11120110, 0x11120111, 0x11120112, 0x11120211, + 0x12100012, 0x12100111, 0x12110011, 0x12110110, 0x12110111, 0x12110112, 0x12110211, 0x12120010, + 0x12120111, 0x12120212, 0x10100021, 0x10100122, 0x10110022, 0x10110121, 0x10110222, 0x10120021, + 0x10120120, 0x11100022, 0x11100121, 0x11100222, 0x11110021, 0x11110120, 0x11110121, 0x11110122, + 0x11110221, 0x11120022, 0x11120121, 0x12100121, 0x12110020, 0x12110022, 0x12110121, 0x12110221, + 0x12110222, 0x12120120, 0x10101100, 0x10101101, 0x10111001, 0x10111100, 0x10111101, 0x10111102, + 0x10111200, 0x10111201, 0x10121001, 0x10121101, 0x10121200, 0x10121202, 0x11101001, 0x11101100, + 0x11101101, 0x11101102, 0x11101201, 0x11101202, 0x11111000, 0x11111001, 0x11111100, 0x11111101, + 0x11111102, 0x11111200, 0x11111201, 0x11111202, 0x11121001, 0x11121002, 0x11121100, 0x11121101, + 0x11121102, 0x11121201, 0x12101000, 0x12101200, 0x12101202, 0x12111001, 0x12111100, 0x12111101, + 0x12111102, 0x12111201, 0x12121001, 0x12121100, 0x12121101, 0x12121202, 0x10101011, 0x10101012, + 0x10101110, 0x10101111, 0x10101112, 0x10101211, 0x10111010, 0x10111011, 0x10111012, 0x10111110, + 0x10111111, 0x10111112, 0x10111211, 0x10111212, 0x10121011, 0x10121110, 0x10121111, 0x10121112, + 0x10121211, 0x11101010, 0x11101011, 0x11101012, 0x11101110, 0x11101111, 0x11101112, 0x11101210, + 0x11101211, 0x11111010, 0x11111011, 0x11111012, 0x11111110, 0x11111111, 0x11111112, 0x11111210, + 0x11111211, 0x11111212, 0x11121010, 0x11121011, 0x11121110, 0x11121111, 0x11121112, 0x11121210, + 0x11121211, 0x11121212, 0x12101011, 0x12101110, 0x12101111, 0x12101211, 0x12101212, 0x12111010, + 0x12111011, 0x12111110, 0x12111111, 0x12111112, 0x12111210, 0x12111211, 0x12121011, 0x12121110, + 0x12121111, 0x12121112, 0x12121211, 0x10101020, 0x10101021, 0x10101022, 0x10101120, 0x10101122, + 0x10101220, 0x10101221, 0x10111021, 0x10111120, 0x10111121, 0x10111220, 0x10111221, 0x10121020, + 0x10121021, 0x10121022, 0x10121120, 0x10121121, 0x10121122, 0x10121220, 0x10121221, 0x11101021, + 0x11101121, 0x11101122, 0x11101220, 0x11101221, 0x11101222, 0x11111020, 0x11111021, 0x11111022, + 0x11111120, 0x11111121, 0x11111122, 0x11111220, 0x11111221, 0x11111222, 0x11121021, 0x11121120, + 0x11121121, 0x11121221, 0x12101022, 0x12101121, 0x12101122, 0x12101220, 0x12101221, 0x12101222, + 0x12111021, 0x12111121, 0x12111222, 0x12121022, 0x12121121, 0x12121122, 0x12121220, 0x12121221, + 0x10102100, 0x10102101, 0x10102102, 0x10102201, 0x10112000, 0x10112101, 0x10112200, 0x10122001, + 0x10122202, 0x11102101, 0x11102200, 0x11102202, 0x11112001, 0x11112100, 0x11112101, 0x11112102, + 0x11112200, 0x11112201, 0x11122000, 0x11122002, 0x11122100, 0x11122101, 0x12102002, 0x12102201, + 0x12112000, 0x12112002, 0x12112101, 0x12112200, 0x12122001, 0x12122201, 0x10102011, 0x10102012, + 0x10102111, 0x10102212, 0x10112011, 0x10112110, 0x10112111, 0x10112112, 0x10112211, 0x10122111, + 0x11102011, 0x11102110, 0x11102111, 0x11102112, 0x11102211, 0x11112010, 0x11112011, 0x11112012, + 0x11112110, 0x11112111, 0x11112112, 0x11112210, 0x11112211, 0x11112212, 0x11122011, 0x11122110, + 0x11122111, 0x11122112, 0x11122211, 0x12102011, 0x12102111, 0x12102211, 0x12112011, 0x12112110, + 0x12112111, 0x12112112, 0x12112210, 0x12112211, 0x12122111, 0x10102120, 0x10102220, 0x10112121, + 0x10112222, 0x10122020, 0x10122121, 0x10122122, 0x10122221, 0x11102121, 0x11102220, 0x11102221, + 0x11112021, 0x11112121, 0x11112122, 0x11112220, 0x11112221, 0x11122022, 0x11122121, 0x11122220, + 0x11122222, 0x12102021, 0x12102222, 0x12112022, 0x12112121, 0x12112122, 0x12112220, 0x12112222, + 0x12122021, 0x10200101, 0x10210100, 0x10210102, 0x10210201, 0x10220101, 0x11200100, 0x11210000, + 0x11210101, 0x11210102, 0x11210200, 0x11210202, 0x11220001, 0x11220100, 0x11220102, 0x11220201, + 0x12200001, 0x12210102, 0x12220101, 0x10200011, 0x10200110, 0x10200112, 0x10200211, 0x10210012, + 0x10210111, 0x10220011, 0x10220012, 0x10220112, 0x10220211, 0x11200111, 0x11200211, 0x11210011, + 0x11210111, 0x11210112, 0x11210211, 0x11220111, 0x11220112, 0x11220212, 0x12200110, 0x12200212, + 0x12210012, 0x12210111, 0x12220011, 0x12220112, 0x12220211, 0x10210021, 0x10210122, 0x10210221, + 0x11200020, 0x11200021, 0x11200122, 0x11210121, 0x11210122, 0x11210220, 0x11220020, 0x12200121, + 0x12210021, 0x12210122, 0x12220121, 0x10211001, 0x10211002, 0x10211101, 0x10211102, 0x10211202, + 0x10221001, 0x10221102, 0x10221201, 0x11201000, 0x11201002, 0x11201101, 0x11201200, 0x11201202, + 0x11211001, 0x11211100, 0x11211101, 0x11211102, 0x11211201, 0x11211202, 0x11221000, 0x11221002, + 0x11221101, 0x12201100, 0x12201101, 0x12201201, 0x12211000, 0x12211002, 0x12211100, 0x12211101, + 0x12211102, 0x12211200, 0x12211202, 0x12221001, 0x12221100, 0x12221201, 0x10201111, 0x10201210, + 0x10201212, 0x10211011, 0x10211111, 0x10211112, 0x10211211, 0x11201110, 0x11201111, 0x11201112, + 0x11201211, 0x11211010, 0x11211011, 0x11211110, 0x11211111, 0x11211112, 0x11211211, 0x11221011, + 0x11221110, 0x11221111, 0x11221112, 0x11221211, 0x12201112, 0x12201211, 0x12201212, 0x12211011, + 0x12211111, 0x12211112, 0x12211211, 0x12211212, 0x12221012, 0x12221111, 0x12221112, 0x12221210, + 0x10201022, 0x10201221, 0x10211121, 0x10221020, 0x10221122, 0x10221220, 0x10221221, 0x11201020, + 0x11201121, 0x11201220, 0x11201222, 0x11211021, 0x11211120, 0x11211121, 0x11211122, 0x11211220, + 0x11211222, 0x11221020, 0x11221121, 0x11221220, 0x12201020, 0x12201022, 0x12201121, 0x12201222, + 0x12211120, 0x12211122, 0x12211220, 0x12211221, 0x12221020, 0x12221120, 0x12221122, 0x12221222, + 0x10212102, 0x10212201, 0x10222101, 0x11202001, 0x11212002, 0x11212101, 0x11212202, 0x11222001, + 0x11222201, 0x12202101, 0x12212001, 0x12212200, 0x12222102, 0x10202011, 0x10202110, 0x10212010, + 0x10212111, 0x10222011, 0x10222110, 0x10222112, 0x10222211, 0x11202010, 0x11202011, 0x11202111, + 0x11202112, 0x11202210, 0x11212011, 0x11212110, 0x11212111, 0x11212112, 0x11212211, 0x11222010, + 0x11222111, 0x11222212, 0x12202012, 0x12202110, 0x12202212, 0x12212111, 0x12222011, 0x12222110, + 0x12222111, 0x12222211, 0x10212021, 0x10212122, 0x10212220, 0x11202021, 0x11202120, 0x11202221, + 0x11212020, 0x11212121, 0x11212220, 0x11212222, 0x11222120, 0x11222121, 0x11222221, 0x12202122, + 0x12212120, 0x12212220, 0x12212222, 0x12222122, 0x20000000, 0x20000002, 0x20000200, 0x20000202, + 0x20020000, 0x20020002, 0x20020200, 0x20020202, 0x21000101, 0x21010000, 0x21010001, 0x21010100, + 0x21010102, 0x21010201, 0x21020101, 0x22000000, 0x22000002, 0x22000200, 0x22000202, 0x22010101, + 0x22020000, 0x22020002, 0x22020200, 0x22020202, 0x20000111, 0x20010011, 0x20010110, 0x20010112, + 0x20010211, 0x20020111, 0x21000011, 0x21000110, 0x21000211, 0x21010010, 0x21010012, 0x21010111, + 0x21010112, 0x21010210, 0x21010211, 0x21020110, 0x21020112, 0x21020211, 0x22000111, 0x22000211, + 0x22010110, 0x22010112, 0x22010211, 0x22020111, 0x20000020, 0x20000022, 0x20000220, 0x20000222, + 0x20010121, 0x20020020, 0x20020022, 0x20020220, 0x20020222, 0x21010021, 0x21010120, 0x21010221, + 0x21020121, 0x22000020, 0x22000022, 0x22000220, 0x22000222, 0x22010121, 0x22020020, 0x22020022, + 0x22020220, 0x22020222, 0x20011100, 0x20011201, 0x21001001, 0x21001100, 0x21011001, 0x21011101, + 0x21011202, 0x21021001, 0x21021100, 0x21021201, 0x22011100, 0x22011201, 0x20001011, 0x20001211, + 0x20011012, 0x20011111, 0x20011212, 0x20021112, 0x20021211, 0x21001010, 0x21001011, 0x21001111, + 0x21001210, 0x21011011, 0x21011110, 0x21011111, 0x21011112, 0x21011211, 0x21011212, 0x21021111, + 0x21021112, 0x21021210, 0x21021212, 0x22001011, 0x22001110, 0x22001112, 0x22001211, 0x22011010, + 0x22011012, 0x22011111, 0x22011210, 0x22021112, 0x20011021, 0x20011122, 0x20011221, 0x20021121, + 0x21001021, 0x21001120, 0x21001221, 0x21001222, 0x21011020, 0x21011121, 0x21011221, 0x21011222, + 0x21021021, 0x21021122, 0x21021222, 0x22001121, 0x22011021, 0x22011222, 0x22021120, 0x20002000, + 0x20002002, 0x20002200, 0x20002202, 0x20012101, 0x20022000, 0x20022002, 0x20022200, 0x20022202, + 0x21002001, 0x21002101, 0x21012001, 0x21012100, 0x21012201, 0x21022101, 0x21022201, 0x22002000, + 0x22002002, 0x22002200, 0x22002202, 0x22012101, 0x22022000, 0x22022002, 0x22022200, 0x22022202, + 0x20002111, 0x20002112, 0x20012011, 0x20012110, 0x20012112, 0x20022111, 0x21002011, 0x21002110, + 0x21002112, 0x21002211, 0x21012010, 0x21012012, 0x21012111, 0x21012212, 0x21022011, 0x21022110, + 0x22002111, 0x22012112, 0x22012211, 0x22022111, 0x20002020, 0x20002022, 0x20002220, 0x20002222, + 0x20012121, 0x20022020, 0x20022022, 0x20022220, 0x20022222, 0x21002121, 0x21012021, 0x21012120, + 0x21012122, 0x22002020, 0x22002022, 0x22002220, 0x22002222, 0x22012121, 0x22022020, 0x22022022, + 0x22022220, 0x22022222, 0x20100101, 0x20110001, 0x20110102, 0x20110200, 0x20110201, 0x20120101, + 0x21100001, 0x21100102, 0x21100201, 0x21110101, 0x21110200, 0x21110202, 0x21120201, 0x21120202, + 0x22100101, 0x22110001, 0x22110100, 0x22110102, 0x22110201, 0x22120101, 0x20100011, 0x20100110, + 0x20100112, 0x20100211, 0x20110010, 0x20110111, 0x20110210, 0x20110212, 0x20120011, 0x20120110, + 0x20120112, 0x20120211, 0x21100010, 0x21100111, 0x21110010, 0x21110011, 0x21110110, 0x21110111, + 0x21110112, 0x21110211, 0x21120012, 0x21120111, 0x22100110, 0x22100112, 0x22110012, 0x22110111, + 0x22110210, 0x22120011, 0x22120110, 0x22120112, 0x22120211, 0x20100121, 0x20110021, 0x20110120, + 0x20110221, 0x20120121, 0x21100120, 0x21100122, 0x21100221, 0x21110020, 0x21110022, 0x21110121, + 0x21110220, 0x21120122, 0x21120221, 0x22100121, 0x22110120, 0x22110122, 0x22120221, 0x20101001, + 0x20101100, 0x20101102, 0x20111000, 0x20111101, 0x20111200, 0x20121102, 0x21101000, 0x21101202, + 0x21111001, 0x21111100, 0x21111101, 0x21111102, 0x21111200, 0x21111201, 0x21121000, 0x21121001, + 0x21121002, 0x21121101, 0x22101100, 0x22101102, 0x22111002, 0x22111100, 0x22111101, 0x22111200, + 0x22121001, 0x22121201, 0x20101010, 0x20101111, 0x20101210, 0x20101212, 0x20111010, 0x20111011, + 0x20111110, 0x20111111, 0x20111112, 0x20111211, 0x20121011, 0x20121111, 0x20121211, 0x20121212, + 0x21101011, 0x21101110, 0x21101111, 0x21101112, 0x21101211, 0x21111010, 0x21111011, 0x21111012, + 0x21111110, 0x21111111, 0x21111112, 0x21111210, 0x21111211, 0x21111212, 0x21121011, 0x21121110, + 0x21121111, 0x21121112, 0x21121211, 0x22101011, 0x22101111, 0x22101210, 0x22111011, 0x22111012, + 0x22111110, 0x22111111, 0x22111112, 0x22111211, 0x22111212, 0x22121010, 0x22121012, 0x22121111, + 0x22121210, 0x22121212, 0x20101021, 0x20101120, 0x20111020, 0x20111121, 0x20111221, 0x20121020, + 0x20121122, 0x20121221, 0x21101121, 0x21101220, 0x21101221, 0x21111021, 0x21111022, 0x21111121, + 0x21111122, 0x21111221, 0x21121121, 0x21121220, 0x22101022, 0x22101120, 0x22101221, 0x22101222, + 0x22111022, 0x22111120, 0x22111121, 0x22121120, 0x22121122, 0x22121221, 0x20102101, 0x20112102, + 0x20112201, 0x20122101, 0x21102001, 0x21102102, 0x21112000, 0x21112002, 0x21112101, 0x21112102, + 0x21112202, 0x21122100, 0x21122101, 0x22102101, 0x22112001, 0x22112102, 0x22112201, 0x22122101, + 0x20102110, 0x20102112, 0x20102211, 0x20112010, 0x20112012, 0x20112111, 0x20112210, 0x20112212, + 0x20122010, 0x20122011, 0x20122110, 0x20122112, 0x21102010, 0x21102012, 0x21102111, 0x21102210, + 0x21102212, 0x21112011, 0x21112110, 0x21112111, 0x21112112, 0x21112211, 0x21122012, 0x21122111, + 0x21122112, 0x21122212, 0x22102011, 0x22102110, 0x22112010, 0x22112012, 0x22112111, 0x22112212, + 0x22122011, 0x22122112, 0x20102121, 0x20112121, 0x20122121, 0x21102120, 0x21102122, 0x21102221, + 0x21112020, 0x21112121, 0x21112220, 0x21122021, 0x22102121, 0x22112021, 0x22112120, 0x22112121, + 0x22112122, 0x20200000, 0x20200002, 0x20200200, 0x20200202, 0x20210101, 0x20220000, 0x20220002, + 0x20220200, 0x20220202, 0x21200101, 0x21210001, 0x21210100, 0x21210102, 0x21210201, 0x22200000, + 0x22200002, 0x22200200, 0x22200202, 0x22210101, 0x22220000, 0x22220002, 0x22220200, 0x22220202, + 0x20200111, 0x20200211, 0x20210011, 0x20210110, 0x20210112, 0x20210211, 0x20210212, 0x21200112, + 0x21200211, 0x21210011, 0x21210111, 0x21210210, 0x21210212, 0x21220011, 0x21220110, 0x22200111, + 0x22210010, 0x22210012, 0x22210112, 0x22210211, 0x20200022, 0x20200220, 0x20200222, 0x20210020, + 0x20210221, 0x20220022, 0x20220220, 0x20220222, 0x21200121, 0x21210021, 0x21210122, 0x21210221, + 0x21220121, 0x22200020, 0x22200022, 0x22200220, 0x22200222, 0x22210121, 0x22220020, 0x22220022, + 0x22220220, 0x22220222, 0x20211201, 0x20221101, 0x21201001, 0x21201100, 0x21211000, 0x21211100, + 0x21211101, 0x21211200, 0x21211202, 0x21221001, 0x21221101, 0x21221102, 0x21221200, 0x21221201, + 0x22201101, 0x20201112, 0x20201211, 0x20211010, 0x20211012, 0x20211111, 0x20211210, 0x20221112, + 0x20221211, 0x21201012, 0x21201111, 0x21211011, 0x21211110, 0x21211111, 0x21211112, 0x21211211, + 0x21221111, 0x21221212, 0x22201011, 0x22201110, 0x22201111, 0x22201112, 0x22201211, 0x22211012, + 0x22211111, 0x22211210, 0x20201121, 0x20211021, 0x20211122, 0x20211222, 0x20221021, 0x20221121, + 0x21201120, 0x21201122, 0x21201222, 0x21211022, 0x21211121, 0x21211122, 0x21211220, 0x21221020, + 0x21221022, 0x22201122, 0x22211020, 0x22211121, 0x22211122, 0x22211221, 0x22221021, 0x22221120, + 0x22221122, 0x20202000, 0x20202002, 0x20202200, 0x20202202, 0x20222000, 0x20222002, 0x20222200, + 0x20222202, 0x21212001, 0x21212100, 0x21212102, 0x21212201, 0x22202000, 0x22202002, 0x22202200, + 0x22202202, 0x22212101, 0x22222000, 0x22222002, 0x22222200, 0x22222202, 0x20202111, 0x20212110, + 0x20212211, 0x20222011, 0x20222111, 0x21202011, 0x21212010, 0x21212111, 0x21212212, 0x21222011, + 0x21222112, 0x21222211, 0x22212010, 0x22212112, 0x20202020, 0x20202022, 0x20202220, 0x20202222, + 0x20222020, 0x20222022, 0x20222220, 0x20222222, 0x21212021, 0x21212120, 0x21212122, 0x22202020, + 0x22202022, 0x22202220, 0x22202222, 0x22212121, 0x22222020, 0x22222022, 0x22222220, 0x22222222, +GGML_TABLE_END() +#endif + +#endif // GGML_COMMON_IMPL +#endif // GGML_COMMON_IMPL diff --git a/src/ggml-cuda.cu b/src/ggml-cuda.cu index 72bcec8cd..d1b5e52ba 100644 --- a/src/ggml-cuda.cu +++ b/src/ggml-cuda.cu @@ -2,6 +2,15 @@ #include "ggml.h" #include "ggml-backend-impl.h" +#if defined(GGML_USE_HIPBLAS) +#define GGML_COMMON_DECL_HIP +#define GGML_COMMON_IMPL_HIP +#else +#define GGML_COMMON_DECL_CUDA +#define GGML_COMMON_IMPL_CUDA +#endif +#include "ggml-common.h" + #include #include #include @@ -63,6 +72,7 @@ #define cudaEventCreateWithFlags hipEventCreateWithFlags #define cudaEventDisableTiming hipEventDisableTiming #define cudaEventRecord hipEventRecord +#define cudaEventSynchronize hipEventSynchronize #define cudaEvent_t hipEvent_t #define cudaEventDestroy hipEventDestroy #define cudaFree hipFree @@ -72,6 +82,7 @@ #define cudaGetDeviceProperties hipGetDeviceProperties #define cudaGetErrorString hipGetErrorString #define cudaGetLastError hipGetLastError +#define cudaLaunchHostFunc hipLaunchHostFunc #ifdef GGML_HIP_UMA #define cudaMalloc hipMallocManaged #define cudaMallocHost(ptr, size) hipHostMalloc(ptr, size) @@ -95,6 +106,7 @@ #define cudaStreamCreateWithFlags hipStreamCreateWithFlags #define cudaStreamFireAndForget hipStreamFireAndForget #define cudaStreamNonBlocking hipStreamNonBlocking +#define cudaStreamPerThread hipStreamPerThread #define cudaStreamSynchronize hipStreamSynchronize #define cudaStreamWaitEvent(stream, event, flags) hipStreamWaitEvent(stream, event, flags) #define cudaStream_t hipStream_t @@ -356,66 +368,6 @@ typedef void (*ggml_cuda_op_flatten_t)( const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst, const float * src0_dd, const float * src1_dd, float * dst_dd, cudaStream_t main_stream); -// QK = number of values after dequantization -// QR = QK / number of values before dequantization -// QI = number of 32 bit integers before dequantization - -#define QK4_0 32 -#define QR4_0 2 -#define QI4_0 (QK4_0 / (4 * QR4_0)) -typedef struct { - half d; // delta - uint8_t qs[QK4_0 / 2]; // nibbles / quants -} block_q4_0; -static_assert(sizeof(block_q4_0) == sizeof(ggml_fp16_t) + QK4_0 / 2, "wrong q4_0 block size/padding"); - -#define QK4_1 32 -#define QR4_1 2 -#define QI4_1 (QK4_1 / (4 * QR4_1)) -typedef struct { - half2 dm; // dm.x = delta, dm.y = min - uint8_t qs[QK4_1 / 2]; // nibbles / quants -} block_q4_1; -static_assert(sizeof(block_q4_1) == sizeof(ggml_fp16_t) * 2 + QK4_1 / 2, "wrong q4_1 block size/padding"); - -#define QK5_0 32 -#define QR5_0 2 -#define QI5_0 (QK5_0 / (4 * QR5_0)) -typedef struct { - half d; // delta - uint8_t qh[4]; // 5-th bit of quants - uint8_t qs[QK5_0 / 2]; // nibbles / quants -} block_q5_0; -static_assert(sizeof(block_q5_0) == sizeof(ggml_fp16_t) + sizeof(uint32_t) + QK5_0 / 2, "wrong q5_0 block size/padding"); - -#define QK5_1 32 -#define QR5_1 2 -#define QI5_1 (QK5_1 / (4 * QR5_1)) -typedef struct { - half2 dm; // dm.x = delta, dm.y = min - uint8_t qh[4]; // 5-th bit of quants - uint8_t qs[QK5_1 / 2]; // nibbles / quants -} block_q5_1; -static_assert(sizeof(block_q5_1) == 2 * sizeof(ggml_fp16_t) + sizeof(uint32_t) + QK5_1 / 2, "wrong q5_1 block size/padding"); - -#define QK8_0 32 -#define QR8_0 1 -#define QI8_0 (QK8_0 / (4 * QR8_0)) -typedef struct { - half d; // delta - int8_t qs[QK8_0]; // quants -} block_q8_0; -static_assert(sizeof(block_q8_0) == sizeof(ggml_fp16_t) + QK8_0, "wrong q8_0 block size/padding"); - -#define QK8_1 32 -#define QR8_1 1 -#define QI8_1 (QK8_1 / (4 * QR8_1)) -typedef struct { - half2 ds; // ds.x = delta, ds.y = sum - int8_t qs[QK8_0]; // quants -} block_q8_1; -static_assert(sizeof(block_q8_1) == 2*sizeof(ggml_fp16_t) + QK8_0, "wrong q8_1 block size/padding"); - typedef float (*vec_dot_q_cuda_t)(const void * __restrict__ vbq, const block_q8_1 * __restrict__ bq8_1, const int & iqs); typedef void (*allocate_tiles_cuda_t)(int ** x_ql, half2 ** x_dm, int ** x_qh, int ** x_sc); typedef void (*load_tiles_cuda_t)( @@ -425,174 +377,6 @@ typedef float (*vec_dot_q_mul_mat_cuda_t)( const int * __restrict__ x_ql, const half2 * __restrict__ x_dm, const int * __restrict__ x_qh, const int * __restrict__ x_sc, const int * __restrict__ y_qs, const half2 * __restrict__ y_ms, const int & i, const int & j, const int & k); -//================================= k-quants - -#ifdef GGML_QKK_64 -#define QK_K 64 -#define K_SCALE_SIZE 4 -#else -#define QK_K 256 -#define K_SCALE_SIZE 12 -#endif - -#define QR2_K 4 -#define QI2_K (QK_K / (4*QR2_K)) -typedef struct { - uint8_t scales[QK_K/16]; // scales and mins, quantized with 4 bits - uint8_t qs[QK_K/4]; // quants - half2 dm; // super-block scale for quantized scales/mins -} block_q2_K; -static_assert(sizeof(block_q2_K) == 2*sizeof(ggml_fp16_t) + QK_K/16 + QK_K/4, "wrong q2_K block size/padding"); - -#define QR3_K 4 -#define QI3_K (QK_K / (4*QR3_K)) -typedef struct { - uint8_t hmask[QK_K/8]; // quants - high bit - uint8_t qs[QK_K/4]; // quants - low 2 bits -#ifdef GGML_QKK_64 - uint8_t scales[2]; // scales, quantized with 8 bits -#else - uint8_t scales[K_SCALE_SIZE]; // scales, quantized with 6 bits -#endif - half d; // super-block scale -} block_q3_K; -//static_assert(sizeof(block_q3_K) == sizeof(ggml_fp16_t) + QK_K / 4 + QK_K / 8 + K_SCALE_SIZE, "wrong q3_K block size/padding"); - -#define QR4_K 2 -#define QI4_K (QK_K / (4*QR4_K)) -#ifdef GGML_QKK_64 -typedef struct { - half dm[2]; // super-block scales/mins - uint8_t scales[2]; // 4-bit block scales/mins - uint8_t qs[QK_K/2]; // 4--bit quants -} block_q4_K; -static_assert(sizeof(block_q4_K) == sizeof(half2) + QK_K/2 + 2, "wrong q4_K block size/padding"); -#else -typedef struct { - half2 dm; // super-block scale for quantized scales/mins - uint8_t scales[3*QK_K/64]; // scales, quantized with 6 bits - uint8_t qs[QK_K/2]; // 4--bit quants -} block_q4_K; -static_assert(sizeof(block_q4_K) == 2*sizeof(ggml_fp16_t) + 3*QK_K/64 + QK_K/2, "wrong q4_K block size/padding"); -#endif - -#define QR5_K 2 -#define QI5_K (QK_K / (4*QR5_K)) -#ifdef GGML_QKK_64 -typedef struct { - half d; // super-block scale - int8_t scales[QK_K/16]; // block scales - uint8_t qh[QK_K/8]; // quants, high bit - uint8_t qs[QK_K/2]; // quants, low 4 bits -} block_q5_K; -static_assert(sizeof(block_q5_K) == sizeof(ggml_fp16_t) + QK_K/2 + QK_K/8 + QK_K/16, "wrong q5_K block size/padding"); -#else -typedef struct { - half2 dm; // super-block scale for quantized scales/mins - uint8_t scales[K_SCALE_SIZE]; // scales and mins, quantized with 6 bits - uint8_t qh[QK_K/8]; // quants, high bit - uint8_t qs[QK_K/2]; // quants, low 4 bits -} block_q5_K; -static_assert(sizeof(block_q5_K) == 2*sizeof(ggml_fp16_t) + K_SCALE_SIZE + QK_K/2 + QK_K/8, "wrong q5_K block size/padding"); -#endif - -#define QR6_K 2 -#define QI6_K (QK_K / (4*QR6_K)) -typedef struct { - uint8_t ql[QK_K/2]; // quants, lower 4 bits - uint8_t qh[QK_K/4]; // quants, upper 2 bits - int8_t scales[QK_K/16]; // scales - half d; // delta -} block_q6_K; -static_assert(sizeof(block_q6_K) == sizeof(ggml_fp16_t) + 13*QK_K/16, "wrong q6_K block size/padding"); - -#define QR2_XXS 8 -#define QI2_XXS (QK_K / (4*QR2_XXS)) -typedef struct { - half d; - uint16_t qs[QK_K/8]; -} block_iq2_xxs; -static_assert(sizeof(block_iq2_xxs) == sizeof(ggml_fp16_t) + QK_K/8*sizeof(uint16_t), "wrong iq2_xxs block size/padding"); - -#define QR2_XS 8 -#define QI2_XS (QK_K / (4*QR2_XS)) -typedef struct { - half d; - uint16_t qs[QK_K/8]; - uint8_t scales[QK_K/32]; -} block_iq2_xs; -static_assert(sizeof(block_iq2_xs) == sizeof(ggml_fp16_t) + QK_K/8*sizeof(uint16_t) + QK_K/32, "wrong iq2_xs block size/padding"); - -// 2.5625 bpw quants -#define QR2_S 8 -#define QI2_S (QK_K / (4*QR2_S)) -typedef struct { - half d; - uint8_t qs[QK_K/4]; - uint8_t qh[QK_K/32]; - uint8_t scales[QK_K/32]; -} block_iq2_s; -static_assert(sizeof(block_iq2_s) == sizeof(ggml_fp16_t) + QK_K/4 + QK_K/16, "wrong iq2_s block size/padding"); - -#define QR3_XXS 8 -#define QI3_XXS (QK_K / (4*QR3_XXS)) -typedef struct { - half d; - uint8_t qs[3*(QK_K/8)]; -} block_iq3_xxs; -static_assert(sizeof(block_iq3_xxs) == sizeof(ggml_fp16_t) + 3*(QK_K/8), "wrong iq3_xxs block size/padding"); - -#define QR3_XS 8 -#define QI3_XS (QK_K / (4*QR3_XS)) -#if QK_K == 64 -#define IQ3S_N_SCALE 2 -#else -#define IQ3S_N_SCALE QK_K/64 -#endif -typedef struct { - half d; - uint8_t qs[QK_K/4]; - uint8_t qh[QK_K/32]; - uint8_t signs[QK_K/8]; - uint8_t scales[IQ3S_N_SCALE]; -} block_iq3_s; -static_assert(sizeof(block_iq3_s) == sizeof(ggml_fp16_t) + 13*(QK_K/32) + IQ3S_N_SCALE, "wrong iq3_s block size/padding"); - -#define QR1_S 8 -#define QI1_S (QK_K / (4*QR1_S)) -typedef struct { - half d; - uint8_t qs[QK_K/8]; - uint8_t scales[QK_K/16]; -} block_iq1_s; -static_assert(sizeof(block_iq1_s) == sizeof(ggml_fp16_t) + QK_K/8 + QK_K/16, "wrong iq1_s block size/padding"); - -#define QK4_NL 32 -#define QR4_NL 2 -#define QI4_NL (QK4_NL / (4*QR4_NL)) -typedef struct { - half d; - uint8_t qs[QK4_NL/2]; -} block_iq4_nl; -static_assert(sizeof(block_iq4_nl) == sizeof(ggml_fp16_t) + QK4_NL/2, "wrong iq4_nl block size/padding"); - -#if QK_K == 64 -#define block_iq4_xs block_iq4_nl -#define QR4_XS QR4_NL -#define QI4_XS QI4_NL -#else -// QR4_XS = 8 is very slightly faster than QR4_XS = 4 -#define QR4_XS 8 -#define QI4_XS (QK_K / (4*QR4_XS)) -typedef struct { - half d; - uint16_t scales_h; - uint8_t scales_l[QK_K/64]; - uint8_t qs[QK_K/2]; -} block_iq4_xs; -static_assert(sizeof(block_iq4_xs) == sizeof(ggml_fp16_t) + sizeof(uint16_t) + QK_K/64 + QK_K/2, "wrong iq4_xs block size/padding"); -#endif - #define WARP_SIZE 32 #define MATRIX_ROW_PADDING 512 // last row of quant. matrices is a multiple of this to avoid out-of-bounds memory accesses @@ -1569,746 +1353,6 @@ static __global__ void dequantize_block_q6_K(const void * __restrict__ vx, dst_t #endif } -static const __device__ uint64_t iq2xxs_grid[256] = { - 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, - 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808, - 0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819, - 0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819, - 0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b, - 0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808, - 0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08, - 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b, - 0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819, - 0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08, - 0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808, - 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08, - 0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808, - 0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808, - 0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919, - 0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819, - 0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08, - 0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908, - 0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819, - 0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808, - 0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808, - 0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908, - 0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808, - 0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08, - 0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819, - 0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819, - 0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819, - 0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908, - 0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19, - 0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819, - 0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b, - 0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808, - 0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908, - 0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08, - 0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08, - 0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908, - 0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819, - 0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808, - 0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808, - 0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19, - 0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819, - 0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, - 0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b, - 0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08, - 0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808, - 0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908, - 0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b, - 0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819, - 0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08, - 0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08, - 0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808, - 0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b, - 0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b, - 0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908, - 0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819, - 0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808, - 0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908, - 0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b, - 0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808, - 0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b, - 0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b, - 0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808, - 0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19, - 0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908, -}; - -static const __device__ uint64_t iq2xs_grid[512] = { - 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, - 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b, - 0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919, - 0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b, - 0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919, - 0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808, - 0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819, - 0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819, - 0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, - 0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b, - 0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b, - 0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908, - 0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908, - 0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919, - 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808, - 0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919, - 0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908, - 0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, - 0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, - 0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08, - 0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808, - 0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808, - 0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819, - 0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908, - 0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819, - 0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808, - 0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b, - 0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819, - 0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819, - 0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808, - 0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908, - 0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19, - 0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b, - 0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b, - 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919, - 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808, - 0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819, - 0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819, - 0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b, - 0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908, - 0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808, - 0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819, - 0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808, - 0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919, - 0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808, - 0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808, - 0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908, - 0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908, - 0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808, - 0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b, - 0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819, - 0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, - 0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908, - 0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808, - 0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908, - 0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919, - 0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08, - 0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19, - 0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b, - 0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b, - 0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808, - 0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08, - 0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b, - 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908, - 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b, - 0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908, - 0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, - 0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808, - 0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808, - 0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08, - 0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819, - 0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919, - 0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808, - 0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808, - 0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819, - 0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819, - 0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908, - 0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908, - 0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b, - 0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908, - 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908, - 0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908, - 0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808, - 0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, - 0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819, - 0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819, - 0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808, - 0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b, - 0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819, - 0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819, - 0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08, - 0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808, - 0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19, - 0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919, - 0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808, - 0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19, - 0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b, - 0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808, - 0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b, - 0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b, - 0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, - 0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b, - 0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808, - 0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819, - 0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808, - 0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808, - 0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08, - 0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b, - 0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19, - 0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08, - 0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919, - 0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08, - 0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08, - 0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908, - 0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908, - 0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b, - 0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908, - 0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808, - 0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b, - 0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808, - 0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808, - 0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19, - 0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08, - 0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808, - 0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b, - 0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808, - 0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b, - 0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b, -}; - -static const __device__ uint64_t iq2s_grid[1024] = { - 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, - 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b, - 0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919, - 0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b, - 0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919, - 0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x08080808192b192b, - 0x08080808192b2b19, 0x080808082b080808, 0x080808082b08082b, 0x080808082b081919, - 0x080808082b082b08, 0x080808082b190819, 0x080808082b191908, 0x080808082b2b0808, - 0x080808082b2b1919, 0x080808082b2b2b2b, 0x0808081908080819, 0x0808081908081908, - 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, 0x080808190819082b, - 0x0808081908191919, 0x0808081908192b08, 0x08080819082b0819, 0x08080819082b1908, - 0x0808081919080808, 0x080808191908082b, 0x0808081919081919, 0x0808081919082b08, - 0x0808081919190819, 0x0808081919191908, 0x080808191919192b, 0x0808081919192b19, - 0x08080819192b0808, 0x08080819192b1919, 0x08080819192b2b08, 0x080808192b080819, - 0x080808192b081908, 0x080808192b190808, 0x080808192b19082b, 0x080808192b191919, - 0x080808192b2b0819, 0x080808192b2b1908, 0x0808082b08080808, 0x0808082b0808082b, - 0x0808082b08081919, 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, - 0x0808082b082b0808, 0x0808082b082b2b2b, 0x0808082b19080819, 0x0808082b19081908, - 0x0808082b1908192b, 0x0808082b19082b19, 0x0808082b19190808, 0x0808082b19191919, - 0x0808082b2b080808, 0x0808082b2b081919, 0x0808082b2b082b2b, 0x0808082b2b191908, - 0x0808082b2b2b082b, 0x0808190808080819, 0x0808190808081908, 0x080819080808192b, - 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, 0x0808190808191919, - 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, 0x08081908082b192b, - 0x08081908082b2b19, 0x0808190819080808, 0x080819081908082b, 0x0808190819081919, - 0x0808190819082b08, 0x0808190819082b2b, 0x0808190819190819, 0x0808190819191908, - 0x080819081919192b, 0x0808190819192b19, 0x08081908192b0808, 0x08081908192b082b, - 0x08081908192b1919, 0x080819082b080819, 0x080819082b081908, 0x080819082b08192b, - 0x080819082b082b19, 0x080819082b190808, 0x080819082b191919, 0x080819082b192b08, - 0x080819082b2b0819, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, - 0x0808191908081919, 0x0808191908082b08, 0x0808191908082b2b, 0x0808191908190819, - 0x0808191908191908, 0x080819190819192b, 0x0808191908192b19, 0x08081919082b0808, - 0x08081919082b1919, 0x08081919082b2b08, 0x0808191919080819, 0x0808191919081908, - 0x080819191908192b, 0x0808191919082b19, 0x0808191919190808, 0x080819191919082b, - 0x0808191919191919, 0x0808191919192b08, 0x08081919192b0819, 0x08081919192b1908, - 0x080819192b080808, 0x080819192b08082b, 0x080819192b081919, 0x080819192b082b08, - 0x080819192b190819, 0x080819192b191908, 0x080819192b2b0808, 0x0808192b08080819, - 0x0808192b08081908, 0x0808192b0808192b, 0x0808192b08082b19, 0x0808192b08190808, - 0x0808192b08191919, 0x0808192b19080808, 0x0808192b19081919, 0x0808192b19082b08, - 0x0808192b19190819, 0x0808192b19191908, 0x0808192b192b0808, 0x0808192b2b080819, - 0x0808192b2b081908, 0x0808192b2b190808, 0x08082b0808080808, 0x08082b080808082b, - 0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808190819, 0x08082b0808191908, - 0x08082b080819192b, 0x08082b0808192b19, 0x08082b08082b0808, 0x08082b08082b1919, - 0x08082b08082b2b2b, 0x08082b0819080819, 0x08082b0819081908, 0x08082b081908192b, - 0x08082b0819082b19, 0x08082b0819190808, 0x08082b081919082b, 0x08082b0819191919, - 0x08082b0819192b08, 0x08082b08192b0819, 0x08082b08192b1908, 0x08082b082b080808, - 0x08082b082b081919, 0x08082b082b191908, 0x08082b082b2b2b2b, 0x08082b1908080819, - 0x08082b1908081908, 0x08082b1908190808, 0x08082b190819082b, 0x08082b1908191919, - 0x08082b1908192b08, 0x08082b19082b0819, 0x08082b1919080808, 0x08082b1919081919, - 0x08082b1919082b08, 0x08082b1919190819, 0x08082b1919191908, 0x08082b19192b0808, - 0x08082b192b080819, 0x08082b192b190808, 0x08082b2b08080808, 0x08082b2b08190819, - 0x08082b2b08191908, 0x08082b2b082b082b, 0x08082b2b082b2b08, 0x08082b2b082b2b2b, - 0x08082b2b19190808, 0x08082b2b2b192b19, 0x0819080808080819, 0x0819080808081908, - 0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, - 0x0819080808191919, 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, - 0x08190808082b192b, 0x0819080819080808, 0x081908081908082b, 0x0819080819081919, - 0x0819080819082b08, 0x0819080819190819, 0x0819080819191908, 0x081908081919192b, - 0x0819080819192b19, 0x08190808192b0808, 0x08190808192b082b, 0x08190808192b1919, - 0x08190808192b2b08, 0x081908082b080819, 0x081908082b081908, 0x081908082b08192b, - 0x081908082b190808, 0x081908082b191919, 0x081908082b192b08, 0x081908082b2b0819, - 0x081908082b2b1908, 0x0819081908080808, 0x081908190808082b, 0x0819081908081919, - 0x0819081908082b08, 0x0819081908082b2b, 0x0819081908190819, 0x0819081908191908, - 0x081908190819192b, 0x0819081908192b19, 0x08190819082b0808, 0x08190819082b082b, - 0x08190819082b1919, 0x08190819082b2b08, 0x0819081919080819, 0x0819081919081908, - 0x081908191908192b, 0x0819081919082b19, 0x0819081919190808, 0x081908191919082b, - 0x0819081919191919, 0x0819081919192b08, 0x08190819192b0819, 0x08190819192b1908, - 0x081908192b080808, 0x081908192b08082b, 0x081908192b081919, 0x081908192b082b08, - 0x081908192b190819, 0x081908192b191908, 0x0819082b08080819, 0x0819082b08081908, - 0x0819082b08082b19, 0x0819082b08190808, 0x0819082b08191919, 0x0819082b082b0819, - 0x0819082b082b1908, 0x0819082b19080808, 0x0819082b19081919, 0x0819082b19190819, - 0x0819082b19191908, 0x0819082b2b080819, 0x0819082b2b081908, 0x0819082b2b190808, - 0x0819190808080808, 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08, - 0x0819190808190819, 0x0819190808191908, 0x081919080819192b, 0x0819190808192b19, - 0x08191908082b0808, 0x08191908082b1919, 0x08191908082b2b08, 0x0819190819080819, - 0x0819190819081908, 0x081919081908192b, 0x0819190819082b19, 0x0819190819190808, - 0x081919081919082b, 0x0819190819191919, 0x0819190819192b08, 0x08191908192b0819, - 0x08191908192b1908, 0x081919082b080808, 0x081919082b08082b, 0x081919082b081919, - 0x081919082b082b08, 0x081919082b190819, 0x081919082b191908, 0x081919082b2b0808, - 0x0819191908080819, 0x0819191908081908, 0x081919190808192b, 0x0819191908082b19, - 0x0819191908190808, 0x081919190819082b, 0x0819191908191919, 0x0819191908192b08, - 0x08191919082b0819, 0x08191919082b1908, 0x0819191919080808, 0x081919191908082b, - 0x0819191919081919, 0x0819191919082b08, 0x0819191919190819, 0x0819191919191908, - 0x08191919192b0808, 0x081919192b080819, 0x081919192b081908, 0x081919192b190808, - 0x0819192b08080808, 0x0819192b08081919, 0x0819192b08082b08, 0x0819192b08190819, - 0x0819192b08191908, 0x0819192b082b0808, 0x0819192b19080819, 0x0819192b19081908, - 0x0819192b19190808, 0x0819192b2b080808, 0x0819192b2b2b2b2b, 0x08192b0808080819, - 0x08192b0808081908, 0x08192b080808192b, 0x08192b0808082b19, 0x08192b0808190808, - 0x08192b0808191919, 0x08192b0808192b08, 0x08192b08082b0819, 0x08192b0819080808, - 0x08192b081908082b, 0x08192b0819081919, 0x08192b0819082b08, 0x08192b0819190819, - 0x08192b0819191908, 0x08192b08192b0808, 0x08192b082b080819, 0x08192b082b081908, - 0x08192b1908080808, 0x08192b190808082b, 0x08192b1908081919, 0x08192b1908082b08, - 0x08192b1908190819, 0x08192b1908191908, 0x08192b19082b0808, 0x08192b1919080819, - 0x08192b1919081908, 0x08192b1919190808, 0x08192b19192b2b19, 0x08192b192b2b082b, - 0x08192b2b08081908, 0x08192b2b08190808, 0x08192b2b19080808, 0x08192b2b1919192b, - 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, 0x082b080808082b08, - 0x082b080808190819, 0x082b080808191908, 0x082b08080819192b, 0x082b080808192b19, - 0x082b0808082b0808, 0x082b0808082b1919, 0x082b0808082b2b2b, 0x082b080819080819, - 0x082b080819081908, 0x082b080819190808, 0x082b08081919082b, 0x082b080819191919, - 0x082b0808192b1908, 0x082b08082b080808, 0x082b08082b082b2b, 0x082b08082b191908, - 0x082b08082b2b2b2b, 0x082b081908080819, 0x082b081908081908, 0x082b081908190808, - 0x082b08190819082b, 0x082b081908191919, 0x082b0819082b0819, 0x082b081919080808, - 0x082b08191908082b, 0x082b081919081919, 0x082b081919190819, 0x082b081919191908, - 0x082b0819192b0808, 0x082b08192b080819, 0x082b08192b081908, 0x082b08192b190808, - 0x082b082b08080808, 0x082b082b08082b2b, 0x082b082b082b082b, 0x082b082b082b2b08, - 0x082b082b082b2b2b, 0x082b082b19081908, 0x082b082b19190808, 0x082b082b2b082b08, - 0x082b082b2b082b2b, 0x082b082b2b2b2b08, 0x082b190808080819, 0x082b190808081908, - 0x082b19080808192b, 0x082b190808082b19, 0x082b190808190808, 0x082b190808191919, - 0x082b190808192b08, 0x082b1908082b0819, 0x082b1908082b1908, 0x082b190819080808, - 0x082b19081908082b, 0x082b190819081919, 0x082b190819082b08, 0x082b190819190819, - 0x082b190819191908, 0x082b1908192b0808, 0x082b19082b080819, 0x082b19082b081908, - 0x082b19082b190808, 0x082b191908080808, 0x082b191908081919, 0x082b191908082b08, - 0x082b191908190819, 0x082b191908191908, 0x082b1919082b0808, 0x082b191919080819, - 0x082b191919081908, 0x082b191919190808, 0x082b1919192b192b, 0x082b19192b080808, - 0x082b192b08080819, 0x082b192b08081908, 0x082b192b08190808, 0x082b192b19080808, - 0x082b192b19192b19, 0x082b2b0808080808, 0x082b2b0808081919, 0x082b2b0808190819, - 0x082b2b0808191908, 0x082b2b0819080819, 0x082b2b0819081908, 0x082b2b0819190808, - 0x082b2b082b082b2b, 0x082b2b082b2b2b2b, 0x082b2b1908080819, 0x082b2b1908081908, - 0x082b2b1908190808, 0x082b2b192b191919, 0x082b2b2b08082b2b, 0x082b2b2b082b082b, - 0x082b2b2b192b1908, 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, - 0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, - 0x190808080819082b, 0x1908080808191919, 0x1908080808192b08, 0x1908080808192b2b, - 0x19080808082b0819, 0x19080808082b1908, 0x19080808082b192b, 0x1908080819080808, - 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, 0x1908080819082b2b, - 0x1908080819190819, 0x1908080819191908, 0x190808081919192b, 0x1908080819192b19, - 0x19080808192b0808, 0x19080808192b082b, 0x19080808192b1919, 0x190808082b080819, - 0x190808082b081908, 0x190808082b190808, 0x190808082b191919, 0x190808082b192b08, - 0x190808082b2b0819, 0x190808082b2b1908, 0x1908081908080808, 0x190808190808082b, - 0x1908081908081919, 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908, - 0x190808190819192b, 0x1908081908192b19, 0x19080819082b0808, 0x19080819082b082b, - 0x19080819082b1919, 0x1908081919080819, 0x1908081919081908, 0x190808191908192b, - 0x1908081919082b19, 0x1908081919190808, 0x190808191919082b, 0x1908081919191919, - 0x1908081919192b08, 0x19080819192b0819, 0x19080819192b1908, 0x190808192b080808, - 0x190808192b08082b, 0x190808192b081919, 0x190808192b082b08, 0x190808192b190819, - 0x190808192b191908, 0x190808192b2b0808, 0x1908082b08080819, 0x1908082b08081908, - 0x1908082b08190808, 0x1908082b0819082b, 0x1908082b08191919, 0x1908082b08192b08, - 0x1908082b082b1908, 0x1908082b19080808, 0x1908082b19081919, 0x1908082b19082b08, - 0x1908082b19190819, 0x1908082b19191908, 0x1908082b192b0808, 0x1908082b2b080819, - 0x1908082b2b081908, 0x1908190808080808, 0x190819080808082b, 0x1908190808081919, - 0x1908190808082b08, 0x1908190808082b2b, 0x1908190808190819, 0x1908190808191908, - 0x190819080819192b, 0x1908190808192b19, 0x19081908082b0808, 0x19081908082b082b, - 0x19081908082b1919, 0x19081908082b2b08, 0x1908190819080819, 0x1908190819081908, - 0x190819081908192b, 0x1908190819082b19, 0x1908190819190808, 0x190819081919082b, - 0x1908190819191919, 0x1908190819192b08, 0x19081908192b0819, 0x19081908192b1908, - 0x190819082b080808, 0x190819082b08082b, 0x190819082b081919, 0x190819082b082b08, - 0x190819082b190819, 0x190819082b191908, 0x190819082b2b0808, 0x1908191908080819, - 0x1908191908081908, 0x190819190808192b, 0x1908191908082b19, 0x1908191908190808, - 0x190819190819082b, 0x1908191908191919, 0x1908191908192b08, 0x19081919082b0819, - 0x19081919082b1908, 0x1908191919080808, 0x190819191908082b, 0x1908191919081919, - 0x1908191919082b08, 0x1908191919190819, 0x1908191919191908, 0x19081919192b0808, - 0x19081919192b2b2b, 0x190819192b080819, 0x190819192b081908, 0x190819192b190808, - 0x1908192b08080808, 0x1908192b0808082b, 0x1908192b08081919, 0x1908192b08082b08, - 0x1908192b08190819, 0x1908192b08191908, 0x1908192b082b0808, 0x1908192b19080819, - 0x1908192b19081908, 0x1908192b19190808, 0x1908192b2b080808, 0x1908192b2b2b1919, - 0x19082b0808080819, 0x19082b0808081908, 0x19082b0808082b19, 0x19082b0808190808, - 0x19082b080819082b, 0x19082b0808191919, 0x19082b0808192b08, 0x19082b08082b0819, - 0x19082b08082b1908, 0x19082b0819080808, 0x19082b081908082b, 0x19082b0819081919, - 0x19082b0819082b08, 0x19082b0819190819, 0x19082b0819191908, 0x19082b08192b0808, - 0x19082b082b081908, 0x19082b082b190808, 0x19082b1908080808, 0x19082b190808082b, - 0x19082b1908081919, 0x19082b1908082b08, 0x19082b1908190819, 0x19082b1908191908, - 0x19082b19082b0808, 0x19082b1919080819, 0x19082b1919081908, 0x19082b1919190808, - 0x19082b192b080808, 0x19082b192b19192b, 0x19082b2b08080819, 0x19082b2b08081908, - 0x19082b2b08190808, 0x19082b2b19080808, 0x1919080808080808, 0x191908080808082b, - 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, 0x1919080808191908, - 0x191908080819192b, 0x1919080808192b19, 0x19190808082b0808, 0x19190808082b082b, - 0x19190808082b1919, 0x19190808082b2b08, 0x1919080819080819, 0x1919080819081908, - 0x191908081908192b, 0x1919080819082b19, 0x1919080819190808, 0x191908081919082b, - 0x1919080819191919, 0x1919080819192b08, 0x19190808192b0819, 0x19190808192b1908, - 0x191908082b080808, 0x191908082b08082b, 0x191908082b081919, 0x191908082b082b08, - 0x191908082b190819, 0x191908082b191908, 0x1919081908080819, 0x1919081908081908, - 0x191908190808192b, 0x1919081908082b19, 0x1919081908190808, 0x191908190819082b, - 0x1919081908191919, 0x1919081908192b08, 0x19190819082b0819, 0x19190819082b1908, - 0x1919081919080808, 0x191908191908082b, 0x1919081919081919, 0x1919081919082b08, - 0x1919081919190819, 0x1919081919191908, 0x19190819192b0808, 0x191908192b080819, - 0x191908192b081908, 0x191908192b190808, 0x1919082b08080808, 0x1919082b08081919, - 0x1919082b08082b08, 0x1919082b08190819, 0x1919082b08191908, 0x1919082b082b0808, - 0x1919082b19080819, 0x1919082b19081908, 0x1919082b19190808, 0x1919082b192b2b19, - 0x1919082b2b080808, 0x1919190808080819, 0x1919190808081908, 0x191919080808192b, - 0x1919190808082b19, 0x1919190808190808, 0x191919080819082b, 0x1919190808191919, - 0x1919190808192b08, 0x19191908082b0819, 0x19191908082b1908, 0x1919190819080808, - 0x191919081908082b, 0x1919190819081919, 0x1919190819082b08, 0x1919190819190819, - 0x1919190819191908, 0x19191908192b0808, 0x191919082b080819, 0x191919082b081908, - 0x191919082b190808, 0x1919191908080808, 0x191919190808082b, 0x1919191908081919, - 0x1919191908082b08, 0x1919191908190819, 0x1919191908191908, 0x19191919082b0808, - 0x1919191919080819, 0x1919191919081908, 0x1919191919190808, 0x191919192b080808, - 0x1919192b08080819, 0x1919192b08081908, 0x1919192b08190808, 0x1919192b082b192b, - 0x1919192b19080808, 0x19192b0808080808, 0x19192b080808082b, 0x19192b0808081919, - 0x19192b0808082b08, 0x19192b0808190819, 0x19192b0808191908, 0x19192b08082b0808, - 0x19192b0819080819, 0x19192b0819081908, 0x19192b0819190808, 0x19192b0819192b2b, - 0x19192b082b080808, 0x19192b1908080819, 0x19192b1908081908, 0x19192b1908190808, - 0x19192b1919080808, 0x19192b2b08080808, 0x19192b2b08192b19, 0x19192b2b2b081919, - 0x19192b2b2b2b2b08, 0x192b080808080819, 0x192b080808081908, 0x192b08080808192b, - 0x192b080808190808, 0x192b08080819082b, 0x192b080808191919, 0x192b080808192b08, - 0x192b0808082b0819, 0x192b0808082b1908, 0x192b080819080808, 0x192b080819081919, - 0x192b080819082b08, 0x192b080819190819, 0x192b080819191908, 0x192b0808192b0808, - 0x192b08082b081908, 0x192b08082b190808, 0x192b081908080808, 0x192b08190808082b, - 0x192b081908081919, 0x192b081908082b08, 0x192b081908190819, 0x192b081908191908, - 0x192b0819082b0808, 0x192b081919080819, 0x192b081919081908, 0x192b081919190808, - 0x192b08192b080808, 0x192b08192b192b19, 0x192b082b08081908, 0x192b082b08190808, - 0x192b082b19080808, 0x192b082b1919192b, 0x192b082b2b2b0819, 0x192b190808080808, - 0x192b190808081919, 0x192b190808082b08, 0x192b190808190819, 0x192b190808191908, - 0x192b1908082b0808, 0x192b190819080819, 0x192b190819081908, 0x192b190819190808, - 0x192b19082b080808, 0x192b191908080819, 0x192b191908081908, 0x192b191908190808, - 0x192b191919080808, 0x192b191919082b2b, 0x192b1919192b2b08, 0x192b19192b19082b, - 0x192b192b08080808, 0x192b192b2b191908, 0x192b2b0808080819, 0x192b2b0808081908, - 0x192b2b0808190808, 0x192b2b08192b1919, 0x192b2b082b192b08, 0x192b2b1908080808, - 0x192b2b19082b2b2b, 0x192b2b2b1908082b, 0x192b2b2b2b2b0819, 0x2b08080808080808, - 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819, - 0x2b08080808191908, 0x2b08080808192b19, 0x2b080808082b0808, 0x2b080808082b1919, - 0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808081919082b, - 0x2b08080819191919, 0x2b08080819192b08, 0x2b080808192b0819, 0x2b0808082b080808, - 0x2b0808082b081919, 0x2b0808082b190819, 0x2b0808082b191908, 0x2b08081908080819, - 0x2b08081908081908, 0x2b08081908082b19, 0x2b08081908190808, 0x2b0808190819082b, - 0x2b08081908191919, 0x2b08081908192b08, 0x2b080819082b0819, 0x2b080819082b1908, - 0x2b08081919080808, 0x2b0808191908082b, 0x2b08081919081919, 0x2b08081919082b08, - 0x2b08081919190819, 0x2b08081919191908, 0x2b0808192b080819, 0x2b0808192b081908, - 0x2b0808192b190808, 0x2b0808192b2b2b19, 0x2b08082b08080808, 0x2b08082b08081919, - 0x2b08082b08082b2b, 0x2b08082b08190819, 0x2b08082b08191908, 0x2b08082b19080819, - 0x2b08082b19081908, 0x2b08082b19190808, 0x2b08190808080819, 0x2b08190808081908, - 0x2b0819080808192b, 0x2b08190808082b19, 0x2b08190808190808, 0x2b0819080819082b, - 0x2b08190808191919, 0x2b08190808192b08, 0x2b081908082b0819, 0x2b08190819080808, - 0x2b0819081908082b, 0x2b08190819081919, 0x2b08190819082b08, 0x2b08190819190819, - 0x2b08190819191908, 0x2b081908192b0808, 0x2b0819082b080819, 0x2b0819082b081908, - 0x2b0819082b190808, 0x2b08191908080808, 0x2b0819190808082b, 0x2b08191908081919, - 0x2b08191908082b08, 0x2b08191908190819, 0x2b08191908191908, 0x2b081919082b0808, - 0x2b08191919080819, 0x2b08191919081908, 0x2b08191919190808, 0x2b0819192b080808, - 0x2b0819192b082b2b, 0x2b08192b08080819, 0x2b08192b08081908, 0x2b08192b08190808, - 0x2b08192b082b2b19, 0x2b08192b19080808, 0x2b082b0808080808, 0x2b082b0808081919, - 0x2b082b0808190819, 0x2b082b0808191908, 0x2b082b0819080819, 0x2b082b0819081908, - 0x2b082b0819190808, 0x2b082b082b2b082b, 0x2b082b1908080819, 0x2b082b1908081908, - 0x2b082b1919080808, 0x2b082b19192b1919, 0x2b082b2b082b082b, 0x2b082b2b19192b08, - 0x2b082b2b19192b2b, 0x2b082b2b2b08082b, 0x2b082b2b2b2b082b, 0x2b19080808080819, - 0x2b19080808081908, 0x2b19080808082b19, 0x2b19080808190808, 0x2b1908080819082b, - 0x2b19080808191919, 0x2b19080808192b08, 0x2b190808082b1908, 0x2b19080819080808, - 0x2b1908081908082b, 0x2b19080819081919, 0x2b19080819082b08, 0x2b19080819190819, - 0x2b19080819191908, 0x2b190808192b0808, 0x2b1908082b080819, 0x2b1908082b081908, - 0x2b1908082b190808, 0x2b19081908080808, 0x2b19081908081919, 0x2b19081908190819, - 0x2b19081908191908, 0x2b19081919080819, 0x2b19081919081908, 0x2b19081919190808, - 0x2b19081919192b2b, 0x2b19082b08080819, 0x2b19082b08081908, 0x2b19082b08190808, - 0x2b19082b19080808, 0x2b19082b2b2b192b, 0x2b19190808080808, 0x2b1919080808082b, - 0x2b19190808081919, 0x2b19190808082b08, 0x2b19190808190819, 0x2b19190808191908, - 0x2b191908082b0808, 0x2b19190819080819, 0x2b19190819081908, 0x2b19190819190808, - 0x2b1919082b080808, 0x2b1919082b19192b, 0x2b19191908080819, 0x2b19191908081908, - 0x2b19191908190808, 0x2b19191919080808, 0x2b1919192b192b08, 0x2b1919192b2b0819, - 0x2b19192b08080808, 0x2b19192b1908192b, 0x2b19192b192b1908, 0x2b192b0808080819, - 0x2b192b0808081908, 0x2b192b0808190808, 0x2b192b08082b192b, 0x2b192b0819080808, - 0x2b192b082b2b2b19, 0x2b192b1908080808, 0x2b192b1919082b19, 0x2b192b191919082b, - 0x2b192b2b2b190808, 0x2b2b080808080808, 0x2b2b080808081919, 0x2b2b080808082b2b, - 0x2b2b080808191908, 0x2b2b0808082b082b, 0x2b2b0808082b2b2b, 0x2b2b080819080819, - 0x2b2b080819081908, 0x2b2b080819190808, 0x2b2b08082b2b082b, 0x2b2b08082b2b2b2b, - 0x2b2b081919080808, 0x2b2b0819192b1919, 0x2b2b082b0808082b, 0x2b2b082b08082b2b, - 0x2b2b082b082b082b, 0x2b2b082b082b2b08, 0x2b2b082b082b2b2b, 0x2b2b082b2b08082b, - 0x2b2b082b2b082b08, 0x2b2b082b2b082b2b, 0x2b2b082b2b2b2b08, 0x2b2b190808080819, - 0x2b2b190808081908, 0x2b2b190808190808, 0x2b2b190819080808, 0x2b2b19082b082b19, - 0x2b2b19082b2b1908, 0x2b2b191908080808, 0x2b2b191908192b19, 0x2b2b192b19190819, - 0x2b2b2b0808082b2b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b082b, 0x2b2b2b1919191908, - 0x2b2b2b192b08192b, 0x2b2b2b2b08082b08, 0x2b2b2b2b08082b2b, 0x2b2b2b2b082b0808, - 0x2b2b2b2b082b082b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b2b082b08, 0x2b2b2b2b2b2b2b2b, -}; - -static const __device__ uint32_t iq3xxs_grid[256] = { - 0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, 0x04041404, 0x04041414, - 0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14, - 0x040c140c, 0x040c142c, 0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404, - 0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c, 0x04141c1c, 0x04141c3e, - 0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c, 0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c, - 0x041c3e04, 0x04240c1c, 0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c, - 0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04, 0x043e0c24, 0x043e0c34, - 0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c, 0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c, - 0x0c041c04, 0x0c041c14, 0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c, - 0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14, 0x0c14140c, 0x0c141c04, - 0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404, 0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c, - 0x0c24042c, 0x0c242c04, 0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414, - 0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404, 0x14041414, 0x14041434, - 0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c, 0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c, - 0x140c1c04, 0x140c341c, 0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e, - 0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c, 0x141c0c04, 0x141c0c24, - 0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c, 0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24, - 0x143e040c, 0x143e041c, 0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c, - 0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414, 0x1c0c1404, 0x1c0c1c0c, - 0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c, 0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14, - 0x1c1c0c0c, 0x1c1c1c1c, 0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414, - 0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404, 0x24040424, 0x24040c3e, - 0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e, 0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404, - 0x24143404, 0x24143434, 0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c, - 0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04, 0x2c040c14, 0x2c04240c, - 0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434, 0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14, - 0x2c1c0414, 0x2c1c2c1c, 0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c, - 0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434, 0x34043424, 0x340c140c, - 0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04, 0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14, - 0x34341c1c, 0x343e041c, 0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14, - 0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14, 0x3e1c0404, 0x3e1c0c2c, - 0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c, 0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04, -}; - -static const __device__ uint32_t iq3s_grid[512] = { - 0x01010101, 0x01010103, 0x01010105, 0x0101010b, 0x0101010f, 0x01010301, 0x01010303, 0x01010305, - 0x01010309, 0x0101030d, 0x01010501, 0x01010503, 0x0101050b, 0x01010707, 0x01010901, 0x01010905, - 0x0101090b, 0x0101090f, 0x01010b03, 0x01010b07, 0x01010d01, 0x01010d05, 0x01010f03, 0x01010f09, - 0x01010f0f, 0x01030101, 0x01030103, 0x01030105, 0x01030109, 0x01030301, 0x01030303, 0x0103030b, - 0x01030501, 0x01030507, 0x0103050f, 0x01030703, 0x0103070b, 0x01030909, 0x01030d03, 0x01030d0b, - 0x01030f05, 0x01050101, 0x01050103, 0x0105010b, 0x0105010f, 0x01050301, 0x01050307, 0x0105030d, - 0x01050503, 0x0105050b, 0x01050701, 0x01050709, 0x01050905, 0x0105090b, 0x0105090f, 0x01050b03, - 0x01050b07, 0x01050f01, 0x01050f07, 0x01070107, 0x01070303, 0x0107030b, 0x01070501, 0x01070505, - 0x01070703, 0x01070707, 0x0107070d, 0x01070909, 0x01070b01, 0x01070b05, 0x01070d0f, 0x01070f03, - 0x01070f0b, 0x01090101, 0x01090307, 0x0109030f, 0x01090503, 0x01090509, 0x01090705, 0x01090901, - 0x01090907, 0x01090b03, 0x01090f01, 0x010b0105, 0x010b0109, 0x010b0501, 0x010b0505, 0x010b050d, - 0x010b0707, 0x010b0903, 0x010b090b, 0x010b090f, 0x010b0d0d, 0x010b0f07, 0x010d010d, 0x010d0303, - 0x010d0307, 0x010d0703, 0x010d0b05, 0x010d0f03, 0x010f0101, 0x010f0105, 0x010f0109, 0x010f0501, - 0x010f0505, 0x010f050d, 0x010f0707, 0x010f0b01, 0x010f0b09, 0x03010101, 0x03010103, 0x03010105, - 0x03010109, 0x03010301, 0x03010303, 0x03010307, 0x0301030b, 0x0301030f, 0x03010501, 0x03010505, - 0x03010703, 0x03010709, 0x0301070d, 0x03010b09, 0x03010b0d, 0x03010d03, 0x03010f05, 0x03030101, - 0x03030103, 0x03030107, 0x0303010d, 0x03030301, 0x03030309, 0x03030503, 0x03030701, 0x03030707, - 0x03030903, 0x03030b01, 0x03030b05, 0x03030f01, 0x03030f0d, 0x03050101, 0x03050305, 0x0305030b, - 0x0305030f, 0x03050501, 0x03050509, 0x03050705, 0x03050901, 0x03050907, 0x03050b0b, 0x03050d01, - 0x03050f05, 0x03070103, 0x03070109, 0x0307010f, 0x03070301, 0x03070307, 0x03070503, 0x0307050f, - 0x03070701, 0x03070709, 0x03070903, 0x03070d05, 0x03070f01, 0x03090107, 0x0309010b, 0x03090305, - 0x03090309, 0x03090703, 0x03090707, 0x03090905, 0x0309090d, 0x03090b01, 0x03090b09, 0x030b0103, - 0x030b0301, 0x030b0307, 0x030b0503, 0x030b0701, 0x030b0705, 0x030b0b03, 0x030d0501, 0x030d0509, - 0x030d050f, 0x030d0909, 0x030d090d, 0x030f0103, 0x030f0107, 0x030f0301, 0x030f0305, 0x030f0503, - 0x030f070b, 0x030f0903, 0x030f0d05, 0x030f0f01, 0x05010101, 0x05010103, 0x05010107, 0x0501010b, - 0x0501010f, 0x05010301, 0x05010305, 0x05010309, 0x0501030d, 0x05010503, 0x05010507, 0x0501050f, - 0x05010701, 0x05010705, 0x05010903, 0x05010907, 0x0501090b, 0x05010b01, 0x05010b05, 0x05010d0f, - 0x05010f01, 0x05010f07, 0x05010f0b, 0x05030101, 0x05030105, 0x05030301, 0x05030307, 0x0503030f, - 0x05030505, 0x0503050b, 0x05030703, 0x05030709, 0x05030905, 0x05030b03, 0x05050103, 0x05050109, - 0x0505010f, 0x05050503, 0x05050507, 0x05050701, 0x0505070f, 0x05050903, 0x05050b07, 0x05050b0f, - 0x05050f03, 0x05050f09, 0x05070101, 0x05070105, 0x0507010b, 0x05070303, 0x05070505, 0x05070509, - 0x05070703, 0x05070707, 0x05070905, 0x05070b01, 0x05070d0d, 0x05090103, 0x0509010f, 0x05090501, - 0x05090507, 0x05090705, 0x0509070b, 0x05090903, 0x05090f05, 0x05090f0b, 0x050b0109, 0x050b0303, - 0x050b0505, 0x050b070f, 0x050b0901, 0x050b0b07, 0x050b0f01, 0x050d0101, 0x050d0105, 0x050d010f, - 0x050d0503, 0x050d0b0b, 0x050d0d03, 0x050f010b, 0x050f0303, 0x050f050d, 0x050f0701, 0x050f0907, - 0x050f0b01, 0x07010105, 0x07010303, 0x07010307, 0x0701030b, 0x0701030f, 0x07010505, 0x07010703, - 0x07010707, 0x0701070b, 0x07010905, 0x07010909, 0x0701090f, 0x07010b03, 0x07010d07, 0x07010f03, - 0x07030103, 0x07030107, 0x0703010b, 0x07030309, 0x07030503, 0x07030507, 0x07030901, 0x07030d01, - 0x07030f05, 0x07030f0d, 0x07050101, 0x07050305, 0x07050501, 0x07050705, 0x07050709, 0x07050b01, - 0x07070103, 0x07070301, 0x07070309, 0x07070503, 0x07070507, 0x0707050f, 0x07070701, 0x07070903, - 0x07070907, 0x0707090f, 0x07070b0b, 0x07070f07, 0x07090107, 0x07090303, 0x0709030d, 0x07090505, - 0x07090703, 0x07090b05, 0x07090d01, 0x07090d09, 0x070b0103, 0x070b0301, 0x070b0305, 0x070b050b, - 0x070b0705, 0x070b0909, 0x070b0b0d, 0x070b0f07, 0x070d030d, 0x070d0903, 0x070f0103, 0x070f0107, - 0x070f0501, 0x070f0505, 0x070f070b, 0x09010101, 0x09010109, 0x09010305, 0x09010501, 0x09010509, - 0x0901050f, 0x09010705, 0x09010903, 0x09010b01, 0x09010f01, 0x09030105, 0x0903010f, 0x09030303, - 0x09030307, 0x09030505, 0x09030701, 0x0903070b, 0x09030907, 0x09030b03, 0x09030b0b, 0x09050103, - 0x09050107, 0x09050301, 0x0905030b, 0x09050503, 0x09050707, 0x09050901, 0x09050b0f, 0x09050d05, - 0x09050f01, 0x09070109, 0x09070303, 0x09070307, 0x09070501, 0x09070505, 0x09070703, 0x0907070b, - 0x09090101, 0x09090105, 0x09090509, 0x0909070f, 0x09090901, 0x09090f03, 0x090b010b, 0x090b010f, - 0x090b0503, 0x090b0d05, 0x090d0307, 0x090d0709, 0x090d0d01, 0x090f0301, 0x090f030b, 0x090f0701, - 0x090f0907, 0x090f0b03, 0x0b010105, 0x0b010301, 0x0b010309, 0x0b010505, 0x0b010901, 0x0b010909, - 0x0b01090f, 0x0b010b05, 0x0b010d0d, 0x0b010f09, 0x0b030103, 0x0b030107, 0x0b03010b, 0x0b030305, - 0x0b030503, 0x0b030705, 0x0b030f05, 0x0b050101, 0x0b050303, 0x0b050507, 0x0b050701, 0x0b05070d, - 0x0b050b07, 0x0b070105, 0x0b07010f, 0x0b070301, 0x0b07050f, 0x0b070909, 0x0b070b03, 0x0b070d0b, - 0x0b070f07, 0x0b090103, 0x0b090109, 0x0b090501, 0x0b090705, 0x0b09090d, 0x0b0b0305, 0x0b0b050d, - 0x0b0b0b03, 0x0b0b0b07, 0x0b0d0905, 0x0b0f0105, 0x0b0f0109, 0x0b0f0505, 0x0d010303, 0x0d010307, - 0x0d01030b, 0x0d010703, 0x0d010707, 0x0d010d01, 0x0d030101, 0x0d030501, 0x0d03050f, 0x0d030d09, - 0x0d050305, 0x0d050709, 0x0d050905, 0x0d050b0b, 0x0d050d05, 0x0d050f01, 0x0d070101, 0x0d070309, - 0x0d070503, 0x0d070901, 0x0d09050b, 0x0d090907, 0x0d090d05, 0x0d0b0101, 0x0d0b0107, 0x0d0b0709, - 0x0d0b0d01, 0x0d0d010b, 0x0d0d0901, 0x0d0f0303, 0x0d0f0307, 0x0f010101, 0x0f010109, 0x0f01010f, - 0x0f010501, 0x0f010505, 0x0f01070d, 0x0f010901, 0x0f010b09, 0x0f010d05, 0x0f030105, 0x0f030303, - 0x0f030509, 0x0f030907, 0x0f03090b, 0x0f050103, 0x0f050109, 0x0f050301, 0x0f05030d, 0x0f050503, - 0x0f050701, 0x0f050b03, 0x0f070105, 0x0f070705, 0x0f07070b, 0x0f070b07, 0x0f090103, 0x0f09010b, - 0x0f090307, 0x0f090501, 0x0f090b01, 0x0f0b0505, 0x0f0b0905, 0x0f0d0105, 0x0f0d0703, 0x0f0f0101, -}; - -static const __device__ uint64_t iq1s_grid[512] = { - 0xffffffffffff0101, 0xffffffffff01ff00, 0xffffffffff010100, 0xffffffff00000000, - 0xffffffff01ff00ff, 0xffffffff01ff0001, 0xffffffff0101ffff, 0xffffffff0101ff01, - 0xffffff00ff000000, 0xffffff000000ff00, 0xffffff00000000ff, 0xffffff0000000100, - 0xffffff0000010000, 0xffffff0001000000, 0xffffff01ffff00ff, 0xffffff01ff01ff00, - 0xffffff01ff010100, 0xffffff0100000001, 0xffffff0101ffff00, 0xffffff0101ff0101, - 0xffffff0101010100, 0xffff00ffff00ff01, 0xffff00ffff0000ff, 0xffff00ff00ff0100, - 0xffff00ff0100ff00, 0xffff00ff010001ff, 0xffff0000ff0101ff, 0xffff000000ffff00, - 0xffff000000000000, 0xffff00000001ff01, 0xffff000001000101, 0xffff0000010100ff, - 0xffff0001ffff0100, 0xffff00010000ff00, 0xffff000100010101, 0xffff000101000000, - 0xffff01ffffff0000, 0xffff01ffff01ffff, 0xffff01ffff010100, 0xffff01ff00000000, - 0xffff01ff01ffffff, 0xffff01ff01ff0001, 0xffff01ff0101ffff, 0xffff01ff01010001, - 0xffff0100ffffff01, 0xffff01000000ffff, 0xffff010000000100, 0xffff010001ff01ff, - 0xffff010001000000, 0xffff0101ff000000, 0xffff0101000101ff, 0xffff010101ffff01, - 0xffff01010101ff00, 0xff00ffffff000000, 0xff00ffff00ffff00, 0xff00ffff00000001, - 0xff00ffff000001ff, 0xff00ffff01010000, 0xff00ff00ffff0000, 0xff00ff00ff00ff00, - 0xff00ff00ff0000ff, 0xff00ff00ff000100, 0xff00ff00ff010001, 0xff00ff0000ff0001, - 0xff00ff000000ffff, 0xff00ff0000000000, 0xff00ff000001ff00, 0xff00ff0000010100, - 0xff00ff0001ff0000, 0xff00ff000100ff00, 0xff00ff0001000100, 0xff00ff01ff000000, - 0xff00ff0100ff0000, 0xff00ff01000001ff, 0xff00ff0101010001, 0xff0000ff00000000, - 0xff0000ff0001ff00, 0xff0000ff00010100, 0xff000000ffff0101, 0xff000000ff000000, - 0xff000000ff01ff00, 0xff00000000ff0000, 0xff0000000000ff00, 0xff000000000000ff, - 0xff00000000000000, 0xff00000000000001, 0xff00000000000100, 0xff0000000001ffff, - 0xff00000000010000, 0xff00000001000000, 0xff00000001010100, 0xff000001ff00ff01, - 0xff000001ff0100ff, 0xff00000100000000, 0xff0000010001ff00, 0xff00000101ff0100, - 0xff0000010100ff00, 0xff0001ff00ff00ff, 0xff0001ff00000101, 0xff0001ff000100ff, - 0xff0001ff01000000, 0xff000100ff0001ff, 0xff0001000000ff01, 0xff00010000000000, - 0xff00010000010001, 0xff00010000010100, 0xff00010001ffff00, 0xff00010001ff0101, - 0xff00010001010000, 0xff000101ffffffff, 0xff000101ff000101, 0xff00010101ff00ff, - 0xff00010101000001, 0xff000101010100ff, 0xff01ffffff000101, 0xff01ffffff01ffff, - 0xff01ffffff01ff01, 0xff01ffffff0101ff, 0xff01ffff00000000, 0xff01ffff01ff0001, - 0xff01ffff0101ff01, 0xff01ff00ff000000, 0xff01ff0000ff0100, 0xff01ff000000ff01, - 0xff01ff0000010000, 0xff01ff00010000ff, 0xff01ff01ff01ff00, 0xff01ff0100000101, - 0xff0100ffffff0000, 0xff0100ffff010000, 0xff0100ff01ff00ff, 0xff0100ff01000100, - 0xff0100ff010100ff, 0xff010000ffffff01, 0xff01000000000000, 0xff0100000101ff00, - 0xff010001ffff00ff, 0xff010001ff000100, 0xff01000100ffff00, 0xff01000100010001, - 0xff01000101ff0001, 0xff010001010001ff, 0xff0101ffffffffff, 0xff0101ffff01ffff, - 0xff0101ffff010101, 0xff0101ff0000ff00, 0xff0101ff01010001, 0xff010100ff000000, - 0xff010100ff01ff01, 0xff01010000ff0001, 0xff01010000000100, 0xff01010001000000, - 0xff0101010100ffff, 0x00ffffff0000ff01, 0x00ffffff000000ff, 0x00ffffff00000100, - 0x00ffffff00010000, 0x00ffff00ffff0001, 0x00ffff00ff0000ff, 0x00ffff00ff000100, - 0x00ffff0000000000, 0x00ffff0001000100, 0x00ffff0001010001, 0x00ffff01ff00ff01, - 0x00ffff0100ff0100, 0x00ffff010000ff00, 0x00ffff01000100ff, 0x00ffff0101ff00ff, - 0x00ffff010101ff00, 0x00ff00ffffffffff, 0x00ff00ffffff01ff, 0x00ff00ffff000101, - 0x00ff00ff00000000, 0x00ff00ff000101ff, 0x00ff00ff01010101, 0x00ff0000ff000000, - 0x00ff0000ff01ffff, 0x00ff000000ff0000, 0x00ff00000000ff00, 0x00ff0000000000ff, - 0x00ff000000000000, 0x00ff000000000001, 0x00ff000000000100, 0x00ff000000010000, - 0x00ff000001ffff01, 0x00ff000001000000, 0x00ff0001ff000101, 0x00ff000100ffffff, - 0x00ff000100000000, 0x00ff0001010001ff, 0x00ff01ffff000000, 0x00ff01ff0001ff00, - 0x00ff01ff01ff0100, 0x00ff0100ff01ff01, 0x00ff010000ff00ff, 0x00ff010000ff0101, - 0x00ff010000000000, 0x00ff010000010101, 0x00ff01000100ff00, 0x00ff010001010000, - 0x00ff0101ffffff00, 0x00ff01010000ff01, 0x00ff010100000100, 0x00ff010101ff0000, - 0x0000ffffffff0100, 0x0000ffffff00ff00, 0x0000ffffff0000ff, 0x0000ffffff010000, - 0x0000ffff00000000, 0x0000ffff00010101, 0x0000ffff01ffff01, 0x0000ffff01000100, - 0x0000ff00ff000000, 0x0000ff00ff01ff00, 0x0000ff00ff0101ff, 0x0000ff0000ff0000, - 0x0000ff000000ff00, 0x0000ff00000000ff, 0x0000ff0000000000, 0x0000ff0000000001, - 0x0000ff0000000100, 0x0000ff0000010000, 0x0000ff0001ffffff, 0x0000ff0001ff01ff, - 0x0000ff0001000000, 0x0000ff000101ffff, 0x0000ff01ffff0101, 0x0000ff01ff010000, - 0x0000ff0100000000, 0x0000ff0101000101, 0x000000ffffff0001, 0x000000ffff000000, - 0x000000ff00ff0000, 0x000000ff0000ff00, 0x000000ff000000ff, 0x000000ff00000000, - 0x000000ff00000001, 0x000000ff00000100, 0x000000ff00010000, 0x000000ff01000000, - 0x000000ff0101ff00, 0x00000000ffff0000, 0x00000000ff00ff00, 0x00000000ff0000ff, - 0x00000000ff000000, 0x00000000ff000001, 0x00000000ff000100, 0x00000000ff010000, - 0x0000000000ffff00, 0x0000000000ff00ff, 0x0000000000ff0000, 0x0000000000ff0001, - 0x0000000000ff0100, 0x000000000000ffff, 0x000000000000ff00, 0x000000000000ff01, - 0x00000000000000ff, 0x0000000000000001, 0x00000000000001ff, 0x0000000000000100, - 0x0000000000000101, 0x000000000001ff00, 0x00000000000100ff, 0x0000000000010000, - 0x0000000000010001, 0x0000000000010100, 0x0000000001ff0000, 0x000000000100ff00, - 0x00000000010000ff, 0x0000000001000000, 0x0000000001000001, 0x0000000001000100, - 0x0000000001010000, 0x00000001ffff01ff, 0x00000001ff000000, 0x0000000100ff0000, - 0x000000010000ff00, 0x00000001000000ff, 0x0000000100000000, 0x0000000100000001, - 0x0000000100000100, 0x0000000100010000, 0x0000000101000000, 0x000001ffff00ff00, - 0x000001ffff010001, 0x000001ffff0101ff, 0x000001ff00ffff01, 0x000001ff0000ffff, - 0x000001ff00000000, 0x000001ff010000ff, 0x000001ff01010100, 0x00000100ffff0100, - 0x00000100ff000000, 0x0000010000ff0000, 0x000001000000ff00, 0x00000100000000ff, - 0x0000010000000000, 0x0000010000000001, 0x0000010000000100, 0x0000010000010000, - 0x0000010001000000, 0x000001000101ff01, 0x00000101ffff0001, 0x00000101ff01ffff, - 0x0000010100000000, 0x0000010101010100, 0x0001ffffff000000, 0x0001ffff00ffffff, - 0x0001ffff00000100, 0x0001ffff0001ff00, 0x0001ffff01000000, 0x0001ff00ffffff00, - 0x0001ff00ffff01ff, 0x0001ff00ff010000, 0x0001ff0000000000, 0x0001ff0000010001, - 0x0001ff0001ff0000, 0x0001ff0001010100, 0x0001ff01ff0000ff, 0x0001ff01ff000001, - 0x0001ff0100ffffff, 0x0001ff010001ffff, 0x0001ff01000101ff, 0x0001ff010100ff01, - 0x000100ffff00ffff, 0x000100ffff00ff01, 0x000100ffff000100, 0x000100ff00000000, - 0x000100ff000101ff, 0x000100ff01ff0101, 0x000100ff0100ffff, 0x000100ff01010101, - 0x00010000ff000000, 0x00010000ff010100, 0x0001000000ff0000, 0x000100000000ff00, - 0x00010000000000ff, 0x0001000000000000, 0x0001000000000001, 0x0001000000000100, - 0x0001000000010000, 0x0001000001ffff01, 0x0001000001000000, 0x0001000100ff0101, - 0x0001000100000000, 0x00010001010100ff, 0x000101ffffff01ff, 0x000101ffffff0101, - 0x000101ff00010000, 0x000101ff01ff0000, 0x000101ff0100ff01, 0x00010100ffff0000, - 0x0001010000000000, 0x000101000001ffff, 0x0001010000010101, 0x00010100010001ff, - 0x00010101ff00ff00, 0x00010101ff010001, 0x0001010100ffffff, 0x0001010100ff01ff, - 0x00010101000101ff, 0x0001010101ff0000, 0x000101010100ff01, 0x0001010101000101, - 0x01ffffffffff0101, 0x01ffffffff01ffff, 0x01ffffffff01ff01, 0x01ffffffff0101ff, - 0x01ffffffff010101, 0x01ffffff00000000, 0x01ffffff01ff01ff, 0x01ffffff01000101, - 0x01ffffff0101ff01, 0x01ffffff010100ff, 0x01ffff000000ff00, 0x01ffff0000000001, - 0x01ffff00000001ff, 0x01ffff0000010000, 0x01ffff0001ff0000, 0x01ffff01ffffffff, - 0x01ffff01ffff01ff, 0x01ffff01ff000000, 0x01ffff01ff01ffff, 0x01ffff01ff0101ff, - 0x01ffff010100ffff, 0x01ff00ffffff0000, 0x01ff00ffff010000, 0x01ff00ff00ffff01, - 0x01ff0000ff0000ff, 0x01ff000000000000, 0x01ff00000001ff01, 0x01ff000001ffffff, - 0x01ff000001010100, 0x01ff0001ffffff01, 0x01ff0001ff010001, 0x01ff000101ff0100, - 0x01ff000101000001, 0x01ff0001010100ff, 0x01ff01ffff00ffff, 0x01ff01ff00010001, - 0x01ff01ff01000000, 0x01ff01ff010101ff, 0x01ff0100ff000001, 0x01ff010000ffff00, - 0x01ff010000000100, 0x01ff010001ff01ff, 0x01ff01000101ffff, 0x01ff0101ffff00ff, - 0x01ff0101ffff0101, 0x01ff0101ff0101ff, 0x01ff010100010000, 0x0100ffff00ff00ff, - 0x0100ffff00ff0001, 0x0100ffff00000100, 0x0100ffff0100ff00, 0x0100ff00ffff0000, - 0x0100ff00ff00ffff, 0x0100ff00ff00ff01, 0x0100ff00ff000100, 0x0100ff00ff010000, - 0x0100ff0000000000, 0x0100ff00000100ff, 0x0100ff0001ff0101, 0x0100ff0001010101, - 0x0100ff0100ff00ff, 0x0100ff0100ff0001, 0x0100ff0100000100, 0x0100ff0100010001, - 0x0100ff0101000000, 0x010000ffff00ff00, 0x010000ff0000ffff, 0x010000ff00000000, - 0x010000ff010001ff, 0x010000ff01010001, 0x01000000ffffff00, 0x01000000ffff0101, - 0x01000000ff000000, 0x01000000ff0100ff, 0x01000000ff010101, 0x0100000000ff0000, - 0x010000000000ff00, 0x01000000000000ff, 0x0100000000000000, 0x0100000000000001, - 0x0100000000000100, 0x0100000000010000, 0x0100000001000000, 0x0100000100000000, - 0x01000001000101ff, 0x0100000101ffff01, 0x010001ffff000101, 0x010001ff00ff0100, - 0x010001ff0000ff00, 0x010001ff000100ff, 0x010001ff01ffffff, 0x01000100ffff0000, - 0x01000100ff0001ff, 0x0100010000000000, 0x010001000001ff00, 0x0100010001ff0000, - 0x01000100010000ff, 0x0100010001000101, 0x01000101ff00ff01, 0x0100010100ff0100, - 0x010001010000ffff, 0x0100010101010001, 0x0101ffffffff0101, 0x0101ffffff0001ff, - 0x0101ffffff01ffff, 0x0101ffffff010101, 0x0101ffff00000000, 0x0101ffff0101ffff, - 0x0101ffff010101ff, 0x0101ff00ff000000, 0x0101ff0000ff0100, 0x0101ff000000ff00, - 0x0101ff0000010000, 0x0101ff00010000ff, 0x0101ff0001000001, 0x0101ff01ff010101, - 0x0101ff0100000000, 0x0101ff010101ff00, 0x010100ffffff0000, 0x010100ffff010000, - 0x010100ff00ff01ff, 0x010100ff000000ff, 0x010100ff00000101, 0x010100ff01ffff00, - 0x01010000ffffff01, 0x01010000ff000100, 0x01010000ff01ff01, 0x0101000000000000, - 0x01010000000100ff, 0x010100000101ff01, 0x01010001ffff0000, 0x01010001ff00ffff, - 0x01010001ff010000, 0x0101000101ffffff, 0x0101000101ff01ff, 0x0101000101010101, - 0x010101ffff01ffff, 0x010101ff00000000, 0x010101ff0001ff01, 0x010101ff0101ffff, - 0x010101ff010101ff, 0x01010100ffffffff, 0x01010100ff000001, 0x010101000000ff00, - 0x0101010001010000, 0x0101010100ff0001, 0x010101010001ff01, 0x010101010101ffff, -}; - -static const __device__ uint8_t ksigns_iq2xs[128] = { - 0, 129, 130, 3, 132, 5, 6, 135, 136, 9, 10, 139, 12, 141, 142, 15, - 144, 17, 18, 147, 20, 149, 150, 23, 24, 153, 154, 27, 156, 29, 30, 159, - 160, 33, 34, 163, 36, 165, 166, 39, 40, 169, 170, 43, 172, 45, 46, 175, - 48, 177, 178, 51, 180, 53, 54, 183, 184, 57, 58, 187, 60, 189, 190, 63, - 192, 65, 66, 195, 68, 197, 198, 71, 72, 201, 202, 75, 204, 77, 78, 207, - 80, 209, 210, 83, 212, 85, 86, 215, 216, 89, 90, 219, 92, 221, 222, 95, - 96, 225, 226, 99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111, - 240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255, -}; - -//#if __CUDA_ARCH__ >= MIN_CC_DP4A // lowest compute capability for integer intrinsics -static const __device__ uint64_t ksigns64[128] = { - 0x0000000000000000, 0xff000000000000ff, 0xff0000000000ff00, 0x000000000000ffff, - 0xff00000000ff0000, 0x0000000000ff00ff, 0x0000000000ffff00, 0xff00000000ffffff, - 0xff000000ff000000, 0x00000000ff0000ff, 0x00000000ff00ff00, 0xff000000ff00ffff, - 0x00000000ffff0000, 0xff000000ffff00ff, 0xff000000ffffff00, 0x00000000ffffffff, - 0xff0000ff00000000, 0x000000ff000000ff, 0x000000ff0000ff00, 0xff0000ff0000ffff, - 0x000000ff00ff0000, 0xff0000ff00ff00ff, 0xff0000ff00ffff00, 0x000000ff00ffffff, - 0x000000ffff000000, 0xff0000ffff0000ff, 0xff0000ffff00ff00, 0x000000ffff00ffff, - 0xff0000ffffff0000, 0x000000ffffff00ff, 0x000000ffffffff00, 0xff0000ffffffffff, - 0xff00ff0000000000, 0x0000ff00000000ff, 0x0000ff000000ff00, 0xff00ff000000ffff, - 0x0000ff0000ff0000, 0xff00ff0000ff00ff, 0xff00ff0000ffff00, 0x0000ff0000ffffff, - 0x0000ff00ff000000, 0xff00ff00ff0000ff, 0xff00ff00ff00ff00, 0x0000ff00ff00ffff, - 0xff00ff00ffff0000, 0x0000ff00ffff00ff, 0x0000ff00ffffff00, 0xff00ff00ffffffff, - 0x0000ffff00000000, 0xff00ffff000000ff, 0xff00ffff0000ff00, 0x0000ffff0000ffff, - 0xff00ffff00ff0000, 0x0000ffff00ff00ff, 0x0000ffff00ffff00, 0xff00ffff00ffffff, - 0xff00ffffff000000, 0x0000ffffff0000ff, 0x0000ffffff00ff00, 0xff00ffffff00ffff, - 0x0000ffffffff0000, 0xff00ffffffff00ff, 0xff00ffffffffff00, 0x0000ffffffffffff, - 0xffff000000000000, 0x00ff0000000000ff, 0x00ff00000000ff00, 0xffff00000000ffff, - 0x00ff000000ff0000, 0xffff000000ff00ff, 0xffff000000ffff00, 0x00ff000000ffffff, - 0x00ff0000ff000000, 0xffff0000ff0000ff, 0xffff0000ff00ff00, 0x00ff0000ff00ffff, - 0xffff0000ffff0000, 0x00ff0000ffff00ff, 0x00ff0000ffffff00, 0xffff0000ffffffff, - 0x00ff00ff00000000, 0xffff00ff000000ff, 0xffff00ff0000ff00, 0x00ff00ff0000ffff, - 0xffff00ff00ff0000, 0x00ff00ff00ff00ff, 0x00ff00ff00ffff00, 0xffff00ff00ffffff, - 0xffff00ffff000000, 0x00ff00ffff0000ff, 0x00ff00ffff00ff00, 0xffff00ffff00ffff, - 0x00ff00ffffff0000, 0xffff00ffffff00ff, 0xffff00ffffffff00, 0x00ff00ffffffffff, - 0x00ffff0000000000, 0xffffff00000000ff, 0xffffff000000ff00, 0x00ffff000000ffff, - 0xffffff0000ff0000, 0x00ffff0000ff00ff, 0x00ffff0000ffff00, 0xffffff0000ffffff, - 0xffffff00ff000000, 0x00ffff00ff0000ff, 0x00ffff00ff00ff00, 0xffffff00ff00ffff, - 0x00ffff00ffff0000, 0xffffff00ffff00ff, 0xffffff00ffffff00, 0x00ffff00ffffffff, - 0xffffffff00000000, 0x00ffffff000000ff, 0x00ffffff0000ff00, 0xffffffff0000ffff, - 0x00ffffff00ff0000, 0xffffffff00ff00ff, 0xffffffff00ffff00, 0x00ffffff00ffffff, - 0x00ffffffff000000, 0xffffffffff0000ff, 0xffffffffff00ff00, 0x00ffffffff00ffff, - 0xffffffffffff0000, 0x00ffffffffff00ff, 0x00ffffffffffff00, 0xffffffffffffffff, -}; -//#endif - -static const __device__ uint8_t kmask_iq2xs[8] = {1, 2, 4, 8, 16, 32, 64, 128}; - inline bool ggml_cuda_supports_mmq(enum ggml_type type) { switch (type) { case GGML_TYPE_Q4_0: @@ -2459,11 +1503,15 @@ static __global__ void dequantize_block_iq1_s(const void * __restrict__ vx, dst_ const int il = tid/8; // 0...3 const int ib = tid%8; // 0...7 dst_t * y = yy + i*QK_K + 32*ib + 8*il; - const int i8 = 4*ib+il; - uint8_t h = x[i].scales[i8/2] >> 4*(i8%2); - const int8_t * grid = (const int8_t *)(iq1s_grid + (x[i].qs[i8] | ((h & 8) << 5))); - const float d = (float)x[i].d * (2*(h & 7) + 1); - for (int j = 0; j < 8; ++j) y[j] = d * grid[j]; + const float delta = x[i].qh[ib] & 0x8000 ? -1 - IQ1S_DELTA : -1 + IQ1S_DELTA; + const float d = (float)x[i].d * (2*((x[i].qh[ib] >> 12) & 7) + 1); + uint32_t grid32[2]; const int8_t * q = (const int8_t *)grid32; + grid32[0] = iq1s_grid_gpu[x[i].qs[4*ib+il] | (((x[i].qh[ib] >> 3*il) & 7) << 8)]; + grid32[1] = (grid32[0] >> 4) & 0x0f0f0f0f; + grid32[0] &= 0x0f0f0f0f; + for (int j = 0; j < 8; ++j) { + y[j] = d * (q[j] + delta); + } #else assert(false); #endif @@ -4303,7 +3351,7 @@ static __device__ __forceinline__ float vec_dot_q2_K_q8_1( #pragma unroll for (int i = 0; i < QR2_K; ++ i) { u[i] = get_int_from_int8_aligned(bq8_1[bq8_offset + i].qs, iqs % QI8_1); - d8[i] = __low2half(bq8_1[bq8_offset + i].ds); + d8[i] = __low2float(bq8_1[bq8_offset + i].ds); } return vec_dot_q2_K_q8_1_impl_mmvq(v, u, scales, bq2_K->dm, d8); @@ -4425,7 +3473,7 @@ static __device__ __forceinline__ float vec_dot_q3_K_q8_1( #pragma unroll for (int i = 0; i < QR3_K; ++i) { u[i] = get_int_from_int8_aligned(bq8_1[bq8_offset + i].qs, iqs % QI8_1); - d8[i] = __low2half(bq8_1[bq8_offset + i].ds); + d8[i] = __low2float(bq8_1[bq8_offset + i].ds); } return vec_dot_q3_K_q8_1_impl_mmvq(vl, vh, u, bq3_K->scales, scale_offset, d, d8); @@ -4594,7 +3642,7 @@ static __device__ __forceinline__ float vec_dot_q4_K_q8_1( for (int i = 0; i < QR4_K; ++i) { const block_q8_1 * bq8i = bq8_1 + bq8_offset + i; - d8[i] = __low2half(bq8i->ds); + d8[i] = __low2float(bq8i->ds); const int * q8 = (const int *)bq8i->qs + ((iqs/2)%4); u[2*i+0] = q8[0]; @@ -4959,7 +4007,7 @@ static __device__ __forceinline__ float vec_dot_q6_K_q8_1( #pragma unroll for (int i = 0; i < QR6_K; ++i) { u[i] = get_int_from_int8_aligned(bq8_1[bq8_offset + 2*i].qs, iqs % QI8_1); - d8[i] = __low2half(bq8_1[bq8_offset + 2*i].ds); + d8[i] = __low2float(bq8_1[bq8_offset + 2*i].ds); } return vec_dot_q6_K_q8_1_impl_mmvq(vl, vh, u, scales, bq6_K->d, d8); @@ -5275,44 +4323,36 @@ static __device__ __forceinline__ float vec_dot_iq3_s_q8_1( #endif } - static __device__ __forceinline__ float vec_dot_iq1_s_q8_1( const void * __restrict__ vbq, const block_q8_1 * __restrict__ bq8_1, const int & iqs) { #if QK_K == 256 const block_iq1_s * bq1 = (const block_iq1_s *) vbq; const int ib32 = iqs; - int sumi1 = 0, sumi2 = 0, sumi3 = 0, sumi4 = 0; - const uint8_t h1 = bq1->scales[2*ib32+0]; - const uint8_t h2 = bq1->scales[2*ib32+1]; + int sumi = 0; #if __CUDA_ARCH__ >= MIN_CC_DP4A // lowest compute capability for integer intrinsics const int * q8 = (const int *)bq8_1[ib32].qs; - const int * grid1 = (const int *)(iq1s_grid + (bq1->qs[4*ib32+0] | ((h1 & 0x08) << 5))); - const int * grid2 = (const int *)(iq1s_grid + (bq1->qs[4*ib32+1] | ((h1 & 0x80) << 1))); - const int * grid3 = (const int *)(iq1s_grid + (bq1->qs[4*ib32+2] | ((h2 & 0x08) << 5))); - const int * grid4 = (const int *)(iq1s_grid + (bq1->qs[4*ib32+3] | ((h2 & 0x80) << 1))); - for (int j = 0; j < 2; ++j) { - sumi1 = __dp4a(q8[j+0], grid1[j], sumi1); - sumi2 = __dp4a(q8[j+2], grid2[j], sumi2); - sumi3 = __dp4a(q8[j+4], grid3[j], sumi3); - sumi4 = __dp4a(q8[j+6], grid4[j], sumi4); + for (int l = 0; l < 4; ++l) { + const int * grid = (const int *)(iq1s_grid_gpu + (bq1->qs[4*ib32+l] | (((bq1->qh[ib32] >> 3*l) & 7) << 8))); + int grid0 = grid[0] & 0x0f0f0f0f; + int grid1 = (grid[0] >> 4) & 0x0f0f0f0f; + sumi = __dp4a(q8[2*l+1], grid1, __dp4a(q8[2*l+0], grid0, sumi)); } #else - const int8_t * q8 = bq8_1[ib32].qs; - const int8_t * grid1 = (const int8_t *)(iq1s_grid + (bq1->qs[4*ib32+0] | ((h1 & 0x08) << 5))); - const int8_t * grid2 = (const int8_t *)(iq1s_grid + (bq1->qs[4*ib32+1] | ((h1 & 0x80) << 1))); - const int8_t * grid3 = (const int8_t *)(iq1s_grid + (bq1->qs[4*ib32+2] | ((h2 & 0x08) << 5))); - const int8_t * grid4 = (const int8_t *)(iq1s_grid + (bq1->qs[4*ib32+3] | ((h2 & 0x80) << 1))); - for (int j = 0; j < 8; ++j) { - sumi1 += q8[j+ 0] * grid1[j]; - sumi2 += q8[j+ 8] * grid2[j]; - sumi3 += q8[j+16] * grid3[j]; - sumi4 += q8[j+24] * grid4[j]; + const int8_t * q8 = bq8_1[ib32].qs; + for (int l = 0; l < 4; ++l) { + const uint8_t * grid = (const uint8_t *)(iq1s_grid_gpu + (bq1->qs[4*ib32+l] | (((bq1->qh[ib32] >> 3*l) & 7) << 8))); + for (int j = 0; j < 4; ++j) { + sumi += q8[j] * (grid[j] & 0xf) + q8[j+4] * (grid[j] >> 4); + } + q8 += 8; } #endif - const float d = (float)bq1->d * __low2float(bq8_1[ib32].ds); - return d * (sumi1 * (2*(h1 & 7) + 1) + sumi2 * (2*((h1 >> 4) & 7) + 1) + - sumi3 * (2*(h2 & 7) + 1) + sumi4 * (2*((h2 >> 4) & 7) + 1)); + const float delta = bq1->qh[ib32] & 0x8000 ? -1-IQ1S_DELTA : -1+IQ1S_DELTA; + const float d1q = (float)bq1->d * (2*((bq1->qh[ib32] >> 12) & 7) + 1); + const float d = d1q * __low2float (bq8_1[ib32].ds); + const float m = d1q * __high2float(bq8_1[ib32].ds); + return d * sumi + m * delta; #else assert(false); return 0.f; @@ -5504,7 +4544,7 @@ static __device__ __forceinline__ void mul_mat_q( *dsi_dst = *dsi_src; } else { float * dfi_dst = (float *) dsi_dst; - *dfi_dst = __low2half(*dsi_src); + *dfi_dst = __low2float(*dsi_src); } } @@ -11604,8 +10644,20 @@ GGML_CALL void ggml_cuda_get_device_description(int device, char * description, #define UNUSED GGML_UNUSED struct ggml_backend_cuda_context { + explicit ggml_backend_cuda_context(int device) : + device(device), + name(GGML_CUDA_NAME + std::to_string(device)) { + } + + ~ggml_backend_cuda_context() { + if (copy_event != nullptr) { + CUDA_CHECK(cudaEventDestroy(copy_event)); + } + } + int device; std::string name; + cudaEvent_t copy_event = nullptr; }; // cuda buffer @@ -11695,9 +10747,8 @@ GGML_CALL static void ggml_backend_cuda_buffer_set_tensor(ggml_backend_buffer_t ggml_backend_cuda_buffer_context * ctx = (ggml_backend_cuda_buffer_context *)buffer->context; ggml_cuda_set_device(ctx->device); - CUDA_CHECK(cudaDeviceSynchronize()); - CUDA_CHECK(cudaMemcpy((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice)); - CUDA_CHECK(cudaDeviceSynchronize()); + CUDA_CHECK(cudaMemcpyAsync((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, cudaStreamPerThread)); + CUDA_CHECK(cudaStreamSynchronize(cudaStreamPerThread)); } GGML_CALL static void ggml_backend_cuda_buffer_get_tensor(ggml_backend_buffer_t buffer, const ggml_tensor * tensor, void * data, size_t offset, size_t size) { @@ -11706,26 +10757,25 @@ GGML_CALL static void ggml_backend_cuda_buffer_get_tensor(ggml_backend_buffer_t ggml_backend_cuda_buffer_context * ctx = (ggml_backend_cuda_buffer_context *)buffer->context; ggml_cuda_set_device(ctx->device); - CUDA_CHECK(cudaDeviceSynchronize()); - CUDA_CHECK(cudaMemcpy(data, (const char *)tensor->data + offset, size, cudaMemcpyDeviceToHost)); - CUDA_CHECK(cudaDeviceSynchronize()); + CUDA_CHECK(cudaMemcpyAsync(data, (const char *)tensor->data + offset, size, cudaMemcpyDeviceToHost, cudaStreamPerThread)); + CUDA_CHECK(cudaStreamSynchronize(cudaStreamPerThread)); } GGML_CALL static bool ggml_backend_cuda_buffer_cpy_tensor(ggml_backend_buffer_t buffer, const ggml_tensor * src, ggml_tensor * dst) { if (ggml_backend_buffer_is_cuda(src->buffer)) { ggml_backend_cuda_buffer_context * src_ctx = (ggml_backend_cuda_buffer_context *)src->buffer->context; - ggml_backend_cuda_buffer_context * dst_ctx = (ggml_backend_cuda_buffer_context *)buffer->context; - - ggml_cuda_set_device(src_ctx->device); - CUDA_CHECK(cudaDeviceSynchronize()); - ggml_cuda_set_device(dst_ctx->device); - CUDA_CHECK(cudaDeviceSynchronize()); - CUDA_CHECK(cudaMemcpy((char *)dst->data, (const char *)src->data, ggml_nbytes(src), cudaMemcpyDeviceToDevice)); - CUDA_CHECK(cudaDeviceSynchronize()); - + ggml_backend_cuda_buffer_context * dst_ctx = (ggml_backend_cuda_buffer_context *)dst->buffer->context; + if (src_ctx->device == dst_ctx->device) { + CUDA_CHECK(cudaMemcpyAsync(dst->data, src->data, ggml_nbytes(src), cudaMemcpyDeviceToDevice, cudaStreamPerThread)); + } else { + CUDA_CHECK(cudaMemcpyPeerAsync(dst->data, dst_ctx->device, src->data, src_ctx->device, ggml_nbytes(src), cudaStreamPerThread)); + } + CUDA_CHECK(cudaStreamSynchronize(cudaStreamPerThread)); return true; } return false; + + UNUSED(buffer); } GGML_CALL static void ggml_backend_cuda_buffer_clear(ggml_backend_buffer_t buffer, uint8_t value) { @@ -11970,7 +11020,11 @@ GGML_CALL static void ggml_backend_cuda_split_buffer_set_tensor(ggml_backend_buf } const char * buf_host = (const char *)data + offset_split; - CUDA_CHECK(cudaMemcpy(extra->data_device[id], buf_host, original_size, cudaMemcpyHostToDevice)); + CUDA_CHECK(cudaMemcpyAsync(extra->data_device[id], buf_host, original_size, cudaMemcpyHostToDevice, cudaStreamPerThread)); + } + + for (int id = 0; id < g_device_count; ++id) { + CUDA_CHECK(cudaStreamSynchronize(cudaStreamPerThread)); } } @@ -12004,7 +11058,11 @@ GGML_CALL static void ggml_backend_cuda_split_buffer_get_tensor(ggml_backend_buf } char * buf_host = (char *)data + offset_split; - CUDA_CHECK(cudaMemcpy(buf_host, extra->data_device[id], original_size, cudaMemcpyDeviceToHost)); + CUDA_CHECK(cudaMemcpyAsync(buf_host, extra->data_device[id], original_size, cudaMemcpyDeviceToHost, cudaStreamPerThread)); + } + + for (int id = 0; id < g_device_count; ++id) { + CUDA_CHECK(cudaStreamSynchronize(cudaStreamPerThread)); } } @@ -12183,6 +11241,10 @@ GGML_CALL ggml_backend_buffer_type_t ggml_backend_cuda_host_buffer_type() { return &ggml_backend_cuda_buffer_type_host; } +//static bool ggml_backend_buffer_is_cuda_host(ggml_backend_buffer_t buffer) { +// return buffer->buft->iface.get_name == ggml_backend_cuda_host_buffer_type_name; +//} + // backend GGML_CALL static const char * ggml_backend_cuda_name(ggml_backend_t backend) { @@ -12206,8 +11268,9 @@ GGML_CALL static ggml_backend_buffer_type_t ggml_backend_cuda_get_default_buffer GGML_CALL static void ggml_backend_cuda_set_tensor_async(ggml_backend_t backend, ggml_tensor * tensor, const void * data, size_t offset, size_t size) { ggml_backend_cuda_context * cuda_ctx = (ggml_backend_cuda_context *)backend->context; + ggml_backend_buffer_t buf = tensor->view_src ? tensor->view_src->buffer : tensor->buffer; - GGML_ASSERT(tensor->buffer->buft == ggml_backend_cuda_buffer_type(cuda_ctx->device) && "unsupported buffer type"); + GGML_ASSERT(buf->buft == ggml_backend_cuda_buffer_type(cuda_ctx->device) && "unsupported buffer type"); GGML_ASSERT(tensor->backend == GGML_BACKEND_TYPE_GPU); CUDA_CHECK(cudaMemcpyAsync((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, g_cudaStreams[cuda_ctx->device][0])); @@ -12215,22 +11278,61 @@ GGML_CALL static void ggml_backend_cuda_set_tensor_async(ggml_backend_t backend, GGML_CALL static void ggml_backend_cuda_get_tensor_async(ggml_backend_t backend, const ggml_tensor * tensor, void * data, size_t offset, size_t size) { ggml_backend_cuda_context * cuda_ctx = (ggml_backend_cuda_context *)backend->context; + ggml_backend_buffer_t buf = tensor->view_src ? tensor->view_src->buffer : tensor->buffer; - GGML_ASSERT(tensor->buffer->buft == ggml_backend_cuda_buffer_type(cuda_ctx->device) && "unsupported buffer type"); + GGML_ASSERT(buf->buft == ggml_backend_cuda_buffer_type(cuda_ctx->device) && "unsupported buffer type"); GGML_ASSERT(tensor->backend == GGML_BACKEND_TYPE_GPU); CUDA_CHECK(cudaMemcpyAsync(data, (const char *)tensor->data + offset, size, cudaMemcpyDeviceToHost, g_cudaStreams[cuda_ctx->device][0])); } -GGML_CALL static bool ggml_backend_cuda_cpy_tensor_async(ggml_backend_t backend, const ggml_tensor * src, ggml_tensor * dst) { - ggml_backend_cuda_context * cuda_ctx = (ggml_backend_cuda_context *)backend->context; +GGML_CALL static bool ggml_backend_cuda_cpy_tensor_async(ggml_backend_t backend_src, ggml_backend_t backend_dst, const ggml_tensor * src, ggml_tensor * dst) { + GGML_ASSERT(ggml_backend_is_cuda(backend_src) || ggml_backend_is_cuda(backend_dst)); - if (dst->buffer->buft == ggml_backend_cuda_buffer_type(cuda_ctx->device) && ggml_backend_buffer_is_cuda(src->buffer)) { - CUDA_CHECK(cudaMemcpyAsync(dst->data, src->data, ggml_nbytes(dst), cudaMemcpyDeviceToDevice, g_cudaStreams[cuda_ctx->device][0])); - return true; + ggml_backend_buffer_t buf_src = src->view_src ? src->view_src->buffer : src->buffer; + ggml_backend_buffer_t buf_dst = dst->view_src ? dst->view_src->buffer : dst->buffer; + + if (!ggml_backend_buffer_is_cuda(src->buffer)) { + return false; } - return false; + if (!ggml_backend_buffer_is_cuda(dst->buffer)) { + return false; + } + + // device -> device + ggml_backend_cuda_context * cuda_ctx_src = (ggml_backend_cuda_context *)backend_src->context; + ggml_backend_cuda_context * cuda_ctx_dst = (ggml_backend_cuda_context *)backend_dst->context; + + if (backend_src != backend_dst) { + ggml_backend_cuda_buffer_context * buf_ctx_src = (ggml_backend_cuda_buffer_context *)buf_src->context; + ggml_backend_cuda_buffer_context * buf_ctx_dst = (ggml_backend_cuda_buffer_context *)buf_dst->context; + + GGML_ASSERT(cuda_ctx_src->device == buf_ctx_src->device); + GGML_ASSERT(cuda_ctx_dst->device == buf_ctx_dst->device); + + if (!cuda_ctx_src->copy_event) { + ggml_cuda_set_device(cuda_ctx_src->device); + CUDA_CHECK(cudaEventCreateWithFlags(&cuda_ctx_src->copy_event, cudaEventDisableTiming)); + } + + // copy on src stream + if (cuda_ctx_src->device == cuda_ctx_dst->device) { + CUDA_CHECK(cudaMemcpyAsync(dst->data, src->data, ggml_nbytes(dst), cudaMemcpyDeviceToDevice, g_cudaStreams[cuda_ctx_dst->device][0])); + } else { + CUDA_CHECK(cudaMemcpyPeerAsync(dst->data, cuda_ctx_dst->device, src->data, cuda_ctx_src->device, ggml_nbytes(dst), g_cudaStreams[cuda_ctx_src->device][0])); + } + + // record event on src stream + CUDA_CHECK(cudaEventRecord(cuda_ctx_src->copy_event, g_cudaStreams[cuda_ctx_src->device][0])); + + // wait on dst stream for the copy to complete + CUDA_CHECK(cudaStreamWaitEvent(g_cudaStreams[cuda_ctx_dst->device][0], cuda_ctx_src->copy_event, 0)); + } else { + // src and dst are on the same backend + CUDA_CHECK(cudaMemcpyAsync(dst->data, src->data, ggml_nbytes(dst), cudaMemcpyDeviceToDevice, g_cudaStreams[cuda_ctx_dst->device][0])); + } + return true; } GGML_CALL static void ggml_backend_cuda_synchronize(ggml_backend_t backend) { @@ -12407,6 +11509,52 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons UNUSED(backend); } +static ggml_backend_event_t ggml_backend_cuda_event_new(ggml_backend_t backend) { + ggml_backend_cuda_context * cuda_ctx = (ggml_backend_cuda_context *)backend->context; + + ggml_cuda_set_device(cuda_ctx->device); + + cudaEvent_t event; + CUDA_CHECK(cudaEventCreateWithFlags(&event, cudaEventDisableTiming)); + + return new ggml_backend_event { + /* .backend = */ backend, + /* .context = */ event, + }; +} + +static void ggml_backend_cuda_event_free(ggml_backend_event_t event) { + CUDA_CHECK(cudaEventDestroy((cudaEvent_t)event->context)); + + delete event; +} + +static void ggml_backend_cuda_event_record(ggml_backend_event_t event) { + ggml_backend_cuda_context * cuda_ctx = (ggml_backend_cuda_context *)event->backend->context; + + CUDA_CHECK(cudaEventRecord((cudaEvent_t)event->context, g_cudaStreams[cuda_ctx->device][0])); +} + +static void ggml_backend_cuda_event_wait(ggml_backend_t backend, ggml_backend_event_t event) { + ggml_backend_cuda_context * cuda_ctx = (ggml_backend_cuda_context *)backend->context; + + if (ggml_backend_is_cuda(event->backend)) { + CUDA_CHECK(cudaStreamWaitEvent(g_cudaStreams[cuda_ctx->device][0], (cudaEvent_t)event->context, 0)); + } else { + // untested + auto wait_fn = [](void * user_data) { + ggml_backend_event_t event = (ggml_backend_event_t)user_data; + ggml_backend_event_synchronize(event); + }; + + CUDA_CHECK(cudaLaunchHostFunc(g_cudaStreams[cuda_ctx->device][0], wait_fn, event)); + } +} + +static void ggml_backend_cuda_event_synchronize(ggml_backend_event_t event) { + CUDA_CHECK(cudaEventSynchronize((cudaEvent_t)event->context)); +} + static ggml_backend_i ggml_backend_cuda_interface = { /* .get_name = */ ggml_backend_cuda_name, /* .free = */ ggml_backend_cuda_free, @@ -12420,6 +11568,11 @@ static ggml_backend_i ggml_backend_cuda_interface = { /* .graph_plan_compute = */ NULL, /* .graph_compute = */ ggml_backend_cuda_graph_compute, /* .supports_op = */ ggml_backend_cuda_supports_op, + /* .event_new = */ ggml_backend_cuda_event_new, + /* .event_free = */ ggml_backend_cuda_event_free, + /* .event_record = */ ggml_backend_cuda_event_record, + /* .event_wait = */ ggml_backend_cuda_event_wait, + /* .event_synchronize = */ ggml_backend_cuda_event_synchronize, }; static ggml_guid_t ggml_backend_cuda_guid() { @@ -12438,10 +11591,11 @@ GGML_CALL ggml_backend_t ggml_backend_cuda_init(int device) { // not strictly necessary, but it may reduce the overhead of the first graph_compute ggml_cuda_set_main_device(device); - ggml_backend_cuda_context * ctx = new ggml_backend_cuda_context { - /* .device = */ device, - /* .name = */ GGML_CUDA_NAME + std::to_string(device), - }; + ggml_backend_cuda_context * ctx = new ggml_backend_cuda_context(device); + if (ctx == nullptr) { + fprintf(stderr, "%s: error: failed to allocate context\n", __func__); + return nullptr; + } ggml_backend_t cuda_backend = new ggml_backend { /* .guid = */ ggml_backend_cuda_guid(), diff --git a/src/ggml-impl.h b/src/ggml-impl.h index c5637e4d4..e68b72877 100644 --- a/src/ggml-impl.h +++ b/src/ggml-impl.h @@ -53,26 +53,30 @@ extern "C" { // #include +typedef __fp16 ggml_fp16_internal_t; + #define GGML_COMPUTE_FP16_TO_FP32(x) ggml_compute_fp16_to_fp32(x) #define GGML_COMPUTE_FP32_TO_FP16(x) ggml_compute_fp32_to_fp16(x) #define GGML_FP16_TO_FP32(x) ggml_compute_fp16_to_fp32(x) static inline float ggml_compute_fp16_to_fp32(ggml_fp16_t h) { - __fp16 tmp; + ggml_fp16_internal_t tmp; memcpy(&tmp, &h, sizeof(ggml_fp16_t)); return (float)tmp; } static inline ggml_fp16_t ggml_compute_fp32_to_fp16(float f) { ggml_fp16_t res; - __fp16 tmp = f; + ggml_fp16_internal_t tmp = f; memcpy(&res, &tmp, sizeof(ggml_fp16_t)); return res; } #else +typedef uint16_t ggml_fp16_internal_t; + #ifdef __wasm_simd128__ #include #else diff --git a/src/ggml-kompute.cpp b/src/ggml-kompute.cpp index 83a7822fd..4caf2c9e7 100644 --- a/src/ggml-kompute.cpp +++ b/src/ggml-kompute.cpp @@ -1951,6 +1951,11 @@ static struct ggml_backend_i kompute_backend_i = { /* .graph_plan_compute = */ NULL, /* .graph_compute = */ ggml_backend_kompute_graph_compute, /* .supports_op = */ ggml_backend_kompute_supports_op, + /* .event_new = */ NULL, + /* .event_free = */ NULL, + /* .event_record = */ NULL, + /* .event_wait = */ NULL, + /* .event_synchronize = */ NULL, }; static ggml_guid_t ggml_backend_kompute_guid() { diff --git a/src/ggml-metal.m b/src/ggml-metal.m index 00df22838..c3451a79b 100644 --- a/src/ggml-metal.m +++ b/src/ggml-metal.m @@ -280,6 +280,11 @@ static void ggml_metal_log(enum ggml_log_level level, const char * format, ...){ id metal_library; // load library + // + // - first check if the library is embedded + // - then check if the library is in the bundle + // - if not found, load the source and compile it + // - if that fails, return NULL { NSBundle * bundle = nil; #ifdef SWIFT_PACKAGE @@ -287,12 +292,21 @@ static void ggml_metal_log(enum ggml_log_level level, const char * format, ...){ #else bundle = [NSBundle bundleForClass:[GGMLMetalClass class]]; #endif + NSError * error = nil; - NSString * libPath = [bundle pathForResource:@"default" ofType:@"metallib"]; - if (libPath != nil) { + +#if GGML_METAL_EMBED_LIBRARY + const bool try_metallib = false; +#else + const bool try_metallib = true; +#endif + + NSString * path_lib = [bundle pathForResource:@"default" ofType:@"metallib"]; + if (try_metallib && path_lib != nil) { // pre-compiled library found - NSURL * libURL = [NSURL fileURLWithPath:libPath]; - GGML_METAL_LOG_INFO("%s: loading '%s'\n", __func__, [libPath UTF8String]); + NSURL * libURL = [NSURL fileURLWithPath:path_lib]; + GGML_METAL_LOG_INFO("%s: loading '%s'\n", __func__, [path_lib UTF8String]); + metal_library = [ctx->device newLibraryWithURL:libURL error:&error]; if (error) { GGML_METAL_LOG_ERROR("%s: error: %s\n", __func__, [[error description] UTF8String]); @@ -305,38 +319,41 @@ static void ggml_metal_log(enum ggml_log_level level, const char * format, ...){ extern const char ggml_metallib_start[]; extern const char ggml_metallib_end[]; - NSString * src = [[NSString alloc] initWithBytes:ggml_metallib_start length:(ggml_metallib_end-ggml_metallib_start) encoding:NSUTF8StringEncoding]; + NSString * src = [[NSString alloc] initWithBytes:ggml_metallib_start length:(ggml_metallib_end-ggml_metallib_start) encoding:NSUTF8StringEncoding]; #else GGML_METAL_LOG_INFO("%s: default.metallib not found, loading from source\n", __func__); - NSString * sourcePath; - NSString * ggmlMetalPathResources = [[NSProcessInfo processInfo].environment objectForKey:@"GGML_METAL_PATH_RESOURCES"]; + NSString * path_source; + NSString * path_resource = [[NSProcessInfo processInfo].environment objectForKey:@"GGML_METAL_PATH_RESOURCES"]; - GGML_METAL_LOG_INFO("%s: GGML_METAL_PATH_RESOURCES = %s\n", __func__, ggmlMetalPathResources ? [ggmlMetalPathResources UTF8String] : "nil"); + GGML_METAL_LOG_INFO("%s: GGML_METAL_PATH_RESOURCES = %s\n", __func__, path_resource ? [path_resource UTF8String] : "nil"); - if (ggmlMetalPathResources) { - sourcePath = [ggmlMetalPathResources stringByAppendingPathComponent:@"ggml-metal.metal"]; + if (path_resource) { + path_source = [path_resource stringByAppendingPathComponent:@"ggml-metal.metal"]; } else { - sourcePath = [bundle pathForResource:@"ggml-metal" ofType:@"metal"]; + path_source = [bundle pathForResource:@"ggml-metal" ofType:@"metal"]; } - if (sourcePath == nil) { + + if (path_source == nil) { GGML_METAL_LOG_WARN("%s: error: could not use bundle path to find ggml-metal.metal, falling back to trying cwd\n", __func__); - sourcePath = @"ggml-metal.metal"; + path_source = @"ggml-metal.metal"; } - GGML_METAL_LOG_INFO("%s: loading '%s'\n", __func__, [sourcePath UTF8String]); - NSString * src = [NSString stringWithContentsOfFile:sourcePath encoding:NSUTF8StringEncoding error:&error]; + + GGML_METAL_LOG_INFO("%s: loading '%s'\n", __func__, [path_source UTF8String]); + + NSString * src = [NSString stringWithContentsOfFile:path_source encoding:NSUTF8StringEncoding error:&error]; if (error) { GGML_METAL_LOG_ERROR("%s: error: %s\n", __func__, [[error description] UTF8String]); return NULL; } -#endif +#endif // GGML_METAL_EMBED_LIBRARY @autoreleasepool { // dictionary of preprocessor macros NSMutableDictionary * prep = [NSMutableDictionary dictionary]; #ifdef GGML_QKK_64 - prep[@"QK_K"] = @(64); + prep[@"GGML_QKK_64"] = @(1); #endif MTLCompileOptions* options = [MTLCompileOptions new]; @@ -1642,8 +1659,8 @@ static enum ggml_status ggml_metal_graph_compute( // TODO: make this more general GGML_ASSERT(n_as <= 8); - // max size of the src1ids array in the kernel stack - GGML_ASSERT(ne11 <= 512); + // max size of the src1ids array in the kernel shared buffer + GGML_ASSERT(ne11 <= 4096); const int64_t ne20 = src2 ? src2->ne[0] : 0; const int64_t ne21 = src2 ? src2->ne[1] : 0; @@ -1741,7 +1758,7 @@ static enum ggml_status ggml_metal_graph_compute( [encoder setBuffer:id_src_cur offset:offs_src_cur atIndex:19 + j]; } - [encoder setThreadgroupMemoryLength:8192 atIndex:0]; + [encoder setThreadgroupMemoryLength:GGML_PAD(8192 + 2*ne11, 16) atIndex:0]; [encoder dispatchThreadgroups:MTLSizeMake((ne11 + 31)/32, (ne21 + 63)/64, n_as*ne12*ne13) threadsPerThreadgroup:MTLSizeMake(128, 1, 1)]; } else { @@ -2820,6 +2837,11 @@ GGML_CALL static bool ggml_backend_metal_supports_op(ggml_backend_t backend, con /* .graph_plan_compute = */ NULL, /* .graph_compute = */ ggml_backend_metal_graph_compute, /* .supports_op = */ ggml_backend_metal_supports_op, + /* .event_new = */ NULL, + /* .event_free = */ NULL, + /* .event_record = */ NULL, + /* .event_wait = */ NULL, + /* .event_synchronize = */ NULL, }; void ggml_backend_metal_log_set_callback(ggml_log_callback log_callback, void * user_data) { diff --git a/src/ggml-metal.metal b/src/ggml-metal.metal index a65d12641..63de56325 100644 --- a/src/ggml-metal.metal +++ b/src/ggml-metal.metal @@ -1,3 +1,7 @@ +#define GGML_COMMON_DECL_METAL +#define GGML_COMMON_IMPL_METAL +#include "ggml-common.h" + #include using namespace metal; @@ -6,41 +10,6 @@ using namespace metal; #define MIN(x, y) ((x) < (y) ? (x) : (y)) #define SWAP(x, y) { auto tmp = (x); (x) = (y); (y) = tmp; } -#define QK4_0 32 -#define QR4_0 2 -typedef struct { - half d; // delta - uint8_t qs[QK4_0 / 2]; // nibbles / quants -} block_q4_0; - -#define QK4_1 32 -typedef struct { - half d; // delta - half m; // min - uint8_t qs[QK4_1 / 2]; // nibbles / quants -} block_q4_1; - -#define QK5_0 32 -typedef struct { - half d; // delta - uint8_t qh[4]; // 5-th bit of quants - uint8_t qs[QK5_0 / 2]; // nibbles / quants -} block_q5_0; - -#define QK5_1 32 -typedef struct { - half d; // delta - half m; // min - uint8_t qh[4]; // 5-th bit of quants - uint8_t qs[QK5_1 / 2]; // nibbles / quants -} block_q5_1; - -#define QK8_0 32 -typedef struct { - half d; // delta - int8_t qs[QK8_0]; // quants -} block_q8_0; - #define N_SIMDWIDTH 32 // assuming SIMD group size is 32 enum ggml_sort_order { @@ -2475,147 +2444,6 @@ kernel void kernel_concat( } } -//============================================ k-quants ====================================================== - -#ifndef QK_K -#define QK_K 256 -#else -static_assert(QK_K == 256 || QK_K == 64, "QK_K must be 256 or 64"); -#endif - -#if QK_K == 256 -#define K_SCALE_SIZE 12 -#else -#define K_SCALE_SIZE 4 -#endif - -typedef struct { - uint8_t scales[QK_K/16]; // scales and mins, quantized with 4 bits - uint8_t qs[QK_K/4]; // quants - half d; // super-block scale for quantized scales - half dmin; // super-block scale for quantized mins -} block_q2_K; -// 84 bytes / block - -typedef struct { - uint8_t hmask[QK_K/8]; // quants - high bit - uint8_t qs[QK_K/4]; // quants - low 2 bits -#if QK_K == 64 - uint8_t scales[2]; -#else - uint8_t scales[K_SCALE_SIZE]; // scales, quantized with 6 bits -#endif - half d; // super-block scale -} block_q3_K; - -#if QK_K == 64 -typedef struct { - half d[2]; // super-block scales/mins - uint8_t scales[2]; - uint8_t qs[QK_K/2]; // 4-bit quants -} block_q4_K; -#else -typedef struct { - half d; // super-block scale for quantized scales - half dmin; // super-block scale for quantized mins - uint8_t scales[K_SCALE_SIZE]; // scales and mins, quantized with 6 bits - uint8_t qs[QK_K/2]; // 4--bit quants -} block_q4_K; -#endif - -#if QK_K == 64 -typedef struct { - half d; // super-block scales/mins - int8_t scales[QK_K/16]; // 8-bit block scales - uint8_t qh[QK_K/8]; // quants, high bit - uint8_t qs[QK_K/2]; // quants, low 4 bits -} block_q5_K; -#else -typedef struct { - half d; // super-block scale for quantized scales - half dmin; // super-block scale for quantized mins - uint8_t scales[3*QK_K/64]; // scales and mins, quantized with 6 bits - uint8_t qh[QK_K/8]; // quants, high bit - uint8_t qs[QK_K/2]; // quants, low 4 bits -} block_q5_K; -// 176 bytes / block -#endif - -typedef struct { - uint8_t ql[QK_K/2]; // quants, lower 4 bits - uint8_t qh[QK_K/4]; // quants, upper 2 bits - int8_t scales[QK_K/16]; // scales, quantized with 8 bits - half d; // super-block scale -} block_q6_K; -// 210 bytes / block - -typedef struct { - half d; - uint16_t qs[QK_K/8]; -} block_iq2_xxs; -// 66 bytes / block for QK_K = 256, so 2.0625 bpw - -typedef struct { - half d; - uint16_t qs[QK_K/8]; - uint8_t scales[QK_K/32]; -} block_iq2_xs; -// 74 bytes / block for QK_K = 256, so 2.3125 bpw - -// 2.5625 bpw quants -typedef struct { - half d; - uint8_t qs[QK_K/4]; - uint8_t qh[QK_K/32]; - uint8_t scales[QK_K/32]; -} block_iq2_s; - -typedef struct { - half d; - uint8_t qs[3*QK_K/8]; -} block_iq3_xxs; -// 98 bytes / block for QK_K = 256, so 3.0625 bpw - -// 3.4375 bpw -#if QK_K == 64 -#define IQ3S_N_SCALE 2 -#else -#define IQ3S_N_SCALE QK_K/64 -#endif -typedef struct { - half d; - uint8_t qs[QK_K/4]; - uint8_t qh[QK_K/32]; - uint8_t signs[QK_K/8]; - uint8_t scales[IQ3S_N_SCALE]; -} block_iq3_s; - -typedef struct { - half d; - uint8_t qs[QK_K/8]; - uint8_t scales[QK_K/16]; -} block_iq1_s; - -// Non-linear quants -#define QK4_NL 32 -typedef struct { - half d; - uint8_t qs[QK4_NL/2]; -} block_iq4_nl; - -#if QK_K == 64 -#define block_iq4_xs block_iq4_nl -#else -typedef struct { - half d; - uint16_t scales_h; - uint8_t scales_l[QK_K/64]; - uint8_t qs[QK_K/2]; -} block_iq4_xs; -#endif - -//====================================== dot products ========================= - void kernel_mul_mv_q2_K_f32_impl( device const void * src0, device const float * src1, @@ -3638,710 +3466,6 @@ kernel void kernel_mul_mv_q6_K_f32( // ======================= "True" 2-bit -constexpr constant static uint64_t iq2xxs_grid[256] = { - 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, - 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808, - 0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819, - 0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819, - 0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b, - 0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808, - 0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08, - 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b, - 0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819, - 0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08, - 0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808, - 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08, - 0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808, - 0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808, - 0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919, - 0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819, - 0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08, - 0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908, - 0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819, - 0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808, - 0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808, - 0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908, - 0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808, - 0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08, - 0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819, - 0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819, - 0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819, - 0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908, - 0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19, - 0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819, - 0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b, - 0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808, - 0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908, - 0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08, - 0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08, - 0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908, - 0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819, - 0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808, - 0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808, - 0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19, - 0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819, - 0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, - 0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b, - 0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08, - 0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808, - 0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908, - 0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b, - 0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819, - 0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08, - 0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08, - 0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808, - 0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b, - 0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b, - 0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908, - 0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819, - 0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808, - 0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908, - 0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b, - 0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808, - 0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b, - 0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b, - 0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808, - 0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19, - 0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908, -}; - -constexpr constant static uint64_t iq2xs_grid[512] = { - 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, - 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b, - 0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919, - 0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b, - 0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919, - 0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808, - 0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819, - 0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819, - 0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, - 0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b, - 0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b, - 0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908, - 0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908, - 0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919, - 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808, - 0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919, - 0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908, - 0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, - 0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, - 0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08, - 0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808, - 0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808, - 0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819, - 0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908, - 0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819, - 0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808, - 0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b, - 0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819, - 0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819, - 0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808, - 0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908, - 0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19, - 0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b, - 0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b, - 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919, - 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808, - 0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819, - 0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819, - 0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b, - 0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908, - 0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808, - 0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819, - 0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808, - 0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919, - 0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808, - 0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808, - 0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908, - 0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908, - 0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808, - 0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b, - 0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819, - 0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, - 0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908, - 0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808, - 0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908, - 0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919, - 0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08, - 0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19, - 0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b, - 0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b, - 0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808, - 0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08, - 0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b, - 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908, - 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b, - 0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908, - 0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, - 0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808, - 0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808, - 0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08, - 0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819, - 0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919, - 0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808, - 0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808, - 0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819, - 0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819, - 0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908, - 0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908, - 0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b, - 0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908, - 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908, - 0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908, - 0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808, - 0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, - 0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819, - 0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819, - 0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808, - 0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b, - 0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819, - 0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819, - 0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08, - 0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808, - 0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19, - 0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919, - 0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808, - 0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19, - 0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b, - 0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808, - 0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b, - 0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b, - 0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, - 0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b, - 0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808, - 0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819, - 0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808, - 0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808, - 0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08, - 0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b, - 0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19, - 0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08, - 0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919, - 0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08, - 0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08, - 0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908, - 0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908, - 0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b, - 0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908, - 0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808, - 0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b, - 0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808, - 0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808, - 0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19, - 0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08, - 0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808, - 0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b, - 0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808, - 0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b, - 0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b, -}; - -constexpr constant static uint64_t iq2s_grid[1024] = { - 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, - 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b, - 0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919, - 0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b, - 0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919, - 0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x08080808192b192b, - 0x08080808192b2b19, 0x080808082b080808, 0x080808082b08082b, 0x080808082b081919, - 0x080808082b082b08, 0x080808082b190819, 0x080808082b191908, 0x080808082b2b0808, - 0x080808082b2b1919, 0x080808082b2b2b2b, 0x0808081908080819, 0x0808081908081908, - 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, 0x080808190819082b, - 0x0808081908191919, 0x0808081908192b08, 0x08080819082b0819, 0x08080819082b1908, - 0x0808081919080808, 0x080808191908082b, 0x0808081919081919, 0x0808081919082b08, - 0x0808081919190819, 0x0808081919191908, 0x080808191919192b, 0x0808081919192b19, - 0x08080819192b0808, 0x08080819192b1919, 0x08080819192b2b08, 0x080808192b080819, - 0x080808192b081908, 0x080808192b190808, 0x080808192b19082b, 0x080808192b191919, - 0x080808192b2b0819, 0x080808192b2b1908, 0x0808082b08080808, 0x0808082b0808082b, - 0x0808082b08081919, 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, - 0x0808082b082b0808, 0x0808082b082b2b2b, 0x0808082b19080819, 0x0808082b19081908, - 0x0808082b1908192b, 0x0808082b19082b19, 0x0808082b19190808, 0x0808082b19191919, - 0x0808082b2b080808, 0x0808082b2b081919, 0x0808082b2b082b2b, 0x0808082b2b191908, - 0x0808082b2b2b082b, 0x0808190808080819, 0x0808190808081908, 0x080819080808192b, - 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, 0x0808190808191919, - 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, 0x08081908082b192b, - 0x08081908082b2b19, 0x0808190819080808, 0x080819081908082b, 0x0808190819081919, - 0x0808190819082b08, 0x0808190819082b2b, 0x0808190819190819, 0x0808190819191908, - 0x080819081919192b, 0x0808190819192b19, 0x08081908192b0808, 0x08081908192b082b, - 0x08081908192b1919, 0x080819082b080819, 0x080819082b081908, 0x080819082b08192b, - 0x080819082b082b19, 0x080819082b190808, 0x080819082b191919, 0x080819082b192b08, - 0x080819082b2b0819, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, - 0x0808191908081919, 0x0808191908082b08, 0x0808191908082b2b, 0x0808191908190819, - 0x0808191908191908, 0x080819190819192b, 0x0808191908192b19, 0x08081919082b0808, - 0x08081919082b1919, 0x08081919082b2b08, 0x0808191919080819, 0x0808191919081908, - 0x080819191908192b, 0x0808191919082b19, 0x0808191919190808, 0x080819191919082b, - 0x0808191919191919, 0x0808191919192b08, 0x08081919192b0819, 0x08081919192b1908, - 0x080819192b080808, 0x080819192b08082b, 0x080819192b081919, 0x080819192b082b08, - 0x080819192b190819, 0x080819192b191908, 0x080819192b2b0808, 0x0808192b08080819, - 0x0808192b08081908, 0x0808192b0808192b, 0x0808192b08082b19, 0x0808192b08190808, - 0x0808192b08191919, 0x0808192b19080808, 0x0808192b19081919, 0x0808192b19082b08, - 0x0808192b19190819, 0x0808192b19191908, 0x0808192b192b0808, 0x0808192b2b080819, - 0x0808192b2b081908, 0x0808192b2b190808, 0x08082b0808080808, 0x08082b080808082b, - 0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808190819, 0x08082b0808191908, - 0x08082b080819192b, 0x08082b0808192b19, 0x08082b08082b0808, 0x08082b08082b1919, - 0x08082b08082b2b2b, 0x08082b0819080819, 0x08082b0819081908, 0x08082b081908192b, - 0x08082b0819082b19, 0x08082b0819190808, 0x08082b081919082b, 0x08082b0819191919, - 0x08082b0819192b08, 0x08082b08192b0819, 0x08082b08192b1908, 0x08082b082b080808, - 0x08082b082b081919, 0x08082b082b191908, 0x08082b082b2b2b2b, 0x08082b1908080819, - 0x08082b1908081908, 0x08082b1908190808, 0x08082b190819082b, 0x08082b1908191919, - 0x08082b1908192b08, 0x08082b19082b0819, 0x08082b1919080808, 0x08082b1919081919, - 0x08082b1919082b08, 0x08082b1919190819, 0x08082b1919191908, 0x08082b19192b0808, - 0x08082b192b080819, 0x08082b192b190808, 0x08082b2b08080808, 0x08082b2b08190819, - 0x08082b2b08191908, 0x08082b2b082b082b, 0x08082b2b082b2b08, 0x08082b2b082b2b2b, - 0x08082b2b19190808, 0x08082b2b2b192b19, 0x0819080808080819, 0x0819080808081908, - 0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, - 0x0819080808191919, 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, - 0x08190808082b192b, 0x0819080819080808, 0x081908081908082b, 0x0819080819081919, - 0x0819080819082b08, 0x0819080819190819, 0x0819080819191908, 0x081908081919192b, - 0x0819080819192b19, 0x08190808192b0808, 0x08190808192b082b, 0x08190808192b1919, - 0x08190808192b2b08, 0x081908082b080819, 0x081908082b081908, 0x081908082b08192b, - 0x081908082b190808, 0x081908082b191919, 0x081908082b192b08, 0x081908082b2b0819, - 0x081908082b2b1908, 0x0819081908080808, 0x081908190808082b, 0x0819081908081919, - 0x0819081908082b08, 0x0819081908082b2b, 0x0819081908190819, 0x0819081908191908, - 0x081908190819192b, 0x0819081908192b19, 0x08190819082b0808, 0x08190819082b082b, - 0x08190819082b1919, 0x08190819082b2b08, 0x0819081919080819, 0x0819081919081908, - 0x081908191908192b, 0x0819081919082b19, 0x0819081919190808, 0x081908191919082b, - 0x0819081919191919, 0x0819081919192b08, 0x08190819192b0819, 0x08190819192b1908, - 0x081908192b080808, 0x081908192b08082b, 0x081908192b081919, 0x081908192b082b08, - 0x081908192b190819, 0x081908192b191908, 0x0819082b08080819, 0x0819082b08081908, - 0x0819082b08082b19, 0x0819082b08190808, 0x0819082b08191919, 0x0819082b082b0819, - 0x0819082b082b1908, 0x0819082b19080808, 0x0819082b19081919, 0x0819082b19190819, - 0x0819082b19191908, 0x0819082b2b080819, 0x0819082b2b081908, 0x0819082b2b190808, - 0x0819190808080808, 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08, - 0x0819190808190819, 0x0819190808191908, 0x081919080819192b, 0x0819190808192b19, - 0x08191908082b0808, 0x08191908082b1919, 0x08191908082b2b08, 0x0819190819080819, - 0x0819190819081908, 0x081919081908192b, 0x0819190819082b19, 0x0819190819190808, - 0x081919081919082b, 0x0819190819191919, 0x0819190819192b08, 0x08191908192b0819, - 0x08191908192b1908, 0x081919082b080808, 0x081919082b08082b, 0x081919082b081919, - 0x081919082b082b08, 0x081919082b190819, 0x081919082b191908, 0x081919082b2b0808, - 0x0819191908080819, 0x0819191908081908, 0x081919190808192b, 0x0819191908082b19, - 0x0819191908190808, 0x081919190819082b, 0x0819191908191919, 0x0819191908192b08, - 0x08191919082b0819, 0x08191919082b1908, 0x0819191919080808, 0x081919191908082b, - 0x0819191919081919, 0x0819191919082b08, 0x0819191919190819, 0x0819191919191908, - 0x08191919192b0808, 0x081919192b080819, 0x081919192b081908, 0x081919192b190808, - 0x0819192b08080808, 0x0819192b08081919, 0x0819192b08082b08, 0x0819192b08190819, - 0x0819192b08191908, 0x0819192b082b0808, 0x0819192b19080819, 0x0819192b19081908, - 0x0819192b19190808, 0x0819192b2b080808, 0x0819192b2b2b2b2b, 0x08192b0808080819, - 0x08192b0808081908, 0x08192b080808192b, 0x08192b0808082b19, 0x08192b0808190808, - 0x08192b0808191919, 0x08192b0808192b08, 0x08192b08082b0819, 0x08192b0819080808, - 0x08192b081908082b, 0x08192b0819081919, 0x08192b0819082b08, 0x08192b0819190819, - 0x08192b0819191908, 0x08192b08192b0808, 0x08192b082b080819, 0x08192b082b081908, - 0x08192b1908080808, 0x08192b190808082b, 0x08192b1908081919, 0x08192b1908082b08, - 0x08192b1908190819, 0x08192b1908191908, 0x08192b19082b0808, 0x08192b1919080819, - 0x08192b1919081908, 0x08192b1919190808, 0x08192b19192b2b19, 0x08192b192b2b082b, - 0x08192b2b08081908, 0x08192b2b08190808, 0x08192b2b19080808, 0x08192b2b1919192b, - 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, 0x082b080808082b08, - 0x082b080808190819, 0x082b080808191908, 0x082b08080819192b, 0x082b080808192b19, - 0x082b0808082b0808, 0x082b0808082b1919, 0x082b0808082b2b2b, 0x082b080819080819, - 0x082b080819081908, 0x082b080819190808, 0x082b08081919082b, 0x082b080819191919, - 0x082b0808192b1908, 0x082b08082b080808, 0x082b08082b082b2b, 0x082b08082b191908, - 0x082b08082b2b2b2b, 0x082b081908080819, 0x082b081908081908, 0x082b081908190808, - 0x082b08190819082b, 0x082b081908191919, 0x082b0819082b0819, 0x082b081919080808, - 0x082b08191908082b, 0x082b081919081919, 0x082b081919190819, 0x082b081919191908, - 0x082b0819192b0808, 0x082b08192b080819, 0x082b08192b081908, 0x082b08192b190808, - 0x082b082b08080808, 0x082b082b08082b2b, 0x082b082b082b082b, 0x082b082b082b2b08, - 0x082b082b082b2b2b, 0x082b082b19081908, 0x082b082b19190808, 0x082b082b2b082b08, - 0x082b082b2b082b2b, 0x082b082b2b2b2b08, 0x082b190808080819, 0x082b190808081908, - 0x082b19080808192b, 0x082b190808082b19, 0x082b190808190808, 0x082b190808191919, - 0x082b190808192b08, 0x082b1908082b0819, 0x082b1908082b1908, 0x082b190819080808, - 0x082b19081908082b, 0x082b190819081919, 0x082b190819082b08, 0x082b190819190819, - 0x082b190819191908, 0x082b1908192b0808, 0x082b19082b080819, 0x082b19082b081908, - 0x082b19082b190808, 0x082b191908080808, 0x082b191908081919, 0x082b191908082b08, - 0x082b191908190819, 0x082b191908191908, 0x082b1919082b0808, 0x082b191919080819, - 0x082b191919081908, 0x082b191919190808, 0x082b1919192b192b, 0x082b19192b080808, - 0x082b192b08080819, 0x082b192b08081908, 0x082b192b08190808, 0x082b192b19080808, - 0x082b192b19192b19, 0x082b2b0808080808, 0x082b2b0808081919, 0x082b2b0808190819, - 0x082b2b0808191908, 0x082b2b0819080819, 0x082b2b0819081908, 0x082b2b0819190808, - 0x082b2b082b082b2b, 0x082b2b082b2b2b2b, 0x082b2b1908080819, 0x082b2b1908081908, - 0x082b2b1908190808, 0x082b2b192b191919, 0x082b2b2b08082b2b, 0x082b2b2b082b082b, - 0x082b2b2b192b1908, 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, - 0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, - 0x190808080819082b, 0x1908080808191919, 0x1908080808192b08, 0x1908080808192b2b, - 0x19080808082b0819, 0x19080808082b1908, 0x19080808082b192b, 0x1908080819080808, - 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, 0x1908080819082b2b, - 0x1908080819190819, 0x1908080819191908, 0x190808081919192b, 0x1908080819192b19, - 0x19080808192b0808, 0x19080808192b082b, 0x19080808192b1919, 0x190808082b080819, - 0x190808082b081908, 0x190808082b190808, 0x190808082b191919, 0x190808082b192b08, - 0x190808082b2b0819, 0x190808082b2b1908, 0x1908081908080808, 0x190808190808082b, - 0x1908081908081919, 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908, - 0x190808190819192b, 0x1908081908192b19, 0x19080819082b0808, 0x19080819082b082b, - 0x19080819082b1919, 0x1908081919080819, 0x1908081919081908, 0x190808191908192b, - 0x1908081919082b19, 0x1908081919190808, 0x190808191919082b, 0x1908081919191919, - 0x1908081919192b08, 0x19080819192b0819, 0x19080819192b1908, 0x190808192b080808, - 0x190808192b08082b, 0x190808192b081919, 0x190808192b082b08, 0x190808192b190819, - 0x190808192b191908, 0x190808192b2b0808, 0x1908082b08080819, 0x1908082b08081908, - 0x1908082b08190808, 0x1908082b0819082b, 0x1908082b08191919, 0x1908082b08192b08, - 0x1908082b082b1908, 0x1908082b19080808, 0x1908082b19081919, 0x1908082b19082b08, - 0x1908082b19190819, 0x1908082b19191908, 0x1908082b192b0808, 0x1908082b2b080819, - 0x1908082b2b081908, 0x1908190808080808, 0x190819080808082b, 0x1908190808081919, - 0x1908190808082b08, 0x1908190808082b2b, 0x1908190808190819, 0x1908190808191908, - 0x190819080819192b, 0x1908190808192b19, 0x19081908082b0808, 0x19081908082b082b, - 0x19081908082b1919, 0x19081908082b2b08, 0x1908190819080819, 0x1908190819081908, - 0x190819081908192b, 0x1908190819082b19, 0x1908190819190808, 0x190819081919082b, - 0x1908190819191919, 0x1908190819192b08, 0x19081908192b0819, 0x19081908192b1908, - 0x190819082b080808, 0x190819082b08082b, 0x190819082b081919, 0x190819082b082b08, - 0x190819082b190819, 0x190819082b191908, 0x190819082b2b0808, 0x1908191908080819, - 0x1908191908081908, 0x190819190808192b, 0x1908191908082b19, 0x1908191908190808, - 0x190819190819082b, 0x1908191908191919, 0x1908191908192b08, 0x19081919082b0819, - 0x19081919082b1908, 0x1908191919080808, 0x190819191908082b, 0x1908191919081919, - 0x1908191919082b08, 0x1908191919190819, 0x1908191919191908, 0x19081919192b0808, - 0x19081919192b2b2b, 0x190819192b080819, 0x190819192b081908, 0x190819192b190808, - 0x1908192b08080808, 0x1908192b0808082b, 0x1908192b08081919, 0x1908192b08082b08, - 0x1908192b08190819, 0x1908192b08191908, 0x1908192b082b0808, 0x1908192b19080819, - 0x1908192b19081908, 0x1908192b19190808, 0x1908192b2b080808, 0x1908192b2b2b1919, - 0x19082b0808080819, 0x19082b0808081908, 0x19082b0808082b19, 0x19082b0808190808, - 0x19082b080819082b, 0x19082b0808191919, 0x19082b0808192b08, 0x19082b08082b0819, - 0x19082b08082b1908, 0x19082b0819080808, 0x19082b081908082b, 0x19082b0819081919, - 0x19082b0819082b08, 0x19082b0819190819, 0x19082b0819191908, 0x19082b08192b0808, - 0x19082b082b081908, 0x19082b082b190808, 0x19082b1908080808, 0x19082b190808082b, - 0x19082b1908081919, 0x19082b1908082b08, 0x19082b1908190819, 0x19082b1908191908, - 0x19082b19082b0808, 0x19082b1919080819, 0x19082b1919081908, 0x19082b1919190808, - 0x19082b192b080808, 0x19082b192b19192b, 0x19082b2b08080819, 0x19082b2b08081908, - 0x19082b2b08190808, 0x19082b2b19080808, 0x1919080808080808, 0x191908080808082b, - 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, 0x1919080808191908, - 0x191908080819192b, 0x1919080808192b19, 0x19190808082b0808, 0x19190808082b082b, - 0x19190808082b1919, 0x19190808082b2b08, 0x1919080819080819, 0x1919080819081908, - 0x191908081908192b, 0x1919080819082b19, 0x1919080819190808, 0x191908081919082b, - 0x1919080819191919, 0x1919080819192b08, 0x19190808192b0819, 0x19190808192b1908, - 0x191908082b080808, 0x191908082b08082b, 0x191908082b081919, 0x191908082b082b08, - 0x191908082b190819, 0x191908082b191908, 0x1919081908080819, 0x1919081908081908, - 0x191908190808192b, 0x1919081908082b19, 0x1919081908190808, 0x191908190819082b, - 0x1919081908191919, 0x1919081908192b08, 0x19190819082b0819, 0x19190819082b1908, - 0x1919081919080808, 0x191908191908082b, 0x1919081919081919, 0x1919081919082b08, - 0x1919081919190819, 0x1919081919191908, 0x19190819192b0808, 0x191908192b080819, - 0x191908192b081908, 0x191908192b190808, 0x1919082b08080808, 0x1919082b08081919, - 0x1919082b08082b08, 0x1919082b08190819, 0x1919082b08191908, 0x1919082b082b0808, - 0x1919082b19080819, 0x1919082b19081908, 0x1919082b19190808, 0x1919082b192b2b19, - 0x1919082b2b080808, 0x1919190808080819, 0x1919190808081908, 0x191919080808192b, - 0x1919190808082b19, 0x1919190808190808, 0x191919080819082b, 0x1919190808191919, - 0x1919190808192b08, 0x19191908082b0819, 0x19191908082b1908, 0x1919190819080808, - 0x191919081908082b, 0x1919190819081919, 0x1919190819082b08, 0x1919190819190819, - 0x1919190819191908, 0x19191908192b0808, 0x191919082b080819, 0x191919082b081908, - 0x191919082b190808, 0x1919191908080808, 0x191919190808082b, 0x1919191908081919, - 0x1919191908082b08, 0x1919191908190819, 0x1919191908191908, 0x19191919082b0808, - 0x1919191919080819, 0x1919191919081908, 0x1919191919190808, 0x191919192b080808, - 0x1919192b08080819, 0x1919192b08081908, 0x1919192b08190808, 0x1919192b082b192b, - 0x1919192b19080808, 0x19192b0808080808, 0x19192b080808082b, 0x19192b0808081919, - 0x19192b0808082b08, 0x19192b0808190819, 0x19192b0808191908, 0x19192b08082b0808, - 0x19192b0819080819, 0x19192b0819081908, 0x19192b0819190808, 0x19192b0819192b2b, - 0x19192b082b080808, 0x19192b1908080819, 0x19192b1908081908, 0x19192b1908190808, - 0x19192b1919080808, 0x19192b2b08080808, 0x19192b2b08192b19, 0x19192b2b2b081919, - 0x19192b2b2b2b2b08, 0x192b080808080819, 0x192b080808081908, 0x192b08080808192b, - 0x192b080808190808, 0x192b08080819082b, 0x192b080808191919, 0x192b080808192b08, - 0x192b0808082b0819, 0x192b0808082b1908, 0x192b080819080808, 0x192b080819081919, - 0x192b080819082b08, 0x192b080819190819, 0x192b080819191908, 0x192b0808192b0808, - 0x192b08082b081908, 0x192b08082b190808, 0x192b081908080808, 0x192b08190808082b, - 0x192b081908081919, 0x192b081908082b08, 0x192b081908190819, 0x192b081908191908, - 0x192b0819082b0808, 0x192b081919080819, 0x192b081919081908, 0x192b081919190808, - 0x192b08192b080808, 0x192b08192b192b19, 0x192b082b08081908, 0x192b082b08190808, - 0x192b082b19080808, 0x192b082b1919192b, 0x192b082b2b2b0819, 0x192b190808080808, - 0x192b190808081919, 0x192b190808082b08, 0x192b190808190819, 0x192b190808191908, - 0x192b1908082b0808, 0x192b190819080819, 0x192b190819081908, 0x192b190819190808, - 0x192b19082b080808, 0x192b191908080819, 0x192b191908081908, 0x192b191908190808, - 0x192b191919080808, 0x192b191919082b2b, 0x192b1919192b2b08, 0x192b19192b19082b, - 0x192b192b08080808, 0x192b192b2b191908, 0x192b2b0808080819, 0x192b2b0808081908, - 0x192b2b0808190808, 0x192b2b08192b1919, 0x192b2b082b192b08, 0x192b2b1908080808, - 0x192b2b19082b2b2b, 0x192b2b2b1908082b, 0x192b2b2b2b2b0819, 0x2b08080808080808, - 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819, - 0x2b08080808191908, 0x2b08080808192b19, 0x2b080808082b0808, 0x2b080808082b1919, - 0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808081919082b, - 0x2b08080819191919, 0x2b08080819192b08, 0x2b080808192b0819, 0x2b0808082b080808, - 0x2b0808082b081919, 0x2b0808082b190819, 0x2b0808082b191908, 0x2b08081908080819, - 0x2b08081908081908, 0x2b08081908082b19, 0x2b08081908190808, 0x2b0808190819082b, - 0x2b08081908191919, 0x2b08081908192b08, 0x2b080819082b0819, 0x2b080819082b1908, - 0x2b08081919080808, 0x2b0808191908082b, 0x2b08081919081919, 0x2b08081919082b08, - 0x2b08081919190819, 0x2b08081919191908, 0x2b0808192b080819, 0x2b0808192b081908, - 0x2b0808192b190808, 0x2b0808192b2b2b19, 0x2b08082b08080808, 0x2b08082b08081919, - 0x2b08082b08082b2b, 0x2b08082b08190819, 0x2b08082b08191908, 0x2b08082b19080819, - 0x2b08082b19081908, 0x2b08082b19190808, 0x2b08190808080819, 0x2b08190808081908, - 0x2b0819080808192b, 0x2b08190808082b19, 0x2b08190808190808, 0x2b0819080819082b, - 0x2b08190808191919, 0x2b08190808192b08, 0x2b081908082b0819, 0x2b08190819080808, - 0x2b0819081908082b, 0x2b08190819081919, 0x2b08190819082b08, 0x2b08190819190819, - 0x2b08190819191908, 0x2b081908192b0808, 0x2b0819082b080819, 0x2b0819082b081908, - 0x2b0819082b190808, 0x2b08191908080808, 0x2b0819190808082b, 0x2b08191908081919, - 0x2b08191908082b08, 0x2b08191908190819, 0x2b08191908191908, 0x2b081919082b0808, - 0x2b08191919080819, 0x2b08191919081908, 0x2b08191919190808, 0x2b0819192b080808, - 0x2b0819192b082b2b, 0x2b08192b08080819, 0x2b08192b08081908, 0x2b08192b08190808, - 0x2b08192b082b2b19, 0x2b08192b19080808, 0x2b082b0808080808, 0x2b082b0808081919, - 0x2b082b0808190819, 0x2b082b0808191908, 0x2b082b0819080819, 0x2b082b0819081908, - 0x2b082b0819190808, 0x2b082b082b2b082b, 0x2b082b1908080819, 0x2b082b1908081908, - 0x2b082b1919080808, 0x2b082b19192b1919, 0x2b082b2b082b082b, 0x2b082b2b19192b08, - 0x2b082b2b19192b2b, 0x2b082b2b2b08082b, 0x2b082b2b2b2b082b, 0x2b19080808080819, - 0x2b19080808081908, 0x2b19080808082b19, 0x2b19080808190808, 0x2b1908080819082b, - 0x2b19080808191919, 0x2b19080808192b08, 0x2b190808082b1908, 0x2b19080819080808, - 0x2b1908081908082b, 0x2b19080819081919, 0x2b19080819082b08, 0x2b19080819190819, - 0x2b19080819191908, 0x2b190808192b0808, 0x2b1908082b080819, 0x2b1908082b081908, - 0x2b1908082b190808, 0x2b19081908080808, 0x2b19081908081919, 0x2b19081908190819, - 0x2b19081908191908, 0x2b19081919080819, 0x2b19081919081908, 0x2b19081919190808, - 0x2b19081919192b2b, 0x2b19082b08080819, 0x2b19082b08081908, 0x2b19082b08190808, - 0x2b19082b19080808, 0x2b19082b2b2b192b, 0x2b19190808080808, 0x2b1919080808082b, - 0x2b19190808081919, 0x2b19190808082b08, 0x2b19190808190819, 0x2b19190808191908, - 0x2b191908082b0808, 0x2b19190819080819, 0x2b19190819081908, 0x2b19190819190808, - 0x2b1919082b080808, 0x2b1919082b19192b, 0x2b19191908080819, 0x2b19191908081908, - 0x2b19191908190808, 0x2b19191919080808, 0x2b1919192b192b08, 0x2b1919192b2b0819, - 0x2b19192b08080808, 0x2b19192b1908192b, 0x2b19192b192b1908, 0x2b192b0808080819, - 0x2b192b0808081908, 0x2b192b0808190808, 0x2b192b08082b192b, 0x2b192b0819080808, - 0x2b192b082b2b2b19, 0x2b192b1908080808, 0x2b192b1919082b19, 0x2b192b191919082b, - 0x2b192b2b2b190808, 0x2b2b080808080808, 0x2b2b080808081919, 0x2b2b080808082b2b, - 0x2b2b080808191908, 0x2b2b0808082b082b, 0x2b2b0808082b2b2b, 0x2b2b080819080819, - 0x2b2b080819081908, 0x2b2b080819190808, 0x2b2b08082b2b082b, 0x2b2b08082b2b2b2b, - 0x2b2b081919080808, 0x2b2b0819192b1919, 0x2b2b082b0808082b, 0x2b2b082b08082b2b, - 0x2b2b082b082b082b, 0x2b2b082b082b2b08, 0x2b2b082b082b2b2b, 0x2b2b082b2b08082b, - 0x2b2b082b2b082b08, 0x2b2b082b2b082b2b, 0x2b2b082b2b2b2b08, 0x2b2b190808080819, - 0x2b2b190808081908, 0x2b2b190808190808, 0x2b2b190819080808, 0x2b2b19082b082b19, - 0x2b2b19082b2b1908, 0x2b2b191908080808, 0x2b2b191908192b19, 0x2b2b192b19190819, - 0x2b2b2b0808082b2b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b082b, 0x2b2b2b1919191908, - 0x2b2b2b192b08192b, 0x2b2b2b2b08082b08, 0x2b2b2b2b08082b2b, 0x2b2b2b2b082b0808, - 0x2b2b2b2b082b082b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b2b082b08, 0x2b2b2b2b2b2b2b2b, -}; - -constexpr constant static uint32_t iq3xxs_grid[256] = { - 0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, 0x04041404, 0x04041414, - 0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14, - 0x040c140c, 0x040c142c, 0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404, - 0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c, 0x04141c1c, 0x04141c3e, - 0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c, 0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c, - 0x041c3e04, 0x04240c1c, 0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c, - 0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04, 0x043e0c24, 0x043e0c34, - 0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c, 0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c, - 0x0c041c04, 0x0c041c14, 0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c, - 0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14, 0x0c14140c, 0x0c141c04, - 0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404, 0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c, - 0x0c24042c, 0x0c242c04, 0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414, - 0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404, 0x14041414, 0x14041434, - 0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c, 0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c, - 0x140c1c04, 0x140c341c, 0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e, - 0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c, 0x141c0c04, 0x141c0c24, - 0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c, 0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24, - 0x143e040c, 0x143e041c, 0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c, - 0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414, 0x1c0c1404, 0x1c0c1c0c, - 0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c, 0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14, - 0x1c1c0c0c, 0x1c1c1c1c, 0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414, - 0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404, 0x24040424, 0x24040c3e, - 0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e, 0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404, - 0x24143404, 0x24143434, 0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c, - 0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04, 0x2c040c14, 0x2c04240c, - 0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434, 0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14, - 0x2c1c0414, 0x2c1c2c1c, 0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c, - 0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434, 0x34043424, 0x340c140c, - 0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04, 0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14, - 0x34341c1c, 0x343e041c, 0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14, - 0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14, 0x3e1c0404, 0x3e1c0c2c, - 0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c, 0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04, -}; - -constexpr constant static uint32_t iq3s_grid[512] = { - 0x01010101, 0x01010103, 0x01010105, 0x0101010b, 0x0101010f, 0x01010301, 0x01010303, 0x01010305, - 0x01010309, 0x0101030d, 0x01010501, 0x01010503, 0x0101050b, 0x01010707, 0x01010901, 0x01010905, - 0x0101090b, 0x0101090f, 0x01010b03, 0x01010b07, 0x01010d01, 0x01010d05, 0x01010f03, 0x01010f09, - 0x01010f0f, 0x01030101, 0x01030103, 0x01030105, 0x01030109, 0x01030301, 0x01030303, 0x0103030b, - 0x01030501, 0x01030507, 0x0103050f, 0x01030703, 0x0103070b, 0x01030909, 0x01030d03, 0x01030d0b, - 0x01030f05, 0x01050101, 0x01050103, 0x0105010b, 0x0105010f, 0x01050301, 0x01050307, 0x0105030d, - 0x01050503, 0x0105050b, 0x01050701, 0x01050709, 0x01050905, 0x0105090b, 0x0105090f, 0x01050b03, - 0x01050b07, 0x01050f01, 0x01050f07, 0x01070107, 0x01070303, 0x0107030b, 0x01070501, 0x01070505, - 0x01070703, 0x01070707, 0x0107070d, 0x01070909, 0x01070b01, 0x01070b05, 0x01070d0f, 0x01070f03, - 0x01070f0b, 0x01090101, 0x01090307, 0x0109030f, 0x01090503, 0x01090509, 0x01090705, 0x01090901, - 0x01090907, 0x01090b03, 0x01090f01, 0x010b0105, 0x010b0109, 0x010b0501, 0x010b0505, 0x010b050d, - 0x010b0707, 0x010b0903, 0x010b090b, 0x010b090f, 0x010b0d0d, 0x010b0f07, 0x010d010d, 0x010d0303, - 0x010d0307, 0x010d0703, 0x010d0b05, 0x010d0f03, 0x010f0101, 0x010f0105, 0x010f0109, 0x010f0501, - 0x010f0505, 0x010f050d, 0x010f0707, 0x010f0b01, 0x010f0b09, 0x03010101, 0x03010103, 0x03010105, - 0x03010109, 0x03010301, 0x03010303, 0x03010307, 0x0301030b, 0x0301030f, 0x03010501, 0x03010505, - 0x03010703, 0x03010709, 0x0301070d, 0x03010b09, 0x03010b0d, 0x03010d03, 0x03010f05, 0x03030101, - 0x03030103, 0x03030107, 0x0303010d, 0x03030301, 0x03030309, 0x03030503, 0x03030701, 0x03030707, - 0x03030903, 0x03030b01, 0x03030b05, 0x03030f01, 0x03030f0d, 0x03050101, 0x03050305, 0x0305030b, - 0x0305030f, 0x03050501, 0x03050509, 0x03050705, 0x03050901, 0x03050907, 0x03050b0b, 0x03050d01, - 0x03050f05, 0x03070103, 0x03070109, 0x0307010f, 0x03070301, 0x03070307, 0x03070503, 0x0307050f, - 0x03070701, 0x03070709, 0x03070903, 0x03070d05, 0x03070f01, 0x03090107, 0x0309010b, 0x03090305, - 0x03090309, 0x03090703, 0x03090707, 0x03090905, 0x0309090d, 0x03090b01, 0x03090b09, 0x030b0103, - 0x030b0301, 0x030b0307, 0x030b0503, 0x030b0701, 0x030b0705, 0x030b0b03, 0x030d0501, 0x030d0509, - 0x030d050f, 0x030d0909, 0x030d090d, 0x030f0103, 0x030f0107, 0x030f0301, 0x030f0305, 0x030f0503, - 0x030f070b, 0x030f0903, 0x030f0d05, 0x030f0f01, 0x05010101, 0x05010103, 0x05010107, 0x0501010b, - 0x0501010f, 0x05010301, 0x05010305, 0x05010309, 0x0501030d, 0x05010503, 0x05010507, 0x0501050f, - 0x05010701, 0x05010705, 0x05010903, 0x05010907, 0x0501090b, 0x05010b01, 0x05010b05, 0x05010d0f, - 0x05010f01, 0x05010f07, 0x05010f0b, 0x05030101, 0x05030105, 0x05030301, 0x05030307, 0x0503030f, - 0x05030505, 0x0503050b, 0x05030703, 0x05030709, 0x05030905, 0x05030b03, 0x05050103, 0x05050109, - 0x0505010f, 0x05050503, 0x05050507, 0x05050701, 0x0505070f, 0x05050903, 0x05050b07, 0x05050b0f, - 0x05050f03, 0x05050f09, 0x05070101, 0x05070105, 0x0507010b, 0x05070303, 0x05070505, 0x05070509, - 0x05070703, 0x05070707, 0x05070905, 0x05070b01, 0x05070d0d, 0x05090103, 0x0509010f, 0x05090501, - 0x05090507, 0x05090705, 0x0509070b, 0x05090903, 0x05090f05, 0x05090f0b, 0x050b0109, 0x050b0303, - 0x050b0505, 0x050b070f, 0x050b0901, 0x050b0b07, 0x050b0f01, 0x050d0101, 0x050d0105, 0x050d010f, - 0x050d0503, 0x050d0b0b, 0x050d0d03, 0x050f010b, 0x050f0303, 0x050f050d, 0x050f0701, 0x050f0907, - 0x050f0b01, 0x07010105, 0x07010303, 0x07010307, 0x0701030b, 0x0701030f, 0x07010505, 0x07010703, - 0x07010707, 0x0701070b, 0x07010905, 0x07010909, 0x0701090f, 0x07010b03, 0x07010d07, 0x07010f03, - 0x07030103, 0x07030107, 0x0703010b, 0x07030309, 0x07030503, 0x07030507, 0x07030901, 0x07030d01, - 0x07030f05, 0x07030f0d, 0x07050101, 0x07050305, 0x07050501, 0x07050705, 0x07050709, 0x07050b01, - 0x07070103, 0x07070301, 0x07070309, 0x07070503, 0x07070507, 0x0707050f, 0x07070701, 0x07070903, - 0x07070907, 0x0707090f, 0x07070b0b, 0x07070f07, 0x07090107, 0x07090303, 0x0709030d, 0x07090505, - 0x07090703, 0x07090b05, 0x07090d01, 0x07090d09, 0x070b0103, 0x070b0301, 0x070b0305, 0x070b050b, - 0x070b0705, 0x070b0909, 0x070b0b0d, 0x070b0f07, 0x070d030d, 0x070d0903, 0x070f0103, 0x070f0107, - 0x070f0501, 0x070f0505, 0x070f070b, 0x09010101, 0x09010109, 0x09010305, 0x09010501, 0x09010509, - 0x0901050f, 0x09010705, 0x09010903, 0x09010b01, 0x09010f01, 0x09030105, 0x0903010f, 0x09030303, - 0x09030307, 0x09030505, 0x09030701, 0x0903070b, 0x09030907, 0x09030b03, 0x09030b0b, 0x09050103, - 0x09050107, 0x09050301, 0x0905030b, 0x09050503, 0x09050707, 0x09050901, 0x09050b0f, 0x09050d05, - 0x09050f01, 0x09070109, 0x09070303, 0x09070307, 0x09070501, 0x09070505, 0x09070703, 0x0907070b, - 0x09090101, 0x09090105, 0x09090509, 0x0909070f, 0x09090901, 0x09090f03, 0x090b010b, 0x090b010f, - 0x090b0503, 0x090b0d05, 0x090d0307, 0x090d0709, 0x090d0d01, 0x090f0301, 0x090f030b, 0x090f0701, - 0x090f0907, 0x090f0b03, 0x0b010105, 0x0b010301, 0x0b010309, 0x0b010505, 0x0b010901, 0x0b010909, - 0x0b01090f, 0x0b010b05, 0x0b010d0d, 0x0b010f09, 0x0b030103, 0x0b030107, 0x0b03010b, 0x0b030305, - 0x0b030503, 0x0b030705, 0x0b030f05, 0x0b050101, 0x0b050303, 0x0b050507, 0x0b050701, 0x0b05070d, - 0x0b050b07, 0x0b070105, 0x0b07010f, 0x0b070301, 0x0b07050f, 0x0b070909, 0x0b070b03, 0x0b070d0b, - 0x0b070f07, 0x0b090103, 0x0b090109, 0x0b090501, 0x0b090705, 0x0b09090d, 0x0b0b0305, 0x0b0b050d, - 0x0b0b0b03, 0x0b0b0b07, 0x0b0d0905, 0x0b0f0105, 0x0b0f0109, 0x0b0f0505, 0x0d010303, 0x0d010307, - 0x0d01030b, 0x0d010703, 0x0d010707, 0x0d010d01, 0x0d030101, 0x0d030501, 0x0d03050f, 0x0d030d09, - 0x0d050305, 0x0d050709, 0x0d050905, 0x0d050b0b, 0x0d050d05, 0x0d050f01, 0x0d070101, 0x0d070309, - 0x0d070503, 0x0d070901, 0x0d09050b, 0x0d090907, 0x0d090d05, 0x0d0b0101, 0x0d0b0107, 0x0d0b0709, - 0x0d0b0d01, 0x0d0d010b, 0x0d0d0901, 0x0d0f0303, 0x0d0f0307, 0x0f010101, 0x0f010109, 0x0f01010f, - 0x0f010501, 0x0f010505, 0x0f01070d, 0x0f010901, 0x0f010b09, 0x0f010d05, 0x0f030105, 0x0f030303, - 0x0f030509, 0x0f030907, 0x0f03090b, 0x0f050103, 0x0f050109, 0x0f050301, 0x0f05030d, 0x0f050503, - 0x0f050701, 0x0f050b03, 0x0f070105, 0x0f070705, 0x0f07070b, 0x0f070b07, 0x0f090103, 0x0f09010b, - 0x0f090307, 0x0f090501, 0x0f090b01, 0x0f0b0505, 0x0f0b0905, 0x0f0d0105, 0x0f0d0703, 0x0f0f0101, -}; - -#define NGRID_IQ1S 512 -constexpr constant static uint64_t iq1s_grid[NGRID_IQ1S] = { - 0xffffffffffff0101, 0xffffffffff01ff00, 0xffffffffff010100, 0xffffffff00000000, - 0xffffffff01ff00ff, 0xffffffff01ff0001, 0xffffffff0101ffff, 0xffffffff0101ff01, - 0xffffff00ff000000, 0xffffff000000ff00, 0xffffff00000000ff, 0xffffff0000000100, - 0xffffff0000010000, 0xffffff0001000000, 0xffffff01ffff00ff, 0xffffff01ff01ff00, - 0xffffff01ff010100, 0xffffff0100000001, 0xffffff0101ffff00, 0xffffff0101ff0101, - 0xffffff0101010100, 0xffff00ffff00ff01, 0xffff00ffff0000ff, 0xffff00ff00ff0100, - 0xffff00ff0100ff00, 0xffff00ff010001ff, 0xffff0000ff0101ff, 0xffff000000ffff00, - 0xffff000000000000, 0xffff00000001ff01, 0xffff000001000101, 0xffff0000010100ff, - 0xffff0001ffff0100, 0xffff00010000ff00, 0xffff000100010101, 0xffff000101000000, - 0xffff01ffffff0000, 0xffff01ffff01ffff, 0xffff01ffff010100, 0xffff01ff00000000, - 0xffff01ff01ffffff, 0xffff01ff01ff0001, 0xffff01ff0101ffff, 0xffff01ff01010001, - 0xffff0100ffffff01, 0xffff01000000ffff, 0xffff010000000100, 0xffff010001ff01ff, - 0xffff010001000000, 0xffff0101ff000000, 0xffff0101000101ff, 0xffff010101ffff01, - 0xffff01010101ff00, 0xff00ffffff000000, 0xff00ffff00ffff00, 0xff00ffff00000001, - 0xff00ffff000001ff, 0xff00ffff01010000, 0xff00ff00ffff0000, 0xff00ff00ff00ff00, - 0xff00ff00ff0000ff, 0xff00ff00ff000100, 0xff00ff00ff010001, 0xff00ff0000ff0001, - 0xff00ff000000ffff, 0xff00ff0000000000, 0xff00ff000001ff00, 0xff00ff0000010100, - 0xff00ff0001ff0000, 0xff00ff000100ff00, 0xff00ff0001000100, 0xff00ff01ff000000, - 0xff00ff0100ff0000, 0xff00ff01000001ff, 0xff00ff0101010001, 0xff0000ff00000000, - 0xff0000ff0001ff00, 0xff0000ff00010100, 0xff000000ffff0101, 0xff000000ff000000, - 0xff000000ff01ff00, 0xff00000000ff0000, 0xff0000000000ff00, 0xff000000000000ff, - 0xff00000000000000, 0xff00000000000001, 0xff00000000000100, 0xff0000000001ffff, - 0xff00000000010000, 0xff00000001000000, 0xff00000001010100, 0xff000001ff00ff01, - 0xff000001ff0100ff, 0xff00000100000000, 0xff0000010001ff00, 0xff00000101ff0100, - 0xff0000010100ff00, 0xff0001ff00ff00ff, 0xff0001ff00000101, 0xff0001ff000100ff, - 0xff0001ff01000000, 0xff000100ff0001ff, 0xff0001000000ff01, 0xff00010000000000, - 0xff00010000010001, 0xff00010000010100, 0xff00010001ffff00, 0xff00010001ff0101, - 0xff00010001010000, 0xff000101ffffffff, 0xff000101ff000101, 0xff00010101ff00ff, - 0xff00010101000001, 0xff000101010100ff, 0xff01ffffff000101, 0xff01ffffff01ffff, - 0xff01ffffff01ff01, 0xff01ffffff0101ff, 0xff01ffff00000000, 0xff01ffff01ff0001, - 0xff01ffff0101ff01, 0xff01ff00ff000000, 0xff01ff0000ff0100, 0xff01ff000000ff01, - 0xff01ff0000010000, 0xff01ff00010000ff, 0xff01ff01ff01ff00, 0xff01ff0100000101, - 0xff0100ffffff0000, 0xff0100ffff010000, 0xff0100ff01ff00ff, 0xff0100ff01000100, - 0xff0100ff010100ff, 0xff010000ffffff01, 0xff01000000000000, 0xff0100000101ff00, - 0xff010001ffff00ff, 0xff010001ff000100, 0xff01000100ffff00, 0xff01000100010001, - 0xff01000101ff0001, 0xff010001010001ff, 0xff0101ffffffffff, 0xff0101ffff01ffff, - 0xff0101ffff010101, 0xff0101ff0000ff00, 0xff0101ff01010001, 0xff010100ff000000, - 0xff010100ff01ff01, 0xff01010000ff0001, 0xff01010000000100, 0xff01010001000000, - 0xff0101010100ffff, 0x00ffffff0000ff01, 0x00ffffff000000ff, 0x00ffffff00000100, - 0x00ffffff00010000, 0x00ffff00ffff0001, 0x00ffff00ff0000ff, 0x00ffff00ff000100, - 0x00ffff0000000000, 0x00ffff0001000100, 0x00ffff0001010001, 0x00ffff01ff00ff01, - 0x00ffff0100ff0100, 0x00ffff010000ff00, 0x00ffff01000100ff, 0x00ffff0101ff00ff, - 0x00ffff010101ff00, 0x00ff00ffffffffff, 0x00ff00ffffff01ff, 0x00ff00ffff000101, - 0x00ff00ff00000000, 0x00ff00ff000101ff, 0x00ff00ff01010101, 0x00ff0000ff000000, - 0x00ff0000ff01ffff, 0x00ff000000ff0000, 0x00ff00000000ff00, 0x00ff0000000000ff, - 0x00ff000000000000, 0x00ff000000000001, 0x00ff000000000100, 0x00ff000000010000, - 0x00ff000001ffff01, 0x00ff000001000000, 0x00ff0001ff000101, 0x00ff000100ffffff, - 0x00ff000100000000, 0x00ff0001010001ff, 0x00ff01ffff000000, 0x00ff01ff0001ff00, - 0x00ff01ff01ff0100, 0x00ff0100ff01ff01, 0x00ff010000ff00ff, 0x00ff010000ff0101, - 0x00ff010000000000, 0x00ff010000010101, 0x00ff01000100ff00, 0x00ff010001010000, - 0x00ff0101ffffff00, 0x00ff01010000ff01, 0x00ff010100000100, 0x00ff010101ff0000, - 0x0000ffffffff0100, 0x0000ffffff00ff00, 0x0000ffffff0000ff, 0x0000ffffff010000, - 0x0000ffff00000000, 0x0000ffff00010101, 0x0000ffff01ffff01, 0x0000ffff01000100, - 0x0000ff00ff000000, 0x0000ff00ff01ff00, 0x0000ff00ff0101ff, 0x0000ff0000ff0000, - 0x0000ff000000ff00, 0x0000ff00000000ff, 0x0000ff0000000000, 0x0000ff0000000001, - 0x0000ff0000000100, 0x0000ff0000010000, 0x0000ff0001ffffff, 0x0000ff0001ff01ff, - 0x0000ff0001000000, 0x0000ff000101ffff, 0x0000ff01ffff0101, 0x0000ff01ff010000, - 0x0000ff0100000000, 0x0000ff0101000101, 0x000000ffffff0001, 0x000000ffff000000, - 0x000000ff00ff0000, 0x000000ff0000ff00, 0x000000ff000000ff, 0x000000ff00000000, - 0x000000ff00000001, 0x000000ff00000100, 0x000000ff00010000, 0x000000ff01000000, - 0x000000ff0101ff00, 0x00000000ffff0000, 0x00000000ff00ff00, 0x00000000ff0000ff, - 0x00000000ff000000, 0x00000000ff000001, 0x00000000ff000100, 0x00000000ff010000, - 0x0000000000ffff00, 0x0000000000ff00ff, 0x0000000000ff0000, 0x0000000000ff0001, - 0x0000000000ff0100, 0x000000000000ffff, 0x000000000000ff00, 0x000000000000ff01, - 0x00000000000000ff, 0x0000000000000001, 0x00000000000001ff, 0x0000000000000100, - 0x0000000000000101, 0x000000000001ff00, 0x00000000000100ff, 0x0000000000010000, - 0x0000000000010001, 0x0000000000010100, 0x0000000001ff0000, 0x000000000100ff00, - 0x00000000010000ff, 0x0000000001000000, 0x0000000001000001, 0x0000000001000100, - 0x0000000001010000, 0x00000001ffff01ff, 0x00000001ff000000, 0x0000000100ff0000, - 0x000000010000ff00, 0x00000001000000ff, 0x0000000100000000, 0x0000000100000001, - 0x0000000100000100, 0x0000000100010000, 0x0000000101000000, 0x000001ffff00ff00, - 0x000001ffff010001, 0x000001ffff0101ff, 0x000001ff00ffff01, 0x000001ff0000ffff, - 0x000001ff00000000, 0x000001ff010000ff, 0x000001ff01010100, 0x00000100ffff0100, - 0x00000100ff000000, 0x0000010000ff0000, 0x000001000000ff00, 0x00000100000000ff, - 0x0000010000000000, 0x0000010000000001, 0x0000010000000100, 0x0000010000010000, - 0x0000010001000000, 0x000001000101ff01, 0x00000101ffff0001, 0x00000101ff01ffff, - 0x0000010100000000, 0x0000010101010100, 0x0001ffffff000000, 0x0001ffff00ffffff, - 0x0001ffff00000100, 0x0001ffff0001ff00, 0x0001ffff01000000, 0x0001ff00ffffff00, - 0x0001ff00ffff01ff, 0x0001ff00ff010000, 0x0001ff0000000000, 0x0001ff0000010001, - 0x0001ff0001ff0000, 0x0001ff0001010100, 0x0001ff01ff0000ff, 0x0001ff01ff000001, - 0x0001ff0100ffffff, 0x0001ff010001ffff, 0x0001ff01000101ff, 0x0001ff010100ff01, - 0x000100ffff00ffff, 0x000100ffff00ff01, 0x000100ffff000100, 0x000100ff00000000, - 0x000100ff000101ff, 0x000100ff01ff0101, 0x000100ff0100ffff, 0x000100ff01010101, - 0x00010000ff000000, 0x00010000ff010100, 0x0001000000ff0000, 0x000100000000ff00, - 0x00010000000000ff, 0x0001000000000000, 0x0001000000000001, 0x0001000000000100, - 0x0001000000010000, 0x0001000001ffff01, 0x0001000001000000, 0x0001000100ff0101, - 0x0001000100000000, 0x00010001010100ff, 0x000101ffffff01ff, 0x000101ffffff0101, - 0x000101ff00010000, 0x000101ff01ff0000, 0x000101ff0100ff01, 0x00010100ffff0000, - 0x0001010000000000, 0x000101000001ffff, 0x0001010000010101, 0x00010100010001ff, - 0x00010101ff00ff00, 0x00010101ff010001, 0x0001010100ffffff, 0x0001010100ff01ff, - 0x00010101000101ff, 0x0001010101ff0000, 0x000101010100ff01, 0x0001010101000101, - 0x01ffffffffff0101, 0x01ffffffff01ffff, 0x01ffffffff01ff01, 0x01ffffffff0101ff, - 0x01ffffffff010101, 0x01ffffff00000000, 0x01ffffff01ff01ff, 0x01ffffff01000101, - 0x01ffffff0101ff01, 0x01ffffff010100ff, 0x01ffff000000ff00, 0x01ffff0000000001, - 0x01ffff00000001ff, 0x01ffff0000010000, 0x01ffff0001ff0000, 0x01ffff01ffffffff, - 0x01ffff01ffff01ff, 0x01ffff01ff000000, 0x01ffff01ff01ffff, 0x01ffff01ff0101ff, - 0x01ffff010100ffff, 0x01ff00ffffff0000, 0x01ff00ffff010000, 0x01ff00ff00ffff01, - 0x01ff0000ff0000ff, 0x01ff000000000000, 0x01ff00000001ff01, 0x01ff000001ffffff, - 0x01ff000001010100, 0x01ff0001ffffff01, 0x01ff0001ff010001, 0x01ff000101ff0100, - 0x01ff000101000001, 0x01ff0001010100ff, 0x01ff01ffff00ffff, 0x01ff01ff00010001, - 0x01ff01ff01000000, 0x01ff01ff010101ff, 0x01ff0100ff000001, 0x01ff010000ffff00, - 0x01ff010000000100, 0x01ff010001ff01ff, 0x01ff01000101ffff, 0x01ff0101ffff00ff, - 0x01ff0101ffff0101, 0x01ff0101ff0101ff, 0x01ff010100010000, 0x0100ffff00ff00ff, - 0x0100ffff00ff0001, 0x0100ffff00000100, 0x0100ffff0100ff00, 0x0100ff00ffff0000, - 0x0100ff00ff00ffff, 0x0100ff00ff00ff01, 0x0100ff00ff000100, 0x0100ff00ff010000, - 0x0100ff0000000000, 0x0100ff00000100ff, 0x0100ff0001ff0101, 0x0100ff0001010101, - 0x0100ff0100ff00ff, 0x0100ff0100ff0001, 0x0100ff0100000100, 0x0100ff0100010001, - 0x0100ff0101000000, 0x010000ffff00ff00, 0x010000ff0000ffff, 0x010000ff00000000, - 0x010000ff010001ff, 0x010000ff01010001, 0x01000000ffffff00, 0x01000000ffff0101, - 0x01000000ff000000, 0x01000000ff0100ff, 0x01000000ff010101, 0x0100000000ff0000, - 0x010000000000ff00, 0x01000000000000ff, 0x0100000000000000, 0x0100000000000001, - 0x0100000000000100, 0x0100000000010000, 0x0100000001000000, 0x0100000100000000, - 0x01000001000101ff, 0x0100000101ffff01, 0x010001ffff000101, 0x010001ff00ff0100, - 0x010001ff0000ff00, 0x010001ff000100ff, 0x010001ff01ffffff, 0x01000100ffff0000, - 0x01000100ff0001ff, 0x0100010000000000, 0x010001000001ff00, 0x0100010001ff0000, - 0x01000100010000ff, 0x0100010001000101, 0x01000101ff00ff01, 0x0100010100ff0100, - 0x010001010000ffff, 0x0100010101010001, 0x0101ffffffff0101, 0x0101ffffff0001ff, - 0x0101ffffff01ffff, 0x0101ffffff010101, 0x0101ffff00000000, 0x0101ffff0101ffff, - 0x0101ffff010101ff, 0x0101ff00ff000000, 0x0101ff0000ff0100, 0x0101ff000000ff00, - 0x0101ff0000010000, 0x0101ff00010000ff, 0x0101ff0001000001, 0x0101ff01ff010101, - 0x0101ff0100000000, 0x0101ff010101ff00, 0x010100ffffff0000, 0x010100ffff010000, - 0x010100ff00ff01ff, 0x010100ff000000ff, 0x010100ff00000101, 0x010100ff01ffff00, - 0x01010000ffffff01, 0x01010000ff000100, 0x01010000ff01ff01, 0x0101000000000000, - 0x01010000000100ff, 0x010100000101ff01, 0x01010001ffff0000, 0x01010001ff00ffff, - 0x01010001ff010000, 0x0101000101ffffff, 0x0101000101ff01ff, 0x0101000101010101, - 0x010101ffff01ffff, 0x010101ff00000000, 0x010101ff0001ff01, 0x010101ff0101ffff, - 0x010101ff010101ff, 0x01010100ffffffff, 0x01010100ff000001, 0x010101000000ff00, - 0x0101010001010000, 0x0101010100ff0001, 0x010101010001ff01, 0x010101010101ffff, -}; - -constexpr constant static uint8_t ksigns_iq2xs[128] = { - 0, 129, 130, 3, 132, 5, 6, 135, 136, 9, 10, 139, 12, 141, 142, 15, - 144, 17, 18, 147, 20, 149, 150, 23, 24, 153, 154, 27, 156, 29, 30, 159, - 160, 33, 34, 163, 36, 165, 166, 39, 40, 169, 170, 43, 172, 45, 46, 175, - 48, 177, 178, 51, 180, 53, 54, 183, 184, 57, 58, 187, 60, 189, 190, 63, - 192, 65, 66, 195, 68, 197, 198, 71, 72, 201, 202, 75, 204, 77, 78, 207, - 80, 209, 210, 83, 212, 85, 86, 215, 216, 89, 90, 219, 92, 221, 222, 95, - 96, 225, 226, 99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111, - 240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255, -}; - -constexpr constant static uint8_t kmask_iq2xs[8] = {1, 2, 4, 8, 16, 32, 64, 128}; - void kernel_mul_mv_iq2_xxs_f32_impl( device const void * src0, device const float * src1, @@ -5039,48 +4163,53 @@ void kernel_mul_mv_iq1_s_f32_impl( device const block_iq1_s * x = (device const block_iq1_s *) src0 + ib_row + offset0; device const float * y = (device const float *) src1 + r1*ne10 + im*ne00*ne1; - float yl[16]; + float yl[32]; float sumf[N_DST]={0.f}, all_sum; const int nb32 = nb * (QK_K / 32); - const int ix = tiisg/2; - const int il = tiisg%2; + const int ix = tiisg; - device const float * y4 = y + 32 * ix + 16 * il; + device const float * y4 = y + 32 * ix; - for (int ib32 = ix; ib32 < nb32; ib32 += 16) { + for (int ib32 = ix; ib32 < nb32; ib32 += 32) { - for (int i = 0; i < 16; ++i) { + float sumy = 0; + for (int i = 0; i < 32; ++i) { yl[i] = y4[i]; + sumy += yl[i]; } const int ibl = ib32 / (QK_K / 32); const int ib = ib32 % (QK_K / 32); device const block_iq1_s * xr = x + ibl; - device const uint8_t * qs = xr->qs + 4 * ib + 2 * il; - device const uint8_t * sc = xr->scales + 2 * ib + il; - device const half * dh = &xr->d; + device const uint8_t * qs = xr->qs + 4 * ib; + device const uint16_t * qh = xr->qh + ib; + device const half * dh = &xr->d; for (int row = 0; row < N_DST; row++) { - constant int8_t * grid1 = (constant int8_t *)(iq1s_grid + (qs[0] | ((sc[0] & 0x08) << 5))); - constant int8_t * grid2 = (constant int8_t *)(iq1s_grid + (qs[1] | ((sc[0] & 0x80) << 1))); + constant uint8_t * grid1 = (constant uint8_t *)(iq1s_grid_gpu + (qs[0] | ((qh[0] << 8) & 0x700))); + constant uint8_t * grid2 = (constant uint8_t *)(iq1s_grid_gpu + (qs[1] | ((qh[0] << 5) & 0x700))); + constant uint8_t * grid3 = (constant uint8_t *)(iq1s_grid_gpu + (qs[2] | ((qh[0] << 2) & 0x700))); + constant uint8_t * grid4 = (constant uint8_t *)(iq1s_grid_gpu + (qs[3] | ((qh[0] >> 1) & 0x700))); - float2 sum = {0}; - for (int j = 0; j < 8; ++j) { - sum[0] += yl[j+ 0] * grid1[j]; - sum[1] += yl[j+ 8] * grid2[j]; + float sum = 0; + for (int j = 0; j < 4; ++j) { + sum += yl[j+ 0] * (grid1[j] & 0xf) + yl[j+ 4] * (grid1[j] >> 4) + + yl[j+ 8] * (grid2[j] & 0xf) + yl[j+12] * (grid2[j] >> 4) + + yl[j+16] * (grid3[j] & 0xf) + yl[j+20] * (grid3[j] >> 4) + + yl[j+24] * (grid4[j] & 0xf) + yl[j+28] * (grid4[j] >> 4); } - sumf[row] += (float)dh[0] * (sum[0] * (2*(sc[0] & 7) + 1) + sum[1] * (2*((sc[0] >> 4) & 7) + 1)); + sumf[row] += (float)dh[0] * (sum + sumy * (qh[0] & 0x8000 ? -1 - IQ1S_DELTA : -1 + IQ1S_DELTA)) * (2*((qh[0] >> 12) & 7) + 1); dh += nb*sizeof(block_iq1_s)/2; qs += nb*sizeof(block_iq1_s); - sc += nb*sizeof(block_iq1_s); + qh += nb*sizeof(block_iq1_s)/2; } - y4 += 16 * 32; + y4 += 32 * 32; } for (int row = 0; row < N_DST; ++row) { @@ -5767,16 +4896,21 @@ void dequantize_iq2_s(device const block_iq2_s * xb, short il, thread type4x4 & template void dequantize_iq1_s(device const block_iq1_s * xb, short il, thread type4x4 & reg) { // il is 0...15 for QK_K = 256 => index of block of 32 is il/2 + const int ib32 = il/2; + il = il%2; const float d = xb->d; - device const uint8_t * qs = xb->qs + 2*il; - device const uint8_t * sc = xb->scales + il; - const float dl1 = d * (2*(sc[0] & 7) + 1); - const float dl2 = d * (2*((sc[0] >> 4) & 7) + 1); - constant int8_t * grid1 = (constant int8_t *)(iq1s_grid + (qs[0] | ((sc[0] & 0x08) << 5))); - constant int8_t * grid2 = (constant int8_t *)(iq1s_grid + (qs[1] | ((sc[0] & 0x80) << 1))); - for (int i = 0; i < 8; ++i) { - reg[i/4+0][i%4] = dl1 * grid1[i]; - reg[i/4+2][i%4] = dl2 * grid2[i]; + device const uint8_t * qs = xb->qs + 4*ib32 + 2*il; + device const uint16_t * qh = xb->qh; + const float dl = d * (2*((qh[ib32] >> 12) & 7) + 1); + const float ml = dl * (qh[ib32] & 0x8000 ? -1 - IQ1S_DELTA : -1 + IQ1S_DELTA); + const uint16_t h = qh[ib32] >> 6*il; + constant uint8_t * grid1 = (constant uint8_t *)(iq1s_grid_gpu + (qs[0] | ((h << 8) & 0x700))); + constant uint8_t * grid2 = (constant uint8_t *)(iq1s_grid_gpu + (qs[1] | ((h << 5) & 0x700))); + for (int i = 0; i < 4; ++i) { + reg[0][i] = dl * (grid1[i] & 0xf) + ml; + reg[1][i] = dl * (grid1[i] >> 4) + ml; + reg[2][i] = dl * (grid2[i] & 0xf) + ml; + reg[3][i] = dl * (grid2[i] >> 4) + ml; } } @@ -6087,7 +5221,7 @@ template #include #include @@ -948,7 +954,7 @@ void quantize_row_q8_1_reference(const float * restrict x, block_q8_1 * restrict const float d = amax / ((1 << 7) - 1); const float id = d ? 1.0f/d : 0.0f; - y[i].d = d; + y[i].d = GGML_FP32_TO_FP16(d); int sum = 0; @@ -963,7 +969,7 @@ void quantize_row_q8_1_reference(const float * restrict x, block_q8_1 * restrict sum += y[i].qs[QK8_1/2 + j]; } - y[i].s = sum*d; + y[i].s = GGML_FP32_TO_FP16(sum*d); } } @@ -991,7 +997,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) { const float d = amax / ((1 << 7) - 1); const float id = d ? 1.0f/d : 0.0f; - y[i].d = d; + y[i].d = GGML_FP32_TO_FP16(d); int32x4_t accv = vdupq_n_s32(0); @@ -1007,7 +1013,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) { accv = vaddq_s32(accv, vi); } - y[i].s = d * vaddvq_s32(accv); + y[i].s = GGML_FP32_TO_FP16(d * vaddvq_s32(accv)); } #elif defined(__wasm_simd128__) for (int i = 0; i < nb; i++) { @@ -1030,7 +1036,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) { const float d = amax / ((1 << 7) - 1); const float id = d ? 1.0f/d : 0.0f; - y[i].d = d; + y[i].d = GGML_FP32_TO_FP16(d); v128_t accv = wasm_i32x4_splat(0); @@ -1046,10 +1052,11 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) { accv = wasm_i32x4_add(accv, vi); } - y[i].s = d * (wasm_i32x4_extract_lane(accv, 0) + - wasm_i32x4_extract_lane(accv, 1) + - wasm_i32x4_extract_lane(accv, 2) + - wasm_i32x4_extract_lane(accv, 3)); + y[i].s = GGML_FP32_TO_FP16( + d * (wasm_i32x4_extract_lane(accv, 0) + + wasm_i32x4_extract_lane(accv, 1) + + wasm_i32x4_extract_lane(accv, 2) + + wasm_i32x4_extract_lane(accv, 3))); } #elif defined(__AVX2__) || defined(__AVX__) for (int i = 0; i < nb; i++) { @@ -1074,7 +1081,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) { // Quantize these floats const float d = maxScalar / 127.f; - y[i].d = d; + y[i].d = GGML_FP32_TO_FP16(d); const float id = ( maxScalar != 0.0f ) ? 127.f / maxScalar : 0.0f; const __m256 mul = _mm256_set1_ps( id ); @@ -1098,7 +1105,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) { #if defined(__AVX2__) // Compute the sum of the quants and set y[i].s - y[i].s = d * hsum_i32_8(_mm256_add_epi32(_mm256_add_epi32(i0, i1), _mm256_add_epi32(i2, i3))); + y[i].s = GGML_FP32_TO_FP16(d * hsum_i32_8(_mm256_add_epi32(_mm256_add_epi32(i0, i1), _mm256_add_epi32(i2, i3)))); // Convert int32 to int16 i0 = _mm256_packs_epi32( i0, i1 ); // 0, 1, 2, 3, 8, 9, 10, 11, 4, 5, 6, 7, 12, 13, 14, 15 @@ -1128,7 +1135,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) { // Compute the sum of the quants and set y[i].s const __m128i s0 = _mm_add_epi32(_mm_add_epi32(ni0, ni1), _mm_add_epi32(ni2, ni3)); const __m128i s1 = _mm_add_epi32(_mm_add_epi32(ni4, ni5), _mm_add_epi32(ni6, ni7)); - y[i].s = d * hsum_i32_4(_mm_add_epi32(s0, s1)); + y[i].s = GGML_FP32_TO_FP16(d * hsum_i32_4(_mm_add_epi32(s0, s1))); // Convert int32 to int16 ni0 = _mm_packs_epi32( ni0, ni1 ); @@ -1159,7 +1166,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) { const float d = amax / ((1 << 7) - 1); const float id = d ? 1.0f/d : 0.0f; - y[i].d = d; + y[i].d = GGML_FP32_TO_FP16(d); vfloat32m4_t x0 = __riscv_vfmul_vf_f32m4(v_x, id, vl); @@ -1176,7 +1183,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) { // set y[i].s int sum = __riscv_vmv_x_s_i16m1_i16(vwrs); - y[i].s = sum*d; + y[i].s = GGML_FP32_TO_FP16(sum*d); } #else GGML_UNUSED(nb); @@ -1701,16 +1708,6 @@ void quantize_row_q2_K(const float * restrict x, void * restrict vy, int k) { quantize_row_q2_K_reference(x, vy, k); } -size_t ggml_quantize_q2_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) { - (void)hist; // TODO: collect histograms - - for (int j = 0; j < n; j += k) { - block_q2_K * restrict y = (block_q2_K *)dst + j/QK_K; - quantize_row_q2_K_reference(src + j, y, k); - } - return (n/QK_K*sizeof(block_q2_K)); -} - static float make_qkx3_quants(int n, int nmax, const float * restrict x, const float * restrict weights, uint8_t * restrict L, float * restrict the_min, uint8_t * restrict Laux, float rmin, float rdelta, int nstep, bool use_mad) { @@ -1963,8 +1960,7 @@ static void quantize_row_q2_K_impl(const float * restrict x, block_q2_K * restri } } -size_t quantize_q2_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { - (void)hist; +size_t quantize_q2_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { size_t row_size = ggml_row_size(GGML_TYPE_Q2_K, n_per_row); if (!quant_weights) { quantize_row_q2_K_reference(src, dst, nrow*n_per_row); @@ -2183,16 +2179,6 @@ void quantize_row_q3_K(const float * restrict x, void * restrict vy, int k) { quantize_row_q3_K_reference(x, vy, k); } -size_t ggml_quantize_q3_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) { - (void)hist; // TODO: collect histograms - - for (int j = 0; j < n; j += k) { - block_q3_K * restrict y = (block_q3_K *)dst + j/QK_K; - quantize_row_q3_K_reference(src + j, y, k); - } - return (n/QK_K*sizeof(block_q3_K)); -} - static void quantize_row_q3_K_impl(const float * restrict x, block_q3_K * restrict y, int n_per_row, const float * restrict quant_weights) { #if QK_K != 256 (void)quant_weights; @@ -2282,8 +2268,7 @@ static void quantize_row_q3_K_impl(const float * restrict x, block_q3_K * restri #endif } -size_t quantize_q3_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { - (void)hist; +size_t quantize_q3_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { size_t row_size = ggml_row_size(GGML_TYPE_Q3_K, n_per_row); if (!quant_weights) { quantize_row_q3_K_reference(src, dst, nrow*n_per_row); @@ -2453,17 +2438,6 @@ void quantize_row_q4_K(const float * restrict x, void * restrict vy, int k) { quantize_row_q4_K_reference(x, y, k); } -size_t ggml_quantize_q4_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) { - assert(k % QK_K == 0); - (void)hist; // TODO: collect histograms - - for (int j = 0; j < n; j += k) { - block_q4_K * restrict y = (block_q4_K *)dst + j/QK_K; - quantize_row_q4_K_reference(src + j, y, k); - } - return (n/QK_K*sizeof(block_q4_K)); -} - static void quantize_row_q4_K_impl(const float * restrict x, block_q4_K * restrict y, int n_per_row, const float * quant_weights) { #if QK_K != 256 (void)quant_weights; @@ -2542,8 +2516,7 @@ static void quantize_row_q4_K_impl(const float * restrict x, block_q4_K * restri #endif } -size_t quantize_q4_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { - (void)hist; +size_t quantize_q4_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { size_t row_size = ggml_row_size(GGML_TYPE_Q4_K, n_per_row); if (!quant_weights) { quantize_row_q4_K_reference(src, dst, nrow*n_per_row); @@ -2754,17 +2727,6 @@ void quantize_row_q5_K(const float * restrict x, void * restrict vy, int k) { quantize_row_q5_K_reference(x, y, k); } -size_t ggml_quantize_q5_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) { - assert(k % QK_K == 0); - (void)hist; // TODO: collect histograms - - for (int j = 0; j < n; j += k) { - block_q5_K * restrict y = (block_q5_K *)dst + j/QK_K; - quantize_row_q5_K_reference(src + j, y, k); - } - return (n/QK_K*sizeof(block_q5_K)); -} - static void quantize_row_q5_K_impl(const float * restrict x, block_q5_K * restrict y, int n_per_row, const float * quant_weights) { #if QK_K != 256 (void)quant_weights; @@ -2863,8 +2825,7 @@ static void quantize_row_q5_K_impl(const float * restrict x, block_q5_K * restri #endif } -size_t quantize_q5_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { - (void)hist; +size_t quantize_q5_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { size_t row_size = ggml_row_size(GGML_TYPE_Q5_K, n_per_row); if (!quant_weights) { quantize_row_q5_K_reference(src, dst, nrow*n_per_row); @@ -3017,17 +2978,6 @@ void quantize_row_q6_K(const float * restrict x, void * restrict vy, int k) { quantize_row_q6_K_reference(x, y, k); } -size_t ggml_quantize_q6_K(const float * src, void * dst, int n, int k, int64_t * hist) { - assert(k % QK_K == 0); - (void)hist; // TODO: collect histograms - - for (int j = 0; j < n; j += k) { - block_q6_K * restrict y = (block_q6_K *)dst + j/QK_K; - quantize_row_q6_K_reference(src + j, y, k); - } - return (n/QK_K*sizeof(block_q6_K)); -} - static void quantize_row_q6_K_impl(const float * restrict x, block_q6_K * restrict y, int n_per_row, const float * quant_weights) { #if QK_K != 256 (void)quant_weights; @@ -3117,8 +3067,7 @@ static void quantize_row_q6_K_impl(const float * restrict x, block_q6_K * restri #endif } -size_t quantize_q6_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { - (void)hist; +size_t quantize_q6_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { size_t row_size = ggml_row_size(GGML_TYPE_Q6_K, n_per_row); if (!quant_weights) { quantize_row_q6_K_reference(src, dst, nrow*n_per_row); @@ -3162,9 +3111,10 @@ static void quantize_row_q4_0_impl(const float * restrict x, block_q4_0 * restri } } -size_t quantize_q4_0(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { +size_t quantize_q4_0(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { if (!quant_weights) { - return ggml_quantize_q4_0(src, dst, nrow*n_per_row, n_per_row, hist); + quantize_row_q4_0_reference(src, dst, nrow*n_per_row); + return nrow * ggml_row_size(GGML_TYPE_Q4_0, n_per_row); } size_t row_size = ggml_row_size(GGML_TYPE_Q4_0, n_per_row); char * qrow = (char *)dst; @@ -3206,9 +3156,10 @@ static void quantize_row_q4_1_impl(const float * restrict x, block_q4_1 * restri } } -size_t quantize_q4_1(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { +size_t quantize_q4_1(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { if (!quant_weights) { - return ggml_quantize_q4_1(src, dst, nrow*n_per_row, n_per_row, hist); + quantize_row_q4_1_reference(src, dst, nrow*n_per_row); + return nrow * ggml_row_size(GGML_TYPE_Q4_1, n_per_row); } size_t row_size = ggml_row_size(GGML_TYPE_Q4_1, n_per_row); char * qrow = (char *)dst; @@ -3259,9 +3210,10 @@ static void quantize_row_q5_0_impl(const float * restrict x, block_q5_0 * restri } } -size_t quantize_q5_0(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { +size_t quantize_q5_0(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { if (!quant_weights) { - return ggml_quantize_q5_0(src, dst, nrow*n_per_row, n_per_row, hist); + quantize_row_q5_0_reference(src, dst, nrow*n_per_row); + return nrow * ggml_row_size(GGML_TYPE_Q5_0, n_per_row); } size_t row_size = ggml_row_size(GGML_TYPE_Q5_0, n_per_row); char * qrow = (char *)dst; @@ -3311,9 +3263,10 @@ static void quantize_row_q5_1_impl(const float * restrict x, block_q5_1 * restri } } -size_t quantize_q5_1(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { +size_t quantize_q5_1(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { if (!quant_weights) { - return ggml_quantize_q5_1(src, dst, nrow*n_per_row, n_per_row, hist); + quantize_row_q5_1_reference(src, dst, nrow*n_per_row); + return nrow * ggml_row_size(GGML_TYPE_Q5_1, n_per_row); } size_t row_size = ggml_row_size(GGML_TYPE_Q5_1, n_per_row); char * qrow = (char *)dst; @@ -3325,712 +3278,14 @@ size_t quantize_q5_1(const float * src, void * dst, int nrow, int n_per_row, int return nrow * row_size; } -// ====================== "True" 2-bit (de)-quantization - -static const uint64_t iq2xxs_grid[256] = { - 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, - 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808, - 0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819, - 0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819, - 0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b, - 0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808, - 0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08, - 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b, - 0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819, - 0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08, - 0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808, - 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08, - 0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808, - 0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808, - 0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919, - 0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819, - 0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08, - 0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908, - 0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819, - 0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808, - 0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808, - 0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908, - 0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808, - 0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08, - 0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819, - 0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819, - 0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819, - 0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908, - 0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19, - 0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819, - 0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b, - 0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808, - 0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908, - 0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08, - 0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08, - 0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908, - 0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819, - 0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808, - 0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808, - 0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19, - 0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819, - 0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, - 0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b, - 0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08, - 0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808, - 0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908, - 0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b, - 0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819, - 0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08, - 0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08, - 0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808, - 0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b, - 0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b, - 0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908, - 0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819, - 0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808, - 0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908, - 0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b, - 0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808, - 0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b, - 0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b, - 0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808, - 0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19, - 0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908, -}; - -static const uint64_t iq2xs_grid[512] = { - 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, - 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b, - 0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919, - 0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b, - 0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919, - 0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808, - 0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819, - 0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819, - 0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, - 0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b, - 0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b, - 0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908, - 0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908, - 0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919, - 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808, - 0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919, - 0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908, - 0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, - 0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, - 0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08, - 0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808, - 0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808, - 0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819, - 0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908, - 0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819, - 0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808, - 0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b, - 0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819, - 0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819, - 0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808, - 0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908, - 0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19, - 0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b, - 0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b, - 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919, - 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808, - 0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819, - 0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819, - 0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b, - 0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908, - 0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808, - 0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819, - 0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808, - 0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919, - 0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808, - 0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808, - 0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908, - 0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908, - 0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808, - 0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b, - 0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819, - 0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, - 0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908, - 0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808, - 0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908, - 0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919, - 0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08, - 0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19, - 0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b, - 0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b, - 0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808, - 0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08, - 0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b, - 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908, - 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b, - 0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908, - 0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, - 0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808, - 0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808, - 0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08, - 0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819, - 0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919, - 0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808, - 0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808, - 0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819, - 0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819, - 0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908, - 0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908, - 0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b, - 0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908, - 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908, - 0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908, - 0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808, - 0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, - 0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819, - 0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819, - 0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808, - 0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b, - 0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819, - 0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819, - 0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08, - 0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808, - 0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19, - 0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919, - 0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808, - 0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19, - 0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b, - 0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808, - 0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b, - 0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b, - 0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, - 0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b, - 0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808, - 0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819, - 0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808, - 0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808, - 0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08, - 0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b, - 0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19, - 0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08, - 0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919, - 0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08, - 0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08, - 0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908, - 0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908, - 0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b, - 0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908, - 0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808, - 0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b, - 0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808, - 0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808, - 0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19, - 0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08, - 0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808, - 0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b, - 0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808, - 0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b, - 0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b, -}; - -static const uint64_t iq2s_grid[1024] = { - 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, - 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b, - 0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919, - 0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b, - 0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919, - 0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x08080808192b192b, - 0x08080808192b2b19, 0x080808082b080808, 0x080808082b08082b, 0x080808082b081919, - 0x080808082b082b08, 0x080808082b190819, 0x080808082b191908, 0x080808082b2b0808, - 0x080808082b2b1919, 0x080808082b2b2b2b, 0x0808081908080819, 0x0808081908081908, - 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, 0x080808190819082b, - 0x0808081908191919, 0x0808081908192b08, 0x08080819082b0819, 0x08080819082b1908, - 0x0808081919080808, 0x080808191908082b, 0x0808081919081919, 0x0808081919082b08, - 0x0808081919190819, 0x0808081919191908, 0x080808191919192b, 0x0808081919192b19, - 0x08080819192b0808, 0x08080819192b1919, 0x08080819192b2b08, 0x080808192b080819, - 0x080808192b081908, 0x080808192b190808, 0x080808192b19082b, 0x080808192b191919, - 0x080808192b2b0819, 0x080808192b2b1908, 0x0808082b08080808, 0x0808082b0808082b, - 0x0808082b08081919, 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, - 0x0808082b082b0808, 0x0808082b082b2b2b, 0x0808082b19080819, 0x0808082b19081908, - 0x0808082b1908192b, 0x0808082b19082b19, 0x0808082b19190808, 0x0808082b19191919, - 0x0808082b2b080808, 0x0808082b2b081919, 0x0808082b2b082b2b, 0x0808082b2b191908, - 0x0808082b2b2b082b, 0x0808190808080819, 0x0808190808081908, 0x080819080808192b, - 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, 0x0808190808191919, - 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, 0x08081908082b192b, - 0x08081908082b2b19, 0x0808190819080808, 0x080819081908082b, 0x0808190819081919, - 0x0808190819082b08, 0x0808190819082b2b, 0x0808190819190819, 0x0808190819191908, - 0x080819081919192b, 0x0808190819192b19, 0x08081908192b0808, 0x08081908192b082b, - 0x08081908192b1919, 0x080819082b080819, 0x080819082b081908, 0x080819082b08192b, - 0x080819082b082b19, 0x080819082b190808, 0x080819082b191919, 0x080819082b192b08, - 0x080819082b2b0819, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, - 0x0808191908081919, 0x0808191908082b08, 0x0808191908082b2b, 0x0808191908190819, - 0x0808191908191908, 0x080819190819192b, 0x0808191908192b19, 0x08081919082b0808, - 0x08081919082b1919, 0x08081919082b2b08, 0x0808191919080819, 0x0808191919081908, - 0x080819191908192b, 0x0808191919082b19, 0x0808191919190808, 0x080819191919082b, - 0x0808191919191919, 0x0808191919192b08, 0x08081919192b0819, 0x08081919192b1908, - 0x080819192b080808, 0x080819192b08082b, 0x080819192b081919, 0x080819192b082b08, - 0x080819192b190819, 0x080819192b191908, 0x080819192b2b0808, 0x0808192b08080819, - 0x0808192b08081908, 0x0808192b0808192b, 0x0808192b08082b19, 0x0808192b08190808, - 0x0808192b08191919, 0x0808192b19080808, 0x0808192b19081919, 0x0808192b19082b08, - 0x0808192b19190819, 0x0808192b19191908, 0x0808192b192b0808, 0x0808192b2b080819, - 0x0808192b2b081908, 0x0808192b2b190808, 0x08082b0808080808, 0x08082b080808082b, - 0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808190819, 0x08082b0808191908, - 0x08082b080819192b, 0x08082b0808192b19, 0x08082b08082b0808, 0x08082b08082b1919, - 0x08082b08082b2b2b, 0x08082b0819080819, 0x08082b0819081908, 0x08082b081908192b, - 0x08082b0819082b19, 0x08082b0819190808, 0x08082b081919082b, 0x08082b0819191919, - 0x08082b0819192b08, 0x08082b08192b0819, 0x08082b08192b1908, 0x08082b082b080808, - 0x08082b082b081919, 0x08082b082b191908, 0x08082b082b2b2b2b, 0x08082b1908080819, - 0x08082b1908081908, 0x08082b1908190808, 0x08082b190819082b, 0x08082b1908191919, - 0x08082b1908192b08, 0x08082b19082b0819, 0x08082b1919080808, 0x08082b1919081919, - 0x08082b1919082b08, 0x08082b1919190819, 0x08082b1919191908, 0x08082b19192b0808, - 0x08082b192b080819, 0x08082b192b190808, 0x08082b2b08080808, 0x08082b2b08190819, - 0x08082b2b08191908, 0x08082b2b082b082b, 0x08082b2b082b2b08, 0x08082b2b082b2b2b, - 0x08082b2b19190808, 0x08082b2b2b192b19, 0x0819080808080819, 0x0819080808081908, - 0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, - 0x0819080808191919, 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, - 0x08190808082b192b, 0x0819080819080808, 0x081908081908082b, 0x0819080819081919, - 0x0819080819082b08, 0x0819080819190819, 0x0819080819191908, 0x081908081919192b, - 0x0819080819192b19, 0x08190808192b0808, 0x08190808192b082b, 0x08190808192b1919, - 0x08190808192b2b08, 0x081908082b080819, 0x081908082b081908, 0x081908082b08192b, - 0x081908082b190808, 0x081908082b191919, 0x081908082b192b08, 0x081908082b2b0819, - 0x081908082b2b1908, 0x0819081908080808, 0x081908190808082b, 0x0819081908081919, - 0x0819081908082b08, 0x0819081908082b2b, 0x0819081908190819, 0x0819081908191908, - 0x081908190819192b, 0x0819081908192b19, 0x08190819082b0808, 0x08190819082b082b, - 0x08190819082b1919, 0x08190819082b2b08, 0x0819081919080819, 0x0819081919081908, - 0x081908191908192b, 0x0819081919082b19, 0x0819081919190808, 0x081908191919082b, - 0x0819081919191919, 0x0819081919192b08, 0x08190819192b0819, 0x08190819192b1908, - 0x081908192b080808, 0x081908192b08082b, 0x081908192b081919, 0x081908192b082b08, - 0x081908192b190819, 0x081908192b191908, 0x0819082b08080819, 0x0819082b08081908, - 0x0819082b08082b19, 0x0819082b08190808, 0x0819082b08191919, 0x0819082b082b0819, - 0x0819082b082b1908, 0x0819082b19080808, 0x0819082b19081919, 0x0819082b19190819, - 0x0819082b19191908, 0x0819082b2b080819, 0x0819082b2b081908, 0x0819082b2b190808, - 0x0819190808080808, 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08, - 0x0819190808190819, 0x0819190808191908, 0x081919080819192b, 0x0819190808192b19, - 0x08191908082b0808, 0x08191908082b1919, 0x08191908082b2b08, 0x0819190819080819, - 0x0819190819081908, 0x081919081908192b, 0x0819190819082b19, 0x0819190819190808, - 0x081919081919082b, 0x0819190819191919, 0x0819190819192b08, 0x08191908192b0819, - 0x08191908192b1908, 0x081919082b080808, 0x081919082b08082b, 0x081919082b081919, - 0x081919082b082b08, 0x081919082b190819, 0x081919082b191908, 0x081919082b2b0808, - 0x0819191908080819, 0x0819191908081908, 0x081919190808192b, 0x0819191908082b19, - 0x0819191908190808, 0x081919190819082b, 0x0819191908191919, 0x0819191908192b08, - 0x08191919082b0819, 0x08191919082b1908, 0x0819191919080808, 0x081919191908082b, - 0x0819191919081919, 0x0819191919082b08, 0x0819191919190819, 0x0819191919191908, - 0x08191919192b0808, 0x081919192b080819, 0x081919192b081908, 0x081919192b190808, - 0x0819192b08080808, 0x0819192b08081919, 0x0819192b08082b08, 0x0819192b08190819, - 0x0819192b08191908, 0x0819192b082b0808, 0x0819192b19080819, 0x0819192b19081908, - 0x0819192b19190808, 0x0819192b2b080808, 0x0819192b2b2b2b2b, 0x08192b0808080819, - 0x08192b0808081908, 0x08192b080808192b, 0x08192b0808082b19, 0x08192b0808190808, - 0x08192b0808191919, 0x08192b0808192b08, 0x08192b08082b0819, 0x08192b0819080808, - 0x08192b081908082b, 0x08192b0819081919, 0x08192b0819082b08, 0x08192b0819190819, - 0x08192b0819191908, 0x08192b08192b0808, 0x08192b082b080819, 0x08192b082b081908, - 0x08192b1908080808, 0x08192b190808082b, 0x08192b1908081919, 0x08192b1908082b08, - 0x08192b1908190819, 0x08192b1908191908, 0x08192b19082b0808, 0x08192b1919080819, - 0x08192b1919081908, 0x08192b1919190808, 0x08192b19192b2b19, 0x08192b192b2b082b, - 0x08192b2b08081908, 0x08192b2b08190808, 0x08192b2b19080808, 0x08192b2b1919192b, - 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, 0x082b080808082b08, - 0x082b080808190819, 0x082b080808191908, 0x082b08080819192b, 0x082b080808192b19, - 0x082b0808082b0808, 0x082b0808082b1919, 0x082b0808082b2b2b, 0x082b080819080819, - 0x082b080819081908, 0x082b080819190808, 0x082b08081919082b, 0x082b080819191919, - 0x082b0808192b1908, 0x082b08082b080808, 0x082b08082b082b2b, 0x082b08082b191908, - 0x082b08082b2b2b2b, 0x082b081908080819, 0x082b081908081908, 0x082b081908190808, - 0x082b08190819082b, 0x082b081908191919, 0x082b0819082b0819, 0x082b081919080808, - 0x082b08191908082b, 0x082b081919081919, 0x082b081919190819, 0x082b081919191908, - 0x082b0819192b0808, 0x082b08192b080819, 0x082b08192b081908, 0x082b08192b190808, - 0x082b082b08080808, 0x082b082b08082b2b, 0x082b082b082b082b, 0x082b082b082b2b08, - 0x082b082b082b2b2b, 0x082b082b19081908, 0x082b082b19190808, 0x082b082b2b082b08, - 0x082b082b2b082b2b, 0x082b082b2b2b2b08, 0x082b190808080819, 0x082b190808081908, - 0x082b19080808192b, 0x082b190808082b19, 0x082b190808190808, 0x082b190808191919, - 0x082b190808192b08, 0x082b1908082b0819, 0x082b1908082b1908, 0x082b190819080808, - 0x082b19081908082b, 0x082b190819081919, 0x082b190819082b08, 0x082b190819190819, - 0x082b190819191908, 0x082b1908192b0808, 0x082b19082b080819, 0x082b19082b081908, - 0x082b19082b190808, 0x082b191908080808, 0x082b191908081919, 0x082b191908082b08, - 0x082b191908190819, 0x082b191908191908, 0x082b1919082b0808, 0x082b191919080819, - 0x082b191919081908, 0x082b191919190808, 0x082b1919192b192b, 0x082b19192b080808, - 0x082b192b08080819, 0x082b192b08081908, 0x082b192b08190808, 0x082b192b19080808, - 0x082b192b19192b19, 0x082b2b0808080808, 0x082b2b0808081919, 0x082b2b0808190819, - 0x082b2b0808191908, 0x082b2b0819080819, 0x082b2b0819081908, 0x082b2b0819190808, - 0x082b2b082b082b2b, 0x082b2b082b2b2b2b, 0x082b2b1908080819, 0x082b2b1908081908, - 0x082b2b1908190808, 0x082b2b192b191919, 0x082b2b2b08082b2b, 0x082b2b2b082b082b, - 0x082b2b2b192b1908, 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, - 0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, - 0x190808080819082b, 0x1908080808191919, 0x1908080808192b08, 0x1908080808192b2b, - 0x19080808082b0819, 0x19080808082b1908, 0x19080808082b192b, 0x1908080819080808, - 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, 0x1908080819082b2b, - 0x1908080819190819, 0x1908080819191908, 0x190808081919192b, 0x1908080819192b19, - 0x19080808192b0808, 0x19080808192b082b, 0x19080808192b1919, 0x190808082b080819, - 0x190808082b081908, 0x190808082b190808, 0x190808082b191919, 0x190808082b192b08, - 0x190808082b2b0819, 0x190808082b2b1908, 0x1908081908080808, 0x190808190808082b, - 0x1908081908081919, 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908, - 0x190808190819192b, 0x1908081908192b19, 0x19080819082b0808, 0x19080819082b082b, - 0x19080819082b1919, 0x1908081919080819, 0x1908081919081908, 0x190808191908192b, - 0x1908081919082b19, 0x1908081919190808, 0x190808191919082b, 0x1908081919191919, - 0x1908081919192b08, 0x19080819192b0819, 0x19080819192b1908, 0x190808192b080808, - 0x190808192b08082b, 0x190808192b081919, 0x190808192b082b08, 0x190808192b190819, - 0x190808192b191908, 0x190808192b2b0808, 0x1908082b08080819, 0x1908082b08081908, - 0x1908082b08190808, 0x1908082b0819082b, 0x1908082b08191919, 0x1908082b08192b08, - 0x1908082b082b1908, 0x1908082b19080808, 0x1908082b19081919, 0x1908082b19082b08, - 0x1908082b19190819, 0x1908082b19191908, 0x1908082b192b0808, 0x1908082b2b080819, - 0x1908082b2b081908, 0x1908190808080808, 0x190819080808082b, 0x1908190808081919, - 0x1908190808082b08, 0x1908190808082b2b, 0x1908190808190819, 0x1908190808191908, - 0x190819080819192b, 0x1908190808192b19, 0x19081908082b0808, 0x19081908082b082b, - 0x19081908082b1919, 0x19081908082b2b08, 0x1908190819080819, 0x1908190819081908, - 0x190819081908192b, 0x1908190819082b19, 0x1908190819190808, 0x190819081919082b, - 0x1908190819191919, 0x1908190819192b08, 0x19081908192b0819, 0x19081908192b1908, - 0x190819082b080808, 0x190819082b08082b, 0x190819082b081919, 0x190819082b082b08, - 0x190819082b190819, 0x190819082b191908, 0x190819082b2b0808, 0x1908191908080819, - 0x1908191908081908, 0x190819190808192b, 0x1908191908082b19, 0x1908191908190808, - 0x190819190819082b, 0x1908191908191919, 0x1908191908192b08, 0x19081919082b0819, - 0x19081919082b1908, 0x1908191919080808, 0x190819191908082b, 0x1908191919081919, - 0x1908191919082b08, 0x1908191919190819, 0x1908191919191908, 0x19081919192b0808, - 0x19081919192b2b2b, 0x190819192b080819, 0x190819192b081908, 0x190819192b190808, - 0x1908192b08080808, 0x1908192b0808082b, 0x1908192b08081919, 0x1908192b08082b08, - 0x1908192b08190819, 0x1908192b08191908, 0x1908192b082b0808, 0x1908192b19080819, - 0x1908192b19081908, 0x1908192b19190808, 0x1908192b2b080808, 0x1908192b2b2b1919, - 0x19082b0808080819, 0x19082b0808081908, 0x19082b0808082b19, 0x19082b0808190808, - 0x19082b080819082b, 0x19082b0808191919, 0x19082b0808192b08, 0x19082b08082b0819, - 0x19082b08082b1908, 0x19082b0819080808, 0x19082b081908082b, 0x19082b0819081919, - 0x19082b0819082b08, 0x19082b0819190819, 0x19082b0819191908, 0x19082b08192b0808, - 0x19082b082b081908, 0x19082b082b190808, 0x19082b1908080808, 0x19082b190808082b, - 0x19082b1908081919, 0x19082b1908082b08, 0x19082b1908190819, 0x19082b1908191908, - 0x19082b19082b0808, 0x19082b1919080819, 0x19082b1919081908, 0x19082b1919190808, - 0x19082b192b080808, 0x19082b192b19192b, 0x19082b2b08080819, 0x19082b2b08081908, - 0x19082b2b08190808, 0x19082b2b19080808, 0x1919080808080808, 0x191908080808082b, - 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, 0x1919080808191908, - 0x191908080819192b, 0x1919080808192b19, 0x19190808082b0808, 0x19190808082b082b, - 0x19190808082b1919, 0x19190808082b2b08, 0x1919080819080819, 0x1919080819081908, - 0x191908081908192b, 0x1919080819082b19, 0x1919080819190808, 0x191908081919082b, - 0x1919080819191919, 0x1919080819192b08, 0x19190808192b0819, 0x19190808192b1908, - 0x191908082b080808, 0x191908082b08082b, 0x191908082b081919, 0x191908082b082b08, - 0x191908082b190819, 0x191908082b191908, 0x1919081908080819, 0x1919081908081908, - 0x191908190808192b, 0x1919081908082b19, 0x1919081908190808, 0x191908190819082b, - 0x1919081908191919, 0x1919081908192b08, 0x19190819082b0819, 0x19190819082b1908, - 0x1919081919080808, 0x191908191908082b, 0x1919081919081919, 0x1919081919082b08, - 0x1919081919190819, 0x1919081919191908, 0x19190819192b0808, 0x191908192b080819, - 0x191908192b081908, 0x191908192b190808, 0x1919082b08080808, 0x1919082b08081919, - 0x1919082b08082b08, 0x1919082b08190819, 0x1919082b08191908, 0x1919082b082b0808, - 0x1919082b19080819, 0x1919082b19081908, 0x1919082b19190808, 0x1919082b192b2b19, - 0x1919082b2b080808, 0x1919190808080819, 0x1919190808081908, 0x191919080808192b, - 0x1919190808082b19, 0x1919190808190808, 0x191919080819082b, 0x1919190808191919, - 0x1919190808192b08, 0x19191908082b0819, 0x19191908082b1908, 0x1919190819080808, - 0x191919081908082b, 0x1919190819081919, 0x1919190819082b08, 0x1919190819190819, - 0x1919190819191908, 0x19191908192b0808, 0x191919082b080819, 0x191919082b081908, - 0x191919082b190808, 0x1919191908080808, 0x191919190808082b, 0x1919191908081919, - 0x1919191908082b08, 0x1919191908190819, 0x1919191908191908, 0x19191919082b0808, - 0x1919191919080819, 0x1919191919081908, 0x1919191919190808, 0x191919192b080808, - 0x1919192b08080819, 0x1919192b08081908, 0x1919192b08190808, 0x1919192b082b192b, - 0x1919192b19080808, 0x19192b0808080808, 0x19192b080808082b, 0x19192b0808081919, - 0x19192b0808082b08, 0x19192b0808190819, 0x19192b0808191908, 0x19192b08082b0808, - 0x19192b0819080819, 0x19192b0819081908, 0x19192b0819190808, 0x19192b0819192b2b, - 0x19192b082b080808, 0x19192b1908080819, 0x19192b1908081908, 0x19192b1908190808, - 0x19192b1919080808, 0x19192b2b08080808, 0x19192b2b08192b19, 0x19192b2b2b081919, - 0x19192b2b2b2b2b08, 0x192b080808080819, 0x192b080808081908, 0x192b08080808192b, - 0x192b080808190808, 0x192b08080819082b, 0x192b080808191919, 0x192b080808192b08, - 0x192b0808082b0819, 0x192b0808082b1908, 0x192b080819080808, 0x192b080819081919, - 0x192b080819082b08, 0x192b080819190819, 0x192b080819191908, 0x192b0808192b0808, - 0x192b08082b081908, 0x192b08082b190808, 0x192b081908080808, 0x192b08190808082b, - 0x192b081908081919, 0x192b081908082b08, 0x192b081908190819, 0x192b081908191908, - 0x192b0819082b0808, 0x192b081919080819, 0x192b081919081908, 0x192b081919190808, - 0x192b08192b080808, 0x192b08192b192b19, 0x192b082b08081908, 0x192b082b08190808, - 0x192b082b19080808, 0x192b082b1919192b, 0x192b082b2b2b0819, 0x192b190808080808, - 0x192b190808081919, 0x192b190808082b08, 0x192b190808190819, 0x192b190808191908, - 0x192b1908082b0808, 0x192b190819080819, 0x192b190819081908, 0x192b190819190808, - 0x192b19082b080808, 0x192b191908080819, 0x192b191908081908, 0x192b191908190808, - 0x192b191919080808, 0x192b191919082b2b, 0x192b1919192b2b08, 0x192b19192b19082b, - 0x192b192b08080808, 0x192b192b2b191908, 0x192b2b0808080819, 0x192b2b0808081908, - 0x192b2b0808190808, 0x192b2b08192b1919, 0x192b2b082b192b08, 0x192b2b1908080808, - 0x192b2b19082b2b2b, 0x192b2b2b1908082b, 0x192b2b2b2b2b0819, 0x2b08080808080808, - 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819, - 0x2b08080808191908, 0x2b08080808192b19, 0x2b080808082b0808, 0x2b080808082b1919, - 0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808081919082b, - 0x2b08080819191919, 0x2b08080819192b08, 0x2b080808192b0819, 0x2b0808082b080808, - 0x2b0808082b081919, 0x2b0808082b190819, 0x2b0808082b191908, 0x2b08081908080819, - 0x2b08081908081908, 0x2b08081908082b19, 0x2b08081908190808, 0x2b0808190819082b, - 0x2b08081908191919, 0x2b08081908192b08, 0x2b080819082b0819, 0x2b080819082b1908, - 0x2b08081919080808, 0x2b0808191908082b, 0x2b08081919081919, 0x2b08081919082b08, - 0x2b08081919190819, 0x2b08081919191908, 0x2b0808192b080819, 0x2b0808192b081908, - 0x2b0808192b190808, 0x2b0808192b2b2b19, 0x2b08082b08080808, 0x2b08082b08081919, - 0x2b08082b08082b2b, 0x2b08082b08190819, 0x2b08082b08191908, 0x2b08082b19080819, - 0x2b08082b19081908, 0x2b08082b19190808, 0x2b08190808080819, 0x2b08190808081908, - 0x2b0819080808192b, 0x2b08190808082b19, 0x2b08190808190808, 0x2b0819080819082b, - 0x2b08190808191919, 0x2b08190808192b08, 0x2b081908082b0819, 0x2b08190819080808, - 0x2b0819081908082b, 0x2b08190819081919, 0x2b08190819082b08, 0x2b08190819190819, - 0x2b08190819191908, 0x2b081908192b0808, 0x2b0819082b080819, 0x2b0819082b081908, - 0x2b0819082b190808, 0x2b08191908080808, 0x2b0819190808082b, 0x2b08191908081919, - 0x2b08191908082b08, 0x2b08191908190819, 0x2b08191908191908, 0x2b081919082b0808, - 0x2b08191919080819, 0x2b08191919081908, 0x2b08191919190808, 0x2b0819192b080808, - 0x2b0819192b082b2b, 0x2b08192b08080819, 0x2b08192b08081908, 0x2b08192b08190808, - 0x2b08192b082b2b19, 0x2b08192b19080808, 0x2b082b0808080808, 0x2b082b0808081919, - 0x2b082b0808190819, 0x2b082b0808191908, 0x2b082b0819080819, 0x2b082b0819081908, - 0x2b082b0819190808, 0x2b082b082b2b082b, 0x2b082b1908080819, 0x2b082b1908081908, - 0x2b082b1919080808, 0x2b082b19192b1919, 0x2b082b2b082b082b, 0x2b082b2b19192b08, - 0x2b082b2b19192b2b, 0x2b082b2b2b08082b, 0x2b082b2b2b2b082b, 0x2b19080808080819, - 0x2b19080808081908, 0x2b19080808082b19, 0x2b19080808190808, 0x2b1908080819082b, - 0x2b19080808191919, 0x2b19080808192b08, 0x2b190808082b1908, 0x2b19080819080808, - 0x2b1908081908082b, 0x2b19080819081919, 0x2b19080819082b08, 0x2b19080819190819, - 0x2b19080819191908, 0x2b190808192b0808, 0x2b1908082b080819, 0x2b1908082b081908, - 0x2b1908082b190808, 0x2b19081908080808, 0x2b19081908081919, 0x2b19081908190819, - 0x2b19081908191908, 0x2b19081919080819, 0x2b19081919081908, 0x2b19081919190808, - 0x2b19081919192b2b, 0x2b19082b08080819, 0x2b19082b08081908, 0x2b19082b08190808, - 0x2b19082b19080808, 0x2b19082b2b2b192b, 0x2b19190808080808, 0x2b1919080808082b, - 0x2b19190808081919, 0x2b19190808082b08, 0x2b19190808190819, 0x2b19190808191908, - 0x2b191908082b0808, 0x2b19190819080819, 0x2b19190819081908, 0x2b19190819190808, - 0x2b1919082b080808, 0x2b1919082b19192b, 0x2b19191908080819, 0x2b19191908081908, - 0x2b19191908190808, 0x2b19191919080808, 0x2b1919192b192b08, 0x2b1919192b2b0819, - 0x2b19192b08080808, 0x2b19192b1908192b, 0x2b19192b192b1908, 0x2b192b0808080819, - 0x2b192b0808081908, 0x2b192b0808190808, 0x2b192b08082b192b, 0x2b192b0819080808, - 0x2b192b082b2b2b19, 0x2b192b1908080808, 0x2b192b1919082b19, 0x2b192b191919082b, - 0x2b192b2b2b190808, 0x2b2b080808080808, 0x2b2b080808081919, 0x2b2b080808082b2b, - 0x2b2b080808191908, 0x2b2b0808082b082b, 0x2b2b0808082b2b2b, 0x2b2b080819080819, - 0x2b2b080819081908, 0x2b2b080819190808, 0x2b2b08082b2b082b, 0x2b2b08082b2b2b2b, - 0x2b2b081919080808, 0x2b2b0819192b1919, 0x2b2b082b0808082b, 0x2b2b082b08082b2b, - 0x2b2b082b082b082b, 0x2b2b082b082b2b08, 0x2b2b082b082b2b2b, 0x2b2b082b2b08082b, - 0x2b2b082b2b082b08, 0x2b2b082b2b082b2b, 0x2b2b082b2b2b2b08, 0x2b2b190808080819, - 0x2b2b190808081908, 0x2b2b190808190808, 0x2b2b190819080808, 0x2b2b19082b082b19, - 0x2b2b19082b2b1908, 0x2b2b191908080808, 0x2b2b191908192b19, 0x2b2b192b19190819, - 0x2b2b2b0808082b2b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b082b, 0x2b2b2b1919191908, - 0x2b2b2b192b08192b, 0x2b2b2b2b08082b08, 0x2b2b2b2b08082b2b, 0x2b2b2b2b082b0808, - 0x2b2b2b2b082b082b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b2b082b08, 0x2b2b2b2b2b2b2b2b, -}; - -static const uint32_t iq3xxs_grid[256] = { - 0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, 0x04041404, 0x04041414, - 0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14, - 0x040c140c, 0x040c142c, 0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404, - 0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c, 0x04141c1c, 0x04141c3e, - 0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c, 0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c, - 0x041c3e04, 0x04240c1c, 0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c, - 0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04, 0x043e0c24, 0x043e0c34, - 0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c, 0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c, - 0x0c041c04, 0x0c041c14, 0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c, - 0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14, 0x0c14140c, 0x0c141c04, - 0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404, 0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c, - 0x0c24042c, 0x0c242c04, 0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414, - 0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404, 0x14041414, 0x14041434, - 0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c, 0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c, - 0x140c1c04, 0x140c341c, 0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e, - 0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c, 0x141c0c04, 0x141c0c24, - 0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c, 0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24, - 0x143e040c, 0x143e041c, 0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c, - 0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414, 0x1c0c1404, 0x1c0c1c0c, - 0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c, 0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14, - 0x1c1c0c0c, 0x1c1c1c1c, 0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414, - 0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404, 0x24040424, 0x24040c3e, - 0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e, 0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404, - 0x24143404, 0x24143434, 0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c, - 0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04, 0x2c040c14, 0x2c04240c, - 0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434, 0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14, - 0x2c1c0414, 0x2c1c2c1c, 0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c, - 0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434, 0x34043424, 0x340c140c, - 0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04, 0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14, - 0x34341c1c, 0x343e041c, 0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14, - 0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14, 0x3e1c0404, 0x3e1c0c2c, - 0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c, 0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04, -}; - -static const uint32_t iq3s_grid[512] = { - 0x01010101, 0x01010103, 0x01010105, 0x0101010b, 0x0101010f, 0x01010301, 0x01010303, 0x01010305, - 0x01010309, 0x0101030d, 0x01010501, 0x01010503, 0x0101050b, 0x01010707, 0x01010901, 0x01010905, - 0x0101090b, 0x0101090f, 0x01010b03, 0x01010b07, 0x01010d01, 0x01010d05, 0x01010f03, 0x01010f09, - 0x01010f0f, 0x01030101, 0x01030103, 0x01030105, 0x01030109, 0x01030301, 0x01030303, 0x0103030b, - 0x01030501, 0x01030507, 0x0103050f, 0x01030703, 0x0103070b, 0x01030909, 0x01030d03, 0x01030d0b, - 0x01030f05, 0x01050101, 0x01050103, 0x0105010b, 0x0105010f, 0x01050301, 0x01050307, 0x0105030d, - 0x01050503, 0x0105050b, 0x01050701, 0x01050709, 0x01050905, 0x0105090b, 0x0105090f, 0x01050b03, - 0x01050b07, 0x01050f01, 0x01050f07, 0x01070107, 0x01070303, 0x0107030b, 0x01070501, 0x01070505, - 0x01070703, 0x01070707, 0x0107070d, 0x01070909, 0x01070b01, 0x01070b05, 0x01070d0f, 0x01070f03, - 0x01070f0b, 0x01090101, 0x01090307, 0x0109030f, 0x01090503, 0x01090509, 0x01090705, 0x01090901, - 0x01090907, 0x01090b03, 0x01090f01, 0x010b0105, 0x010b0109, 0x010b0501, 0x010b0505, 0x010b050d, - 0x010b0707, 0x010b0903, 0x010b090b, 0x010b090f, 0x010b0d0d, 0x010b0f07, 0x010d010d, 0x010d0303, - 0x010d0307, 0x010d0703, 0x010d0b05, 0x010d0f03, 0x010f0101, 0x010f0105, 0x010f0109, 0x010f0501, - 0x010f0505, 0x010f050d, 0x010f0707, 0x010f0b01, 0x010f0b09, 0x03010101, 0x03010103, 0x03010105, - 0x03010109, 0x03010301, 0x03010303, 0x03010307, 0x0301030b, 0x0301030f, 0x03010501, 0x03010505, - 0x03010703, 0x03010709, 0x0301070d, 0x03010b09, 0x03010b0d, 0x03010d03, 0x03010f05, 0x03030101, - 0x03030103, 0x03030107, 0x0303010d, 0x03030301, 0x03030309, 0x03030503, 0x03030701, 0x03030707, - 0x03030903, 0x03030b01, 0x03030b05, 0x03030f01, 0x03030f0d, 0x03050101, 0x03050305, 0x0305030b, - 0x0305030f, 0x03050501, 0x03050509, 0x03050705, 0x03050901, 0x03050907, 0x03050b0b, 0x03050d01, - 0x03050f05, 0x03070103, 0x03070109, 0x0307010f, 0x03070301, 0x03070307, 0x03070503, 0x0307050f, - 0x03070701, 0x03070709, 0x03070903, 0x03070d05, 0x03070f01, 0x03090107, 0x0309010b, 0x03090305, - 0x03090309, 0x03090703, 0x03090707, 0x03090905, 0x0309090d, 0x03090b01, 0x03090b09, 0x030b0103, - 0x030b0301, 0x030b0307, 0x030b0503, 0x030b0701, 0x030b0705, 0x030b0b03, 0x030d0501, 0x030d0509, - 0x030d050f, 0x030d0909, 0x030d090d, 0x030f0103, 0x030f0107, 0x030f0301, 0x030f0305, 0x030f0503, - 0x030f070b, 0x030f0903, 0x030f0d05, 0x030f0f01, 0x05010101, 0x05010103, 0x05010107, 0x0501010b, - 0x0501010f, 0x05010301, 0x05010305, 0x05010309, 0x0501030d, 0x05010503, 0x05010507, 0x0501050f, - 0x05010701, 0x05010705, 0x05010903, 0x05010907, 0x0501090b, 0x05010b01, 0x05010b05, 0x05010d0f, - 0x05010f01, 0x05010f07, 0x05010f0b, 0x05030101, 0x05030105, 0x05030301, 0x05030307, 0x0503030f, - 0x05030505, 0x0503050b, 0x05030703, 0x05030709, 0x05030905, 0x05030b03, 0x05050103, 0x05050109, - 0x0505010f, 0x05050503, 0x05050507, 0x05050701, 0x0505070f, 0x05050903, 0x05050b07, 0x05050b0f, - 0x05050f03, 0x05050f09, 0x05070101, 0x05070105, 0x0507010b, 0x05070303, 0x05070505, 0x05070509, - 0x05070703, 0x05070707, 0x05070905, 0x05070b01, 0x05070d0d, 0x05090103, 0x0509010f, 0x05090501, - 0x05090507, 0x05090705, 0x0509070b, 0x05090903, 0x05090f05, 0x05090f0b, 0x050b0109, 0x050b0303, - 0x050b0505, 0x050b070f, 0x050b0901, 0x050b0b07, 0x050b0f01, 0x050d0101, 0x050d0105, 0x050d010f, - 0x050d0503, 0x050d0b0b, 0x050d0d03, 0x050f010b, 0x050f0303, 0x050f050d, 0x050f0701, 0x050f0907, - 0x050f0b01, 0x07010105, 0x07010303, 0x07010307, 0x0701030b, 0x0701030f, 0x07010505, 0x07010703, - 0x07010707, 0x0701070b, 0x07010905, 0x07010909, 0x0701090f, 0x07010b03, 0x07010d07, 0x07010f03, - 0x07030103, 0x07030107, 0x0703010b, 0x07030309, 0x07030503, 0x07030507, 0x07030901, 0x07030d01, - 0x07030f05, 0x07030f0d, 0x07050101, 0x07050305, 0x07050501, 0x07050705, 0x07050709, 0x07050b01, - 0x07070103, 0x07070301, 0x07070309, 0x07070503, 0x07070507, 0x0707050f, 0x07070701, 0x07070903, - 0x07070907, 0x0707090f, 0x07070b0b, 0x07070f07, 0x07090107, 0x07090303, 0x0709030d, 0x07090505, - 0x07090703, 0x07090b05, 0x07090d01, 0x07090d09, 0x070b0103, 0x070b0301, 0x070b0305, 0x070b050b, - 0x070b0705, 0x070b0909, 0x070b0b0d, 0x070b0f07, 0x070d030d, 0x070d0903, 0x070f0103, 0x070f0107, - 0x070f0501, 0x070f0505, 0x070f070b, 0x09010101, 0x09010109, 0x09010305, 0x09010501, 0x09010509, - 0x0901050f, 0x09010705, 0x09010903, 0x09010b01, 0x09010f01, 0x09030105, 0x0903010f, 0x09030303, - 0x09030307, 0x09030505, 0x09030701, 0x0903070b, 0x09030907, 0x09030b03, 0x09030b0b, 0x09050103, - 0x09050107, 0x09050301, 0x0905030b, 0x09050503, 0x09050707, 0x09050901, 0x09050b0f, 0x09050d05, - 0x09050f01, 0x09070109, 0x09070303, 0x09070307, 0x09070501, 0x09070505, 0x09070703, 0x0907070b, - 0x09090101, 0x09090105, 0x09090509, 0x0909070f, 0x09090901, 0x09090f03, 0x090b010b, 0x090b010f, - 0x090b0503, 0x090b0d05, 0x090d0307, 0x090d0709, 0x090d0d01, 0x090f0301, 0x090f030b, 0x090f0701, - 0x090f0907, 0x090f0b03, 0x0b010105, 0x0b010301, 0x0b010309, 0x0b010505, 0x0b010901, 0x0b010909, - 0x0b01090f, 0x0b010b05, 0x0b010d0d, 0x0b010f09, 0x0b030103, 0x0b030107, 0x0b03010b, 0x0b030305, - 0x0b030503, 0x0b030705, 0x0b030f05, 0x0b050101, 0x0b050303, 0x0b050507, 0x0b050701, 0x0b05070d, - 0x0b050b07, 0x0b070105, 0x0b07010f, 0x0b070301, 0x0b07050f, 0x0b070909, 0x0b070b03, 0x0b070d0b, - 0x0b070f07, 0x0b090103, 0x0b090109, 0x0b090501, 0x0b090705, 0x0b09090d, 0x0b0b0305, 0x0b0b050d, - 0x0b0b0b03, 0x0b0b0b07, 0x0b0d0905, 0x0b0f0105, 0x0b0f0109, 0x0b0f0505, 0x0d010303, 0x0d010307, - 0x0d01030b, 0x0d010703, 0x0d010707, 0x0d010d01, 0x0d030101, 0x0d030501, 0x0d03050f, 0x0d030d09, - 0x0d050305, 0x0d050709, 0x0d050905, 0x0d050b0b, 0x0d050d05, 0x0d050f01, 0x0d070101, 0x0d070309, - 0x0d070503, 0x0d070901, 0x0d09050b, 0x0d090907, 0x0d090d05, 0x0d0b0101, 0x0d0b0107, 0x0d0b0709, - 0x0d0b0d01, 0x0d0d010b, 0x0d0d0901, 0x0d0f0303, 0x0d0f0307, 0x0f010101, 0x0f010109, 0x0f01010f, - 0x0f010501, 0x0f010505, 0x0f01070d, 0x0f010901, 0x0f010b09, 0x0f010d05, 0x0f030105, 0x0f030303, - 0x0f030509, 0x0f030907, 0x0f03090b, 0x0f050103, 0x0f050109, 0x0f050301, 0x0f05030d, 0x0f050503, - 0x0f050701, 0x0f050b03, 0x0f070105, 0x0f070705, 0x0f07070b, 0x0f070b07, 0x0f090103, 0x0f09010b, - 0x0f090307, 0x0f090501, 0x0f090b01, 0x0f0b0505, 0x0f0b0905, 0x0f0d0105, 0x0f0d0703, 0x0f0f0101, -}; - -#define NGRID_IQ2XXS 512 -static const uint64_t iq1s_grid[NGRID_IQ2XXS] = { - 0xffffffffffff0101, 0xffffffffff01ff00, 0xffffffffff010100, 0xffffffff00000000, - 0xffffffff01ff00ff, 0xffffffff01ff0001, 0xffffffff0101ffff, 0xffffffff0101ff01, - 0xffffff00ff000000, 0xffffff000000ff00, 0xffffff00000000ff, 0xffffff0000000100, - 0xffffff0000010000, 0xffffff0001000000, 0xffffff01ffff00ff, 0xffffff01ff01ff00, - 0xffffff01ff010100, 0xffffff0100000001, 0xffffff0101ffff00, 0xffffff0101ff0101, - 0xffffff0101010100, 0xffff00ffff00ff01, 0xffff00ffff0000ff, 0xffff00ff00ff0100, - 0xffff00ff0100ff00, 0xffff00ff010001ff, 0xffff0000ff0101ff, 0xffff000000ffff00, - 0xffff000000000000, 0xffff00000001ff01, 0xffff000001000101, 0xffff0000010100ff, - 0xffff0001ffff0100, 0xffff00010000ff00, 0xffff000100010101, 0xffff000101000000, - 0xffff01ffffff0000, 0xffff01ffff01ffff, 0xffff01ffff010100, 0xffff01ff00000000, - 0xffff01ff01ffffff, 0xffff01ff01ff0001, 0xffff01ff0101ffff, 0xffff01ff01010001, - 0xffff0100ffffff01, 0xffff01000000ffff, 0xffff010000000100, 0xffff010001ff01ff, - 0xffff010001000000, 0xffff0101ff000000, 0xffff0101000101ff, 0xffff010101ffff01, - 0xffff01010101ff00, 0xff00ffffff000000, 0xff00ffff00ffff00, 0xff00ffff00000001, - 0xff00ffff000001ff, 0xff00ffff01010000, 0xff00ff00ffff0000, 0xff00ff00ff00ff00, - 0xff00ff00ff0000ff, 0xff00ff00ff000100, 0xff00ff00ff010001, 0xff00ff0000ff0001, - 0xff00ff000000ffff, 0xff00ff0000000000, 0xff00ff000001ff00, 0xff00ff0000010100, - 0xff00ff0001ff0000, 0xff00ff000100ff00, 0xff00ff0001000100, 0xff00ff01ff000000, - 0xff00ff0100ff0000, 0xff00ff01000001ff, 0xff00ff0101010001, 0xff0000ff00000000, - 0xff0000ff0001ff00, 0xff0000ff00010100, 0xff000000ffff0101, 0xff000000ff000000, - 0xff000000ff01ff00, 0xff00000000ff0000, 0xff0000000000ff00, 0xff000000000000ff, - 0xff00000000000000, 0xff00000000000001, 0xff00000000000100, 0xff0000000001ffff, - 0xff00000000010000, 0xff00000001000000, 0xff00000001010100, 0xff000001ff00ff01, - 0xff000001ff0100ff, 0xff00000100000000, 0xff0000010001ff00, 0xff00000101ff0100, - 0xff0000010100ff00, 0xff0001ff00ff00ff, 0xff0001ff00000101, 0xff0001ff000100ff, - 0xff0001ff01000000, 0xff000100ff0001ff, 0xff0001000000ff01, 0xff00010000000000, - 0xff00010000010001, 0xff00010000010100, 0xff00010001ffff00, 0xff00010001ff0101, - 0xff00010001010000, 0xff000101ffffffff, 0xff000101ff000101, 0xff00010101ff00ff, - 0xff00010101000001, 0xff000101010100ff, 0xff01ffffff000101, 0xff01ffffff01ffff, - 0xff01ffffff01ff01, 0xff01ffffff0101ff, 0xff01ffff00000000, 0xff01ffff01ff0001, - 0xff01ffff0101ff01, 0xff01ff00ff000000, 0xff01ff0000ff0100, 0xff01ff000000ff01, - 0xff01ff0000010000, 0xff01ff00010000ff, 0xff01ff01ff01ff00, 0xff01ff0100000101, - 0xff0100ffffff0000, 0xff0100ffff010000, 0xff0100ff01ff00ff, 0xff0100ff01000100, - 0xff0100ff010100ff, 0xff010000ffffff01, 0xff01000000000000, 0xff0100000101ff00, - 0xff010001ffff00ff, 0xff010001ff000100, 0xff01000100ffff00, 0xff01000100010001, - 0xff01000101ff0001, 0xff010001010001ff, 0xff0101ffffffffff, 0xff0101ffff01ffff, - 0xff0101ffff010101, 0xff0101ff0000ff00, 0xff0101ff01010001, 0xff010100ff000000, - 0xff010100ff01ff01, 0xff01010000ff0001, 0xff01010000000100, 0xff01010001000000, - 0xff0101010100ffff, 0x00ffffff0000ff01, 0x00ffffff000000ff, 0x00ffffff00000100, - 0x00ffffff00010000, 0x00ffff00ffff0001, 0x00ffff00ff0000ff, 0x00ffff00ff000100, - 0x00ffff0000000000, 0x00ffff0001000100, 0x00ffff0001010001, 0x00ffff01ff00ff01, - 0x00ffff0100ff0100, 0x00ffff010000ff00, 0x00ffff01000100ff, 0x00ffff0101ff00ff, - 0x00ffff010101ff00, 0x00ff00ffffffffff, 0x00ff00ffffff01ff, 0x00ff00ffff000101, - 0x00ff00ff00000000, 0x00ff00ff000101ff, 0x00ff00ff01010101, 0x00ff0000ff000000, - 0x00ff0000ff01ffff, 0x00ff000000ff0000, 0x00ff00000000ff00, 0x00ff0000000000ff, - 0x00ff000000000000, 0x00ff000000000001, 0x00ff000000000100, 0x00ff000000010000, - 0x00ff000001ffff01, 0x00ff000001000000, 0x00ff0001ff000101, 0x00ff000100ffffff, - 0x00ff000100000000, 0x00ff0001010001ff, 0x00ff01ffff000000, 0x00ff01ff0001ff00, - 0x00ff01ff01ff0100, 0x00ff0100ff01ff01, 0x00ff010000ff00ff, 0x00ff010000ff0101, - 0x00ff010000000000, 0x00ff010000010101, 0x00ff01000100ff00, 0x00ff010001010000, - 0x00ff0101ffffff00, 0x00ff01010000ff01, 0x00ff010100000100, 0x00ff010101ff0000, - 0x0000ffffffff0100, 0x0000ffffff00ff00, 0x0000ffffff0000ff, 0x0000ffffff010000, - 0x0000ffff00000000, 0x0000ffff00010101, 0x0000ffff01ffff01, 0x0000ffff01000100, - 0x0000ff00ff000000, 0x0000ff00ff01ff00, 0x0000ff00ff0101ff, 0x0000ff0000ff0000, - 0x0000ff000000ff00, 0x0000ff00000000ff, 0x0000ff0000000000, 0x0000ff0000000001, - 0x0000ff0000000100, 0x0000ff0000010000, 0x0000ff0001ffffff, 0x0000ff0001ff01ff, - 0x0000ff0001000000, 0x0000ff000101ffff, 0x0000ff01ffff0101, 0x0000ff01ff010000, - 0x0000ff0100000000, 0x0000ff0101000101, 0x000000ffffff0001, 0x000000ffff000000, - 0x000000ff00ff0000, 0x000000ff0000ff00, 0x000000ff000000ff, 0x000000ff00000000, - 0x000000ff00000001, 0x000000ff00000100, 0x000000ff00010000, 0x000000ff01000000, - 0x000000ff0101ff00, 0x00000000ffff0000, 0x00000000ff00ff00, 0x00000000ff0000ff, - 0x00000000ff000000, 0x00000000ff000001, 0x00000000ff000100, 0x00000000ff010000, - 0x0000000000ffff00, 0x0000000000ff00ff, 0x0000000000ff0000, 0x0000000000ff0001, - 0x0000000000ff0100, 0x000000000000ffff, 0x000000000000ff00, 0x000000000000ff01, - 0x00000000000000ff, 0x0000000000000001, 0x00000000000001ff, 0x0000000000000100, - 0x0000000000000101, 0x000000000001ff00, 0x00000000000100ff, 0x0000000000010000, - 0x0000000000010001, 0x0000000000010100, 0x0000000001ff0000, 0x000000000100ff00, - 0x00000000010000ff, 0x0000000001000000, 0x0000000001000001, 0x0000000001000100, - 0x0000000001010000, 0x00000001ffff01ff, 0x00000001ff000000, 0x0000000100ff0000, - 0x000000010000ff00, 0x00000001000000ff, 0x0000000100000000, 0x0000000100000001, - 0x0000000100000100, 0x0000000100010000, 0x0000000101000000, 0x000001ffff00ff00, - 0x000001ffff010001, 0x000001ffff0101ff, 0x000001ff00ffff01, 0x000001ff0000ffff, - 0x000001ff00000000, 0x000001ff010000ff, 0x000001ff01010100, 0x00000100ffff0100, - 0x00000100ff000000, 0x0000010000ff0000, 0x000001000000ff00, 0x00000100000000ff, - 0x0000010000000000, 0x0000010000000001, 0x0000010000000100, 0x0000010000010000, - 0x0000010001000000, 0x000001000101ff01, 0x00000101ffff0001, 0x00000101ff01ffff, - 0x0000010100000000, 0x0000010101010100, 0x0001ffffff000000, 0x0001ffff00ffffff, - 0x0001ffff00000100, 0x0001ffff0001ff00, 0x0001ffff01000000, 0x0001ff00ffffff00, - 0x0001ff00ffff01ff, 0x0001ff00ff010000, 0x0001ff0000000000, 0x0001ff0000010001, - 0x0001ff0001ff0000, 0x0001ff0001010100, 0x0001ff01ff0000ff, 0x0001ff01ff000001, - 0x0001ff0100ffffff, 0x0001ff010001ffff, 0x0001ff01000101ff, 0x0001ff010100ff01, - 0x000100ffff00ffff, 0x000100ffff00ff01, 0x000100ffff000100, 0x000100ff00000000, - 0x000100ff000101ff, 0x000100ff01ff0101, 0x000100ff0100ffff, 0x000100ff01010101, - 0x00010000ff000000, 0x00010000ff010100, 0x0001000000ff0000, 0x000100000000ff00, - 0x00010000000000ff, 0x0001000000000000, 0x0001000000000001, 0x0001000000000100, - 0x0001000000010000, 0x0001000001ffff01, 0x0001000001000000, 0x0001000100ff0101, - 0x0001000100000000, 0x00010001010100ff, 0x000101ffffff01ff, 0x000101ffffff0101, - 0x000101ff00010000, 0x000101ff01ff0000, 0x000101ff0100ff01, 0x00010100ffff0000, - 0x0001010000000000, 0x000101000001ffff, 0x0001010000010101, 0x00010100010001ff, - 0x00010101ff00ff00, 0x00010101ff010001, 0x0001010100ffffff, 0x0001010100ff01ff, - 0x00010101000101ff, 0x0001010101ff0000, 0x000101010100ff01, 0x0001010101000101, - 0x01ffffffffff0101, 0x01ffffffff01ffff, 0x01ffffffff01ff01, 0x01ffffffff0101ff, - 0x01ffffffff010101, 0x01ffffff00000000, 0x01ffffff01ff01ff, 0x01ffffff01000101, - 0x01ffffff0101ff01, 0x01ffffff010100ff, 0x01ffff000000ff00, 0x01ffff0000000001, - 0x01ffff00000001ff, 0x01ffff0000010000, 0x01ffff0001ff0000, 0x01ffff01ffffffff, - 0x01ffff01ffff01ff, 0x01ffff01ff000000, 0x01ffff01ff01ffff, 0x01ffff01ff0101ff, - 0x01ffff010100ffff, 0x01ff00ffffff0000, 0x01ff00ffff010000, 0x01ff00ff00ffff01, - 0x01ff0000ff0000ff, 0x01ff000000000000, 0x01ff00000001ff01, 0x01ff000001ffffff, - 0x01ff000001010100, 0x01ff0001ffffff01, 0x01ff0001ff010001, 0x01ff000101ff0100, - 0x01ff000101000001, 0x01ff0001010100ff, 0x01ff01ffff00ffff, 0x01ff01ff00010001, - 0x01ff01ff01000000, 0x01ff01ff010101ff, 0x01ff0100ff000001, 0x01ff010000ffff00, - 0x01ff010000000100, 0x01ff010001ff01ff, 0x01ff01000101ffff, 0x01ff0101ffff00ff, - 0x01ff0101ffff0101, 0x01ff0101ff0101ff, 0x01ff010100010000, 0x0100ffff00ff00ff, - 0x0100ffff00ff0001, 0x0100ffff00000100, 0x0100ffff0100ff00, 0x0100ff00ffff0000, - 0x0100ff00ff00ffff, 0x0100ff00ff00ff01, 0x0100ff00ff000100, 0x0100ff00ff010000, - 0x0100ff0000000000, 0x0100ff00000100ff, 0x0100ff0001ff0101, 0x0100ff0001010101, - 0x0100ff0100ff00ff, 0x0100ff0100ff0001, 0x0100ff0100000100, 0x0100ff0100010001, - 0x0100ff0101000000, 0x010000ffff00ff00, 0x010000ff0000ffff, 0x010000ff00000000, - 0x010000ff010001ff, 0x010000ff01010001, 0x01000000ffffff00, 0x01000000ffff0101, - 0x01000000ff000000, 0x01000000ff0100ff, 0x01000000ff010101, 0x0100000000ff0000, - 0x010000000000ff00, 0x01000000000000ff, 0x0100000000000000, 0x0100000000000001, - 0x0100000000000100, 0x0100000000010000, 0x0100000001000000, 0x0100000100000000, - 0x01000001000101ff, 0x0100000101ffff01, 0x010001ffff000101, 0x010001ff00ff0100, - 0x010001ff0000ff00, 0x010001ff000100ff, 0x010001ff01ffffff, 0x01000100ffff0000, - 0x01000100ff0001ff, 0x0100010000000000, 0x010001000001ff00, 0x0100010001ff0000, - 0x01000100010000ff, 0x0100010001000101, 0x01000101ff00ff01, 0x0100010100ff0100, - 0x010001010000ffff, 0x0100010101010001, 0x0101ffffffff0101, 0x0101ffffff0001ff, - 0x0101ffffff01ffff, 0x0101ffffff010101, 0x0101ffff00000000, 0x0101ffff0101ffff, - 0x0101ffff010101ff, 0x0101ff00ff000000, 0x0101ff0000ff0100, 0x0101ff000000ff00, - 0x0101ff0000010000, 0x0101ff00010000ff, 0x0101ff0001000001, 0x0101ff01ff010101, - 0x0101ff0100000000, 0x0101ff010101ff00, 0x010100ffffff0000, 0x010100ffff010000, - 0x010100ff00ff01ff, 0x010100ff000000ff, 0x010100ff00000101, 0x010100ff01ffff00, - 0x01010000ffffff01, 0x01010000ff000100, 0x01010000ff01ff01, 0x0101000000000000, - 0x01010000000100ff, 0x010100000101ff01, 0x01010001ffff0000, 0x01010001ff00ffff, - 0x01010001ff010000, 0x0101000101ffffff, 0x0101000101ff01ff, 0x0101000101010101, - 0x010101ffff01ffff, 0x010101ff00000000, 0x010101ff0001ff01, 0x010101ff0101ffff, - 0x010101ff010101ff, 0x01010100ffffffff, 0x01010100ff000001, 0x010101000000ff00, - 0x0101010001010000, 0x0101010100ff0001, 0x010101010001ff01, 0x010101010101ffff, - -}; - -static const uint8_t ksigns_iq2xs[128] = { - 0, 129, 130, 3, 132, 5, 6, 135, 136, 9, 10, 139, 12, 141, 142, 15, - 144, 17, 18, 147, 20, 149, 150, 23, 24, 153, 154, 27, 156, 29, 30, 159, - 160, 33, 34, 163, 36, 165, 166, 39, 40, 169, 170, 43, 172, 45, 46, 175, - 48, 177, 178, 51, 180, 53, 54, 183, 184, 57, 58, 187, 60, 189, 190, 63, - 192, 65, 66, 195, 68, 197, 198, 71, 72, 201, 202, 75, 204, 77, 78, 207, - 80, 209, 210, 83, 212, 85, 86, 215, 216, 89, 90, 219, 92, 221, 222, 95, - 96, 225, 226, 99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111, - 240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255, -}; +size_t quantize_q8_0(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { + (void)quant_weights; // not used + const size_t row_size = ggml_row_size(GGML_TYPE_Q8_0, n_per_row); + quantize_row_q8_0_reference(src, dst, nrow*n_per_row); + return nrow * row_size; +} -static const uint8_t kmask_iq2xs[8] = {1, 2, 4, 8, 16, 32, 64, 128}; +// ====================== "True" 2-bit (de)-quantization void dequantize_row_iq2_xxs(const block_iq2_xxs * restrict x, float * restrict y, int k) { assert(k % QK_K == 0); @@ -4198,39 +3453,23 @@ void dequantize_row_iq1_s(const block_iq1_s * restrict x, float * restrict y, in assert(k % QK_K == 0); const int nb = k / QK_K; - float db[4]; - uint16_t idx[4]; - //const int8_t * grid[4]; - for (int i = 0; i < nb; i++) { const float d = GGML_FP16_TO_FP32(x[i].d); - const uint8_t * sc = x[i].scales; - const uint8_t * qs = x[i].qs; + const uint8_t * qs = x[i].qs; + const uint16_t * qh = x[i].qh; - for (int i8 = 0; i8 < QK_K/8; i8 += 4) { - idx[0] = qs[0] | ((sc[0] & 0x08) << 5); - idx[1] = qs[1] | ((sc[0] & 0x80) << 1); - idx[2] = qs[2] | ((sc[1] & 0x08) << 5); - idx[3] = qs[3] | ((sc[1] & 0x80) << 1); - //grid[0] = (const int8_t *)(iq1s_grid + (qs[0] | ((sc[0] & 0x08) << 5))); - //grid[1] = (const int8_t *)(iq1s_grid + (qs[1] | ((sc[0] & 0x80) << 1))); - //grid[2] = (const int8_t *)(iq1s_grid + (qs[2] | ((sc[1] & 0x08) << 5))); - //grid[3] = (const int8_t *)(iq1s_grid + (qs[3] | ((sc[1] & 0x80) << 1))); - db[0] = d * (2*(sc[0] & 7) + 1); - db[1] = d * (2*((sc[0] >> 4) & 7) + 1); - db[2] = d * (2*(sc[1] & 7) + 1); - db[3] = d * (2*((sc[1] >> 4) & 7) + 1); + for (int ib = 0; ib < QK_K/32; ++ib) { + const float dl = d * (2*((qh[ib] >> 12) & 7) + 1); + const float delta = qh[ib] & 0x8000 ? -IQ1S_DELTA : IQ1S_DELTA; for (int l = 0; l < 4; ++l) { - const int8_t * grid = (const int8_t *)(iq1s_grid + idx[l]); + const int8_t * grid = (const int8_t *)(iq1s_grid + (qs[l] | (((qh[ib] >> 3*l) & 7) << 8))); for (int j = 0; j < 8; ++j) { - //y[j] = db[l] * grid[l][j]; - y[j] = db[l] * grid[j]; + y[j] = dl * (grid[j] + delta); } y += 8; } qs += 4; - sc += 2; } } } @@ -4784,10 +4023,10 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r const block_q8_1 * restrict b_y0 = &vy0[i]; const block_q8_1 * restrict b_y1 = &vy1[i]; - float32x4_t summs_t = {GGML_FP16_TO_FP32(b_x0->m) * b_y0->s, - GGML_FP16_TO_FP32(b_x1->m) * b_y0->s, - GGML_FP16_TO_FP32(b_x0->m) * b_y1->s, - GGML_FP16_TO_FP32(b_x1->m) * b_y1->s}; + float32x4_t summs_t = {GGML_FP16_TO_FP32(b_x0->m) * GGML_FP16_TO_FP32(b_y0->s), + GGML_FP16_TO_FP32(b_x1->m) * GGML_FP16_TO_FP32(b_y0->s), + GGML_FP16_TO_FP32(b_x0->m) * GGML_FP16_TO_FP32(b_y1->s), + GGML_FP16_TO_FP32(b_x1->m) * GGML_FP16_TO_FP32(b_y1->s)}; summs0 += summs_t; const uint8x16_t m4b = vdupq_n_u8(0x0F); @@ -4808,10 +4047,10 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r const int8x16_t y1_h = vld1q_s8(b_y1->qs + 16); // mmla into int32x4_t - float32x4_t scale = {GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y0->d), - GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y1->d), - GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y0->d), - GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y1->d)}; + float32x4_t scale = {GGML_FP16_TO_FP32(b_x0->d)*b_y0->d, + GGML_FP16_TO_FP32(b_x0->d)*b_y1->d, + GGML_FP16_TO_FP32(b_x1->d)*b_y0->d, + GGML_FP16_TO_FP32(b_x1->d)*b_y1->d}; int8x16_t l0 = vreinterpretq_s8_s64(vzip1q_s64(vreinterpretq_s64_s8(x0_l), vreinterpretq_s64_s8(x1_l))); int8x16_t l1 = vreinterpretq_s8_s64(vzip2q_s64(vreinterpretq_s64_s8(x0_l), vreinterpretq_s64_s8(x1_l))); @@ -4852,7 +4091,7 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r const block_q8_1 * restrict y0 = &y[i + 0]; const block_q8_1 * restrict y1 = &y[i + 1]; - summs += GGML_FP16_TO_FP32(x0->m) * y0->s + GGML_FP16_TO_FP32(x1->m) * y1->s; + summs += GGML_FP16_TO_FP32(x0->m) * GGML_FP16_TO_FP32(y0->s) + GGML_FP16_TO_FP32(x1->m) * GGML_FP16_TO_FP32(y1->s); const uint8x16_t m4b = vdupq_n_u8(0x0F); @@ -4875,8 +4114,8 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r const int32x4_t p_0 = ggml_vdotq_s32(ggml_vdotq_s32(vdupq_n_s32(0), v0_0l, v1_0l), v0_0h, v1_0h); const int32x4_t p_1 = ggml_vdotq_s32(ggml_vdotq_s32(vdupq_n_s32(0), v0_1l, v1_1l), v0_1h, v1_1h); - sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(p_0), GGML_FP16_TO_FP32(x0->d)*y0->d); - sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(p_1), GGML_FP16_TO_FP32(x1->d)*y1->d); + sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(p_0), GGML_FP16_TO_FP32(x0->d)*GGML_FP16_TO_FP32(y0->d)); + sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(p_1), GGML_FP16_TO_FP32(x1->d)*GGML_FP16_TO_FP32(y1->d)); } *s = vaddvq_f32(sumv0) + vaddvq_f32(sumv1) + summs; @@ -4889,9 +4128,9 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r // Main loop for (int i = 0; i < nb; ++i) { const float d0 = GGML_FP16_TO_FP32(x[i].d); - const float d1 = y[i].d; + const float d1 = GGML_FP16_TO_FP32(y[i].d); - summs += GGML_FP16_TO_FP32(x[i].m) * y[i].s; + summs += GGML_FP16_TO_FP32(x[i].m) * GGML_FP16_TO_FP32(y[i].s); const __m256 d0v = _mm256_set1_ps( d0 ); const __m256 d1v = _mm256_set1_ps( d1 ); @@ -4943,7 +4182,7 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r int sumi = __riscv_vmv_x_s_i32m1_i32(vs2); - sumf += (GGML_FP16_TO_FP32(x[i].d)*y[i].d)*sumi + GGML_FP16_TO_FP32(x[i].m)*y[i].s; + sumf += (GGML_FP16_TO_FP32(x[i].d)*GGML_FP16_TO_FP32(y[i].d))*sumi + GGML_FP16_TO_FP32(x[i].m)*GGML_FP16_TO_FP32(y[i].s); } *s = sumf; @@ -4961,7 +4200,7 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r sumi += (v0 * y[i].qs[j]) + (v1 * y[i].qs[j + qk/2]); } - sumf += (GGML_FP16_TO_FP32(x[i].d)*y[i].d)*sumi + GGML_FP16_TO_FP32(x[i].m)*y[i].s; + sumf += (GGML_FP16_TO_FP32(x[i].d)*GGML_FP16_TO_FP32(y[i].d))*sumi + GGML_FP16_TO_FP32(x[i].m)*GGML_FP16_TO_FP32(y[i].s); } *s = sumf; @@ -5297,8 +4536,8 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r const uint8x16_t m4b = vdupq_n_u8(0x0F); - summs0 += GGML_FP16_TO_FP32(x0->m) * y0->s; - summs1 += GGML_FP16_TO_FP32(x1->m) * y1->s; + summs0 += GGML_FP16_TO_FP32(x0->m) * GGML_FP16_TO_FP32(y0->s); + summs1 += GGML_FP16_TO_FP32(x1->m) * GGML_FP16_TO_FP32(y1->s); // extract the 5th bit via lookup table ((b) << 4) memcpy(&qh0, x0->qh, sizeof(qh0)); @@ -5342,10 +4581,10 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(vaddq_s32( ggml_vdotq_s32(vdupq_n_s32(0), v0_0lf, v1_0l), - ggml_vdotq_s32(vdupq_n_s32(0), v0_0hf, v1_0h))), GGML_FP16_TO_FP32(x0->d)*y0->d); + ggml_vdotq_s32(vdupq_n_s32(0), v0_0hf, v1_0h))), GGML_FP16_TO_FP32(x0->d)*GGML_FP16_TO_FP32(y0->d)); sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(vaddq_s32( ggml_vdotq_s32(vdupq_n_s32(0), v0_1lf, v1_1l), - ggml_vdotq_s32(vdupq_n_s32(0), v0_1hf, v1_1h))), GGML_FP16_TO_FP32(x1->d)*y1->d); + ggml_vdotq_s32(vdupq_n_s32(0), v0_1hf, v1_1h))), GGML_FP16_TO_FP32(x1->d)*GGML_FP16_TO_FP32(y1->d)); } *s = vaddvq_f32(sumv0) + vaddvq_f32(sumv1) + summs0 + summs1; @@ -5362,7 +4601,7 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r const block_q5_1 * restrict x0 = &x[i]; const block_q8_1 * restrict y0 = &y[i]; - summs += GGML_FP16_TO_FP32(x0->m) * y0->s; + summs += GGML_FP16_TO_FP32(x0->m) * GGML_FP16_TO_FP32(y0->s); const v128_t m4b = wasm_i8x16_splat(0x0F); @@ -5409,7 +4648,7 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r wasm_i32x4_dot_i16x8(v0lfh, v1lh)), wasm_i32x4_add(wasm_i32x4_dot_i16x8(v0hfl, v1hl), wasm_i32x4_dot_i16x8(v0hfh, v1hh)))), - wasm_f32x4_splat(GGML_FP16_TO_FP32(x0->d) * y0->d))); + wasm_f32x4_splat(GGML_FP16_TO_FP32(x0->d) * GGML_FP16_TO_FP32(y0->d)))); } *s = wasm_f32x4_extract_lane(sumv, 0) + wasm_f32x4_extract_lane(sumv, 1) + @@ -5424,14 +4663,14 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r for (int i = 0; i < nb; i++) { const __m256 dx = _mm256_set1_ps(GGML_FP16_TO_FP32(x[i].d)); - summs += GGML_FP16_TO_FP32(x[i].m) * y[i].s; + summs += GGML_FP16_TO_FP32(x[i].m) * GGML_FP16_TO_FP32(y[i].s); __m256i qx = bytes_from_nibbles_32(x[i].qs); __m256i bxhi = bytes_from_bits_32(x[i].qh); bxhi = _mm256_and_si256(bxhi, _mm256_set1_epi8(0x10)); qx = _mm256_or_si256(qx, bxhi); - const __m256 dy = _mm256_set1_ps(y[i].d); + const __m256 dy = _mm256_set1_ps(GGML_FP16_TO_FP32(y[i].d)); const __m256i qy = _mm256_loadu_si256((const __m256i *)y[i].qs); const __m256 q = mul_sum_us8_pairs_float(qx, qy); @@ -5451,7 +4690,7 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r for (int i = 0; i < nb; i++) { const __m256 dx = _mm256_set1_ps(GGML_FP16_TO_FP32(x[i].d)); - summs += GGML_FP16_TO_FP32(x[i].m) * y[i].s; + summs += GGML_FP16_TO_FP32(x[i].m) * GGML_FP16_TO_FP32(y[i].s); __m256i bx_0 = bytes_from_nibbles_32(x[i].qs); const __m256i bxhi = bytes_from_bits_32(x[i].qh); @@ -5465,7 +4704,7 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r bxh = _mm_or_si128(bxh, bxhih); bx_0 = MM256_SET_M128I(bxh, bxl); - const __m256 dy = _mm256_set1_ps(y[i].d); + const __m256 dy = _mm256_set1_ps(GGML_FP16_TO_FP32(y[i].d)); const __m256i by_0 = _mm256_loadu_si256((const __m256i *)y[i].qs); const __m256 q = mul_sum_us8_pairs_float(bx_0, by_0); @@ -5532,7 +4771,7 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r int sumi = __riscv_vmv_x_s_i32m1_i32(vs2); - sumf += (GGML_FP16_TO_FP32(x[i].d)*y[i].d)*sumi + GGML_FP16_TO_FP32(x[i].m)*y[i].s; + sumf += (GGML_FP16_TO_FP32(x[i].d)*GGML_FP16_TO_FP32(y[i].d))*sumi + GGML_FP16_TO_FP32(x[i].m)*GGML_FP16_TO_FP32(y[i].s); } *s = sumf; @@ -5556,7 +4795,7 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r sumi += (x0 * y[i].qs[j]) + (x1 * y[i].qs[j + qk/2]); } - sumf += (GGML_FP16_TO_FP32(x[i].d)*y[i].d)*sumi + GGML_FP16_TO_FP32(x[i].m)*y[i].s; + sumf += (GGML_FP16_TO_FP32(x[i].d)*GGML_FP16_TO_FP32(y[i].d))*sumi + GGML_FP16_TO_FP32(x[i].m)*GGML_FP16_TO_FP32(y[i].s); } *s = sumf; @@ -9790,7 +9029,7 @@ void ggml_vec_dot_iq2_s_q8_K(int n, float * restrict s, size_t bs, const void * vld1_s8((const int8_t *)(iq2s_grid + (qs[7] | ((qh[ib32+1] << 2) & 0x300))))); qs += 8; - vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[0] | (signs[1] << 16))); + vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[0] | ((uint32_t) signs[1] << 16))); vs.val[1] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[1]), mask2); vs.val[0] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[0]), mask2); vs.val[0] = vceqq_u8(vs.val[0], mask2); @@ -9799,7 +9038,7 @@ void ggml_vec_dot_iq2_s_q8_K(int n, float * restrict s, size_t bs, const void * q2s.val[0] = vmulq_s8(vreinterpretq_s8_u8(vorrq_u8(vs.val[0], m1)), q2s.val[0]); q2s.val[1] = vmulq_s8(vreinterpretq_s8_u8(vorrq_u8(vs.val[1], m1)), q2s.val[1]); - vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[2] | (signs[3] << 16))); + vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[2] | ((uint32_t) signs[3] << 16))); vs.val[1] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[1]), mask2); vs.val[0] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[0]), mask2); vs.val[0] = vceqq_u8(vs.val[0], mask2); @@ -9870,12 +9109,12 @@ void ggml_vec_dot_iq2_s_q8_K(int n, float * restrict s, size_t bs, const void * iq2s_grid[qs[4] | ((qh[ib32+1] << 8) & 0x300)]); qs += 8; - __m256i aux256 = _mm256_set1_epi32(signs[0] | (signs[1] << 16)); + __m256i aux256 = _mm256_set1_epi32(signs[0] | ((uint32_t) signs[1] << 16)); aux256 = _mm256_and_si256(_mm256_shuffle_epi8(aux256,mask1), mask2); const __m256i s2_1 = _mm256_cmpeq_epi8(aux256, mask2); const __m256i q8s_1 = _mm256_sub_epi8(_mm256_xor_si256(s2_1, q8_1), s2_1); - aux256 = _mm256_set1_epi32(signs[2] | (signs[3] << 16)); + aux256 = _mm256_set1_epi32(signs[2] | ((uint32_t) signs[3] << 16)); aux256 = _mm256_and_si256(_mm256_shuffle_epi8(aux256,mask1), mask2); const __m256i s2_2 = _mm256_cmpeq_epi8(aux256, mask2); const __m256i q8s_2 = _mm256_sub_epi8(_mm256_xor_si256(s2_2, q8_2), s2_2); @@ -10075,7 +9314,7 @@ void ggml_vec_dot_iq3_xxs_q8_K(int n, float * restrict s, size_t bs, const void #endif } -void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc) { +void ggml_vec_dot_iq3_s_q8_K (int n, float * restrict s, size_t bs, const void * restrict vx, size_t bx, const void * restrict vy, size_t by, int nrc) { assert(n % QK_K == 0); assert(nrc == 1); UNUSED(nrc); @@ -10140,18 +9379,18 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v const uint8x16_t idx_l = vld1q_u8(qs); qs += 16; idx.vec_index = vorrq_u16(vmovl_u8(vget_low_u8 (idx_l)), vandq_u16(vshlq_u16(vdupq_n_u16(qh[ib32+0]), hshift), m256)); - const uint32x4_t aux32x4_0 = {iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]], - iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]}; - const uint32x4_t aux32x4_1 = {iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]], - iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]}; + const uint32x4_t aux32x4_0 = ggml_vld1q_u32(iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]], + iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]); + const uint32x4_t aux32x4_1 = ggml_vld1q_u32(iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]], + iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]); idx.vec_index = vorrq_u16(vmovl_u8(vget_high_u8(idx_l)), vandq_u16(vshlq_u16(vdupq_n_u16(qh[ib32+1]), hshift), m256)); - const uint32x4_t aux32x4_2 = {iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]], - iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]}; - const uint32x4_t aux32x4_3 = {iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]], - iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]}; + const uint32x4_t aux32x4_2 = ggml_vld1q_u32(iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]], + iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]); + const uint32x4_t aux32x4_3 = ggml_vld1q_u32(iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]], + iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]); - vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[0] | (signs[1] << 16))); + vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[0] | ((uint32_t) signs[1] << 16))); vs.val[1] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[1]), mask2); vs.val[0] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[0]), mask2); vs.val[0] = vorrq_u8(vceqq_u8(vs.val[0], mask2), m1); @@ -10160,7 +9399,7 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v q3s.val[0] = vmulq_s8(vreinterpretq_s8_u8(vs.val[0]), vreinterpretq_s8_u32(aux32x4_0)); q3s.val[1] = vmulq_s8(vreinterpretq_s8_u8(vs.val[1]), vreinterpretq_s8_u32(aux32x4_1)); - vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[2] | (signs[3] << 16))); + vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[2] | ((uint32_t) signs[3] << 16))); vs.val[1] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[1]), mask2); vs.val[0] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[0]), mask2); vs.val[0] = vorrq_u8(vceqq_u8(vs.val[0], mask2), m1); @@ -10323,7 +9562,7 @@ static inline __m256i mul_add_epi8(const __m256i x, const __m256i y) { } #endif -void ggml_vec_dot_iq1_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc) { +void ggml_vec_dot_iq1_s_q8_K (int n, float * restrict s, size_t bs, const void * restrict vx, size_t bx, const void * restrict vy, size_t by, int nrc) { assert(n % QK_K == 0); assert(nrc == 1); UNUSED(nrc); @@ -10336,155 +9575,119 @@ void ggml_vec_dot_iq1_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const const int nb = n / QK_K; - // TODO: implement for QK_K = 64 -#if defined __ARM_NEON && QK_K == 256 - - const uint8x16_t m8 = vdupq_n_u8(0x08); - const uint8x16_t m7 = vdupq_n_u8(0x07); - const uint8x16_t m1 = vdupq_n_u8(0x01); - const int32x4_t vzero = vdupq_n_s32(0); +#if defined __ARM_NEON - uint16_t gindex[8]; - uint16x8x2_t vindex; - int8x16x4_t q1b; + ggml_int8x16x4_t q1b; ggml_int8x16x4_t q8b; - uint16x8x4_t scales; - int32x4x2_t sumi; - int32x4x2_t dotq; float sumf = 0; for (int i = 0; i < nb; ++i) { - const int8_t * q8 = y[i].qs; - const uint8_t * qs = x[i].qs; - const uint8_t * sc = x[i].scales; + const int8_t * q8 = y[i].qs; + const uint8_t * qs = x[i].qs; + const uint16_t * qh = x[i].qh; - sumi.val[0] = sumi.val[1] = vzero; + int sumi1 = 0, sumi2 = 0, sumi3 = 0; - for (int i128 = 0; i128 < QK_K/128; ++i128) { - const uint8x16_t ql = vld1q_u8(qs); qs += 16; - const uint8x8_t tm1 = vld1_u8 (sc); sc += 8; - const uint8x8_t tm2 = vshr_n_u8(tm1, 4); - const uint8x16_t qh = vcombine_u8(vzip1_u8(tm1, tm2), vzip2_u8(tm1, tm2)); - const uint8x16_t hbit = vandq_u8(qh, m8); - vindex.val[0] = vorrq_u16(vmovl_u8(vget_low_u8 (ql)), vshlq_n_u16(vmovl_u8(vget_low_u8 (hbit)), 5)); - vindex.val[1] = vorrq_u16(vmovl_u8(vget_high_u8(ql)), vshlq_n_u16(vmovl_u8(vget_high_u8(hbit)), 5)); - const uint8x16_t scales8 = vorrq_u8(vshlq_n_u8(vandq_u8(qh, m7), 1), m1); - scales.val[0] = vmovl_u8(vget_low_u8 (scales8)); - scales.val[1] = vmovl_u8(vget_high_u8 (scales8)); + for (int ib = 0; ib < QK_K/32; ib += 2) { - for (int l = 0; l < 2; ++l) { - vst1q_u16(gindex+0, vindex.val[l]); - q1b.val[0] = vcombine_s8(vld1_s8((const void *)(iq1s_grid+gindex[0])), vld1_s8((const void *)(iq1s_grid+gindex[1]))); - q1b.val[1] = vcombine_s8(vld1_s8((const void *)(iq1s_grid+gindex[2])), vld1_s8((const void *)(iq1s_grid+gindex[3]))); - q1b.val[2] = vcombine_s8(vld1_s8((const void *)(iq1s_grid+gindex[4])), vld1_s8((const void *)(iq1s_grid+gindex[5]))); - q1b.val[3] = vcombine_s8(vld1_s8((const void *)(iq1s_grid+gindex[6])), vld1_s8((const void *)(iq1s_grid+gindex[7]))); - q8b = ggml_vld1q_s8_x4(q8); q8 += 64; + q1b.val[0] = vcombine_s8(vld1_s8((const int8_t *)(iq1s_grid + (qs[0] | ((qh[ib+0] << 8) & 0x700)))), + vld1_s8((const int8_t *)(iq1s_grid + (qs[1] | ((qh[ib+0] << 5) & 0x700))))); + q1b.val[1] = vcombine_s8(vld1_s8((const int8_t *)(iq1s_grid + (qs[2] | ((qh[ib+0] << 2) & 0x700)))), + vld1_s8((const int8_t *)(iq1s_grid + (qs[3] | ((qh[ib+0] >> 1) & 0x700))))); + q1b.val[2] = vcombine_s8(vld1_s8((const int8_t *)(iq1s_grid + (qs[4] | ((qh[ib+1] << 8) & 0x700)))), + vld1_s8((const int8_t *)(iq1s_grid + (qs[5] | ((qh[ib+1] << 5) & 0x700))))); + q1b.val[3] = vcombine_s8(vld1_s8((const int8_t *)(iq1s_grid + (qs[6] | ((qh[ib+1] << 2) & 0x700)))), + vld1_s8((const int8_t *)(iq1s_grid + (qs[7] | ((qh[ib+1] >> 1) & 0x700))))); + qs += 8; - dotq.val[0] = vpaddq_s32(ggml_vdotq_s32(vzero, q1b.val[0], q8b.val[0]), ggml_vdotq_s32(vzero, q1b.val[1], q8b.val[1])); - dotq.val[1] = vpaddq_s32(ggml_vdotq_s32(vzero, q1b.val[2], q8b.val[2]), ggml_vdotq_s32(vzero, q1b.val[3], q8b.val[3])); + q8b = ggml_vld1q_s8_x4(q8); q8 += 64; + + const int32x4_t p1 = ggml_vdotq_s32(ggml_vdotq_s32(vdupq_n_s32(0), q1b.val[0], q8b.val[0]), q1b.val[1], q8b.val[1]); + const int32x4_t p2 = ggml_vdotq_s32(ggml_vdotq_s32(vdupq_n_s32(0), q1b.val[2], q8b.val[2]), q1b.val[3], q8b.val[3]); + + const int ls1 = 2*((qh[ib+0] >> 12) & 7) + 1; + const int ls2 = 2*((qh[ib+1] >> 12) & 7) + 1; + sumi1 += vaddvq_s32(p1) * ls1; + sumi2 += vaddvq_s32(p2) * ls2; + sumi3 += (y[i].bsums[2*ib+0] + y[i].bsums[2*ib+1]) * ls1 * (qh[ib+0] & 0x8000 ? -1 : 1) + + (y[i].bsums[2*ib+2] + y[i].bsums[2*ib+3]) * ls2 * (qh[ib+1] & 0x8000 ? -1 : 1); - sumi.val[0] = vmlaq_s32(sumi.val[0], dotq.val[0], vreinterpretq_s32_u32(vmovl_u16(vget_low_u16 (scales.val[l])))); - sumi.val[1] = vmlaq_s32(sumi.val[1], dotq.val[1], vreinterpretq_s32_u32(vmovl_u16(vget_high_u16(scales.val[l])))); - } } - sumf += y[i].d * GGML_FP16_TO_FP32(x[i].d) * vaddvq_s32(vaddq_s32(sumi.val[0], sumi.val[1])); + sumf += y[i].d * GGML_FP16_TO_FP32(x[i].d) * (sumi1 + sumi2 + IQ1S_DELTA * sumi3); } *s = sumf; - // TODO: implement for QK_K = 64 -#elif defined __AVX2__ && QK_K == 256 - - const __m128i m8 = _mm_set1_epi8(0x08); - const __m128i m7 = _mm_set1_epi8(0x07); - const __m128i m1 = _mm_set1_epi8(0x01); - const __m128i shuffle_h = _mm_set_epi8(15, 7, 14, 6, 13, 5, 12, 4, 11, 3, 10, 2, 9, 1, 8, 0); - const __m128i shuffle_s[4] = { - _mm_set_epi32(0x03030303, 0x02020202, 0x01010101, 0x00000000), - _mm_set_epi32(0x07070707, 0x06060606, 0x05050505, 0x04040404), - _mm_set_epi32(0x0b0b0b0b, 0x0a0a0a0a, 0x09090909, 0x08080808), - _mm_set_epi32(0x0f0f0f0f, 0x0e0e0e0e, 0x0d0d0d0d, 0x0c0c0c0c) - }; - - uint64_t aux64; - - typedef union m256i_uint16 { - __m256i reg; - uint16_t s[16]; - } m256i_uint16_t; - - m256i_uint16_t v_gindex; +#elif defined __AVX2__ __m256 accum = _mm256_setzero_ps(); + float accum1 = 0; for (int i = 0; i < nb; ++i) { - const int8_t * q8 = y[i].qs; - const uint8_t * qs = x[i].qs; - const uint8_t * sc = x[i].scales; + const int8_t * q8 = y[i].qs; + const uint8_t * qs = x[i].qs; + const uint16_t * qh = x[i].qh; __m256i sumi = _mm256_setzero_si256(); - for (int i128 = 0; i128 < QK_K/128; ++i128) { - const __m128i ql = _mm_loadu_si128((const __m128i*)qs); qs += 16; - memcpy(&aux64, sc, 8); sc += 8; - const __m128i qh = _mm_shuffle_epi8(_mm_set_epi64x(aux64 >> 4, aux64), shuffle_h); - const __m256i hbit = _mm256_cvtepu8_epi16(_mm_and_si128(qh, m8)); - v_gindex.reg = _mm256_or_si256(_mm256_cvtepu8_epi16(ql), _mm256_slli_epi16(hbit, 5)); - const __m128i scales = _mm_or_si128(_mm_slli_epi16(_mm_and_si128(qh, m7), 1), m1); + int sumi1 = 0; + for (int ib = 0; ib < QK_K/32; ib += 2) { + const __m256i q1b_1 = _mm256_set_epi64x(iq1s_grid[qs[3] | ((qh[ib+0] >> 1) & 0x700)], iq1s_grid[qs[2] | ((qh[ib+0] << 2) & 0x700)], + iq1s_grid[qs[1] | ((qh[ib+0] << 5) & 0x700)], iq1s_grid[qs[0] | ((qh[ib+0] << 8) & 0x700)]); + const __m256i q1b_2 = _mm256_set_epi64x(iq1s_grid[qs[7] | ((qh[ib+1] >> 1) & 0x700)], iq1s_grid[qs[6] | ((qh[ib+1] << 2) & 0x700)], + iq1s_grid[qs[5] | ((qh[ib+1] << 5) & 0x700)], iq1s_grid[qs[4] | ((qh[ib+1] << 8) & 0x700)]); + qs += 8; + const __m256i q8b_1 = _mm256_loadu_si256((const __m256i*)q8); q8 += 32; + const __m256i q8b_2 = _mm256_loadu_si256((const __m256i*)q8); q8 += 32; - for (int i32 = 0; i32 < 4; ++i32) { - const __m256i q8b = _mm256_loadu_si256((const __m256i*)q8); q8 += 32; - const __m256i q1b = _mm256_set_epi64x(iq1s_grid[v_gindex.s[4*i32+3]], iq1s_grid[v_gindex.s[4*i32+2]], - iq1s_grid[v_gindex.s[4*i32+1]], iq1s_grid[v_gindex.s[4*i32+0]]); - const __m256i dot = mul_add_epi8(q1b, q8b); - const __m256i s16 = _mm256_cvtepi8_epi16(_mm_shuffle_epi8(scales, shuffle_s[i32])); - const __m256i p = _mm256_madd_epi16(s16, dot); - sumi = _mm256_add_epi32(sumi, p); - } + const __m256i dot1 = mul_add_epi8(q1b_1, q8b_1); + const __m256i dot2 = mul_add_epi8(q1b_2, q8b_2); + const int16_t ls1 = 2*((qh[ib+0] >> 12) & 7) + 1; + const int16_t ls2 = 2*((qh[ib+1] >> 12) & 7) + 1; + const __m256i p1 = _mm256_madd_epi16(dot1, _mm256_set1_epi16(ls1)); + const __m256i p2 = _mm256_madd_epi16(dot2, _mm256_set1_epi16(ls2)); + sumi = _mm256_add_epi32(sumi, _mm256_add_epi32(p1, p2)); + sumi1 += (y[i].bsums[2*ib+0] + y[i].bsums[2*ib+1]) * (qh[ib+0] & 0x8000 ? -1 : 1) * ls1 + + (y[i].bsums[2*ib+2] + y[i].bsums[2*ib+3]) * (qh[ib+1] & 0x8000 ? -1 : 1) * ls2; } - accum = _mm256_fmadd_ps(_mm256_set1_ps(y[i].d * GGML_FP16_TO_FP32(x[i].d)), _mm256_cvtepi32_ps(sumi), accum); + const float d = y[i].d * GGML_FP16_TO_FP32(x[i].d); + accum = _mm256_fmadd_ps(_mm256_set1_ps(d), _mm256_cvtepi32_ps(sumi), accum); + accum1 += d * sumi1; } - *s = hsum_float_8(accum); + *s = hsum_float_8(accum) + IQ1S_DELTA * accum1; #else - int db[4]; - uint16_t idx[4]; - float sumf = 0; - for (int i = 0; i < nb; ++i) { + for (int i = 0; i < nb; i++) { - const int8_t * q8 = y[i].qs; - const uint8_t * qs = x[i].qs; - const uint8_t * sc = x[i].scales; + const int8_t * q8 = y[i].qs; + const uint8_t * qs = x[i].qs; + const uint16_t * qh = x[i].qh; - int sumi = 0; - for (int i32 = 0; i32 < QK_K/32; ++i32) { - idx[0] = qs[0] | ((sc[0] & 0x08) << 5); - idx[1] = qs[1] | ((sc[0] & 0x80) << 1); - idx[2] = qs[2] | ((sc[1] & 0x08) << 5); - idx[3] = qs[3] | ((sc[1] & 0x80) << 1); - db[0] = (2*(sc[0] & 7) + 1); - db[1] = (2*((sc[0] >> 4) & 7) + 1); - db[2] = (2*(sc[1] & 7) + 1); - db[3] = (2*((sc[1] >> 4) & 7) + 1); + int sumi = 0, sumi1 = 0; + for (int ib = 0; ib < QK_K/32; ++ib) { + const int ls = 2*((qh[ib] >> 12) & 7) + 1; + const int delta = qh[ib] & 0x8000 ? -1 : 1; + int lsum = 0; for (int l = 0; l < 4; ++l) { - const int8_t * grid = (const int8_t *)(iq1s_grid + idx[l]); - int suml = 0; - for (int j = 0; j < 8; ++j) suml += q8[j] * grid[j]; - sumi += db[l] * suml; + const int8_t * grid = (const int8_t *)(iq1s_grid + (qs[l] | (((qh[ib] >> 3*l) & 7) << 8))); + for (int j = 0; j < 8; ++j) { + lsum += q8[j] * grid[j]; + } q8 += 8; } + sumi += ls * lsum; + sumi1 += ls * delta * (y[i].bsums[2*ib+0] + y[i].bsums[2*ib+1]); qs += 4; - sc += 2; } - sumf += GGML_FP16_TO_FP32(x[i].d) * y[i].d * sumi; + sumf += GGML_FP16_TO_FP32(x[i].d) * y[i].d * (sumi + IQ1S_DELTA * sumi1); } *s = sumf; @@ -10745,7 +9948,7 @@ static inline int iq2_grid_size(enum ggml_type type) { GGML_ASSERT(type == GGML_TYPE_IQ2_XXS || type == GGML_TYPE_IQ2_XS || type == GGML_TYPE_IQ1_S || type == GGML_TYPE_IQ2_S); return type == GGML_TYPE_IQ2_XXS ? 256 : type == GGML_TYPE_IQ2_XS ? 512 : - type == GGML_TYPE_IQ1_S ? 512 : 1024; + type == GGML_TYPE_IQ1_S ? NGRID_IQ1S : 1024; } static int iq2_compare_func(const void * left, const void * right) { @@ -10812,39 +10015,135 @@ void iq2xs_init_impl(enum ggml_type type) { 40962, 40968, 40970, 40992, 41002, 41120, 41297, 41305, 41382, 41472, 41474, 41480, 41514, 41600, 41632, 42048, 42133, 42597, 42648, 43018, 43040, 43042, 43048, 43168, 43176, 43268, 43396, 43398, 43560, 43562, 43665, 43690, }; - static const uint16_t kgrid_1bit_512[512] = { - 10, 33, 41, 85, 132, 134, 160, 162, 277, 337, 340, 345, 357, 405, 516, 545, - 553, 598, 641, 650, 681, 1042, 1044, 1097, 1169, 1176, 1320, 1345, 1365, 1378, 1434, 1444, - 1545, 1617, 1642, 1685, 2053, 2080, 2089, 2133, 2176, 2182, 2208, 2214, 2306, 2384, 2393, 2440, - 2453, 2581, 2664, 2690, 2721, 4117, 4161, 4182, 4184, 4261, 4357, 4369, 4372, 4377, 4390, 4422, - 4432, 4437, 4449, 4457, 4485, 4497, 4505, 4629, 4677, 4696, 4774, 5205, 5217, 5225, 5386, 5397, - 5409, 5445, 5457, 5460, 5461, 5462, 5465, 5472, 5477, 5525, 5545, 5650, 5668, 5717, 5729, 5769, - 5777, 6212, 6234, 6244, 6293, 6424, 6482, 6485, 6502, 6505, 6529, 6538, 6565, 6656, 6682, 6788, - 6806, 6820, 8218, 8224, 8226, 8232, 8277, 8326, 8354, 8469, 8521, 8530, 8549, 8596, 8737, 8794, - 9221, 9253, 9348, 9369, 9380, 9474, 9557, 9633, 9732, 9753, 9793, 9830, 9862, 9880, 10240, 10272, - 10282, 10321, 10406, 10517, 10530, 10566, 10585, 10645, 10896, 16466, 16468, 16473, 16485, 16646, 16660, 16665, - 16725, 16793, 16806, 16914, 16969, 16977, 16996, 17028, 17057, 17408, 17416, 17434, 17493, 17512, 17578, 17685, - 17696, 17733, 17745, 17748, 17749, 17750, 17753, 17765, 17794, 17813, 17946, 17984, 18005, 18072, 18453, 18529, - 18569, 18722, 18756, 18762, 18773, 18794, 18833, 18853, 18945, 19026, 19033, 19077, 20489, 20497, 20500, 20517, - 20565, 20586, 20610, 20633, 20757, 20769, 20776, 20805, 20817, 20820, 20821, 20822, 20825, 20837, 20864, 20872, - 20885, 20896, 21002, 21029, 21077, 21146, 21510, 21525, 21573, 21585, 21588, 21589, 21590, 21593, 21605, 21653, - 21665, 21765, 21777, 21780, 21781, 21782, 21785, 21797, 21825, 21828, 21829, 21830, 21833, 21840, 21841, 21842, - 21844, 21846, 21848, 21849, 21850, 21857, 21860, 21861, 21862, 21865, 21893, 21905, 21908, 21909, 21910, 21913, - 21925, 22024, 22037, 22085, 22097, 22100, 22101, 22102, 22105, 22117, 22165, 22545, 22566, 22568, 22594, 22608, - 22613, 22676, 22697, 22793, 22805, 22853, 22865, 22868, 22869, 22870, 22873, 22885, 22933, 22946, 23046, 23072, - 23125, 23209, 24597, 24640, 24665, 24673, 24725, 24833, 24840, 24869, 24917, 24934, 24965, 25001, 25108, 25110, - 25152, 25184, 25192, 25234, 25616, 25618, 25625, 25685, 25704, 25738, 25744, 25770, 25877, 25897, 25925, 25937, - 25940, 25941, 25942, 25945, 25957, 25986, 26005, 26186, 26197, 26276, 26632, 26634, 26725, 26757, 26770, 26885, - 26965, 26976, 26986, 27032, 27153, 27174, 27200, 27208, 27240, 27269, 27282, 27290, 32778, 32800, 32802, 32808, - 32810, 32853, 32904, 32922, 32930, 32932, 33105, 33110, 33112, 33125, 33157, 33280, 33288, 33301, 33312, 33320, - 33424, 33797, 33829, 33858, 34068, 34133, 34146, 34176, 34217, 34306, 34342, 34441, 34454, 34468, 34832, 34918, - 34965, 34984, 35094, 35137, 35161, 35208, 35232, 35332, 35338, 35368, 35429, 36932, 36934, 36953, 37009, 37125, - 37136, 37138, 37145, 37157, 37205, 37220, 37258, 37290, 37444, 37446, 37465, 37478, 37525, 37905, 37968, 37973, - 38040, 38054, 38145, 38154, 38165, 38180, 38186, 38213, 38225, 38228, 38229, 38230, 38233, 38245, 38293, 38485, - 38504, 38530, 38938, 38985, 38993, 39012, 39040, 39173, 39192, 39253, 39265, 39301, 39316, 39322, 39442, 39497, - 39504, 39590, 40970, 40984, 40992, 41002, 41045, 41120, 41128, 41237, 41289, 41297, 41317, 41364, 41366, 41514, - 41557, 41633, 41989, 42021, 42056, 42068, 42074, 42113, 42242, 42265, 42274, 42325, 42340, 42402, 42501, 42512, - 42533, 42624, 42632, 42666, 43040, 43093, 43106, 43168, 43176, 43264, 43286, 43345, 43429, 43590, 43618, 43680, + static const uint16_t kgrid_1bit_2048[NGRID_IQ1S] = { + 0, 2, 5, 8, 10, 17, 21, 32, 34, 40, 42, 69, 81, 84, 86, 101, + 128, 130, 136, 138, 149, 160, 162, 168, 170, 260, 261, 273, 276, 278, 281, 282, + 293, 321, 326, 329, 338, 341, 346, 353, 356, 358, 360, 389, 401, 404, 406, 421, + 512, 514, 520, 522, 533, 544, 546, 552, 554, 581, 593, 601, 612, 617, 640, 642, + 648, 650, 657, 661, 665, 672, 674, 680, 682, 1041, 1044, 1046, 1061, 1089, 1097, 1109, + 1114, 1124, 1125, 1169, 1177, 1189, 1281, 1284, 1285, 1286, 1301, 1304, 1306, 1321, 1344, 1349, + 1354, 1360, 1361, 1364, 1365, 1366, 1369, 1376, 1378, 1381, 1384, 1386, 1409, 1425, 1429, 1432, + 1434, 1441, 1444, 1445, 1446, 1449, 1556, 1561, 1601, 1604, 1616, 1618, 1621, 1624, 1632, 1633, + 1638, 1641, 1669, 1681, 1684, 1689, 2048, 2050, 2056, 2058, 2069, 2080, 2082, 2088, 2090, 2117, + 2129, 2134, 2149, 2176, 2178, 2184, 2186, 2197, 2208, 2210, 2216, 2218, 2309, 2321, 2324, 2329, + 2340, 2341, 2369, 2384, 2385, 2389, 2401, 2404, 2409, 2449, 2452, 2454, 2457, 2469, 2560, 2562, + 2568, 2570, 2581, 2592, 2594, 2600, 2602, 2629, 2641, 2649, 2657, 2661, 2688, 2690, 2693, 2696, + 2698, 2709, 2720, 2722, 2728, 2730, 4112, 4113, 4116, 4121, 4132, 4133, 4161, 4164, 4176, 4181, + 4184, 4193, 4196, 4197, 4201, 4241, 4244, 4246, 4257, 4261, 4353, 4356, 4358, 4361, 4368, 4370, + 4373, 4376, 4385, 4388, 4393, 4421, 4426, 4432, 4433, 4434, 4436, 4437, 4438, 4441, 4448, 4453, + 4484, 4498, 4501, 4513, 4516, 4625, 4628, 4630, 4645, 4672, 4678, 4681, 4690, 4693, 4696, 4698, + 4708, 4710, 4741, 4753, 4756, 4758, 4773, 5121, 5126, 5129, 5140, 5141, 5144, 5145, 5153, 5158, + 5185, 5189, 5190, 5192, 5194, 5201, 5204, 5205, 5206, 5209, 5218, 5221, 5224, 5252, 5257, 5264, + 5268, 5269, 5272, 5273, 5274, 5281, 5284, 5285, 5289, 5378, 5381, 5386, 5393, 5396, 5397, 5398, + 5401, 5408, 5410, 5413, 5416, 5418, 5441, 5444, 5445, 5446, 5457, 5458, 5460, 5461, 5462, 5465, + 5466, 5473, 5476, 5477, 5478, 5481, 5504, 5506, 5508, 5509, 5512, 5514, 5520, 5521, 5524, 5525, + 5526, 5529, 5530, 5536, 5538, 5541, 5633, 5636, 5637, 5638, 5653, 5654, 5656, 5658, 5665, 5670, + 5696, 5698, 5700, 5701, 5704, 5706, 5713, 5717, 5718, 5720, 5721, 5729, 5732, 5733, 5736, 5737, + 5738, 5766, 5770, 5778, 5781, 5796, 5801, 6161, 6166, 6181, 6209, 6212, 6214, 6217, 6224, 6229, + 6232, 6234, 6240, 6241, 6244, 6246, 6249, 6277, 6289, 6292, 6309, 6416, 6418, 6421, 6426, 6433, + 6437, 6466, 6468, 6469, 6472, 6481, 6484, 6485, 6486, 6489, 6490, 6496, 6501, 6506, 6537, 6545, + 6546, 6549, 6552, 6561, 6566, 6569, 6665, 6678, 6692, 6694, 6724, 6726, 6729, 6736, 6738, 6741, + 6744, 6753, 6758, 6761, 6789, 6801, 6806, 6810, 8192, 8194, 8200, 8202, 8213, 8224, 8226, 8229, + 8232, 8234, 8261, 8273, 8281, 8289, 8293, 8320, 8322, 8328, 8330, 8341, 8352, 8354, 8357, 8360, + 8362, 8453, 8465, 8468, 8473, 8485, 8514, 8516, 8521, 8533, 8536, 8538, 8545, 8548, 8549, 8550, + 8581, 8592, 8598, 8601, 8613, 8705, 8712, 8714, 8721, 8725, 8736, 8738, 8744, 8746, 8773, 8785, + 8790, 8793, 8805, 8833, 8840, 8842, 8849, 8853, 8864, 8866, 8872, 8874, 9221, 9236, 9238, 9241, + 9253, 9284, 9285, 9286, 9289, 9298, 9301, 9304, 9306, 9318, 9349, 9361, 9364, 9369, 9377, 9381, + 9481, 9493, 9505, 9513, 9536, 9541, 9544, 9553, 9556, 9557, 9561, 9570, 9573, 9576, 9609, 9616, + 9620, 9621, 9624, 9626, 9633, 9636, 9638, 9641, 9733, 9744, 9746, 9753, 9765, 9793, 9801, 9813, + 9824, 9825, 9833, 9860, 9862, 9872, 9882, 10240, 10242, 10248, 10250, 10261, 10272, 10274, 10280, 10282, + 10309, 10321, 10324, 10341, 10368, 10370, 10376, 10378, 10400, 10402, 10408, 10410, 10505, 10513, 10516, 10521, + 10533, 10566, 10569, 10578, 10581, 10593, 10596, 10598, 10601, 10629, 10640, 10646, 10649, 10660, 10661, 10752, + 10754, 10760, 10762, 10784, 10786, 10792, 10794, 10821, 10833, 10838, 10841, 10853, 10880, 10882, 10888, 10890, + 10901, 10912, 10914, 10920, 10922, 16389, 16401, 16406, 16421, 16457, 16466, 16469, 16472, 16474, 16481, 16484, + 16486, 16532, 16537, 16545, 16550, 16640, 16641, 16644, 16646, 16649, 16658, 16661, 16662, 16664, 16666, 16673, + 16678, 16681, 16709, 16712, 16714, 16721, 16724, 16725, 16726, 16729, 16730, 16741, 16744, 16746, 16769, 16772, + 16774, 16784, 16786, 16789, 16800, 16801, 16802, 16901, 16913, 16916, 16918, 16933, 16961, 16978, 16981, 16986, + 16996, 17001, 17033, 17044, 17061, 17409, 17429, 17433, 17449, 17477, 17480, 17482, 17489, 17492, 17493, 17494, + 17505, 17506, 17509, 17512, 17514, 17537, 17542, 17545, 17552, 17554, 17557, 17568, 17569, 17577, 17665, 17666, + 17669, 17674, 17681, 17684, 17685, 17686, 17689, 17696, 17701, 17706, 17729, 17732, 17733, 17734, 17737, 17744, + 17745, 17748, 17749, 17750, 17752, 17753, 17761, 17764, 17765, 17766, 17769, 17794, 17796, 17797, 17800, 17809, + 17812, 17813, 17814, 17817, 17818, 17829, 17832, 17834, 17921, 17925, 17929, 17940, 17941, 17944, 17946, 17953, + 17956, 17961, 17984, 17986, 17989, 17992, 18000, 18001, 18002, 18005, 18006, 18009, 18018, 18021, 18024, 18049, + 18053, 18058, 18068, 18069, 18081, 18084, 18086, 18437, 18449, 18453, 18458, 18469, 18498, 18505, 18512, 18517, + 18520, 18529, 18532, 18534, 18537, 18565, 18577, 18580, 18582, 18585, 18597, 18689, 18693, 18694, 18698, 18704, + 18708, 18709, 18712, 18721, 18724, 18726, 18752, 18757, 18762, 18769, 18770, 18772, 18773, 18774, 18777, 18784, + 18786, 18789, 18790, 18794, 18822, 18825, 18834, 18837, 18838, 18840, 18849, 18852, 18854, 18857, 18966, 19012, + 19014, 19017, 19029, 19032, 19034, 19044, 19049, 19092, 19109, 20481, 20484, 20485, 20486, 20489, 20498, 20501, + 20506, 20513, 20516, 20521, 20544, 20549, 20552, 20561, 20564, 20565, 20566, 20569, 20581, 20584, 20614, 20617, + 20629, 20632, 20640, 20641, 20646, 20649, 20741, 20744, 20745, 20746, 20753, 20756, 20757, 20758, 20760, 20761, + 20768, 20773, 20774, 20776, 20778, 20801, 20804, 20805, 20806, 20809, 20816, 20817, 20818, 20820, 20821, 20822, + 20824, 20825, 20826, 20833, 20836, 20837, 20838, 20841, 20866, 20869, 20881, 20884, 20885, 20886, 20889, 20896, + 20901, 20906, 20993, 20998, 21010, 21013, 21018, 21025, 21028, 21058, 21061, 21066, 21073, 21076, 21077, 21078, + 21081, 21090, 21093, 21125, 21136, 21138, 21141, 21145, 21146, 21156, 21508, 21509, 21521, 21524, 21525, 21526, + 21528, 21529, 21537, 21541, 21544, 21546, 21569, 21572, 21573, 21574, 21577, 21578, 21584, 21585, 21588, 21589, + 21590, 21592, 21593, 21594, 21601, 21602, 21604, 21605, 21606, 21609, 21632, 21640, 21642, 21649, 21652, 21653, + 21654, 21657, 21665, 21668, 21669, 21674, 21761, 21762, 21764, 21765, 21766, 21769, 21776, 21777, 21778, 21780, + 21781, 21782, 21785, 21786, 21793, 21796, 21797, 21798, 21801, 21824, 21825, 21826, 21828, 21829, 21830, 21832, + 21833, 21840, 21841, 21842, 21844, 21845, 21846, 21848, 21849, 21850, 21856, 21857, 21860, 21861, 21862, 21864, + 21865, 21866, 21889, 21892, 21893, 21897, 21898, 21904, 21905, 21908, 21909, 21910, 21912, 21913, 21921, 21924, + 21925, 21926, 21929, 22016, 22017, 22018, 22020, 22022, 22024, 22025, 22033, 22036, 22037, 22040, 22041, 22048, + 22049, 22050, 22052, 22053, 22054, 22056, 22057, 22081, 22085, 22086, 22088, 22089, 22090, 22096, 22097, 22098, + 22100, 22101, 22102, 22104, 22105, 22106, 22113, 22116, 22117, 22121, 22146, 22149, 22150, 22152, 22153, 22154, + 22161, 22165, 22170, 22178, 22181, 22182, 22184, 22185, 22532, 22533, 22534, 22537, 22544, 22549, 22552, 22561, + 22570, 22597, 22600, 22602, 22609, 22612, 22613, 22614, 22616, 22617, 22624, 22626, 22628, 22629, 22658, 22665, + 22672, 22674, 22677, 22680, 22689, 22697, 22785, 22786, 22789, 22794, 22801, 22804, 22805, 22806, 22809, 22821, + 22849, 22852, 22853, 22854, 22857, 22864, 22865, 22866, 22868, 22869, 22870, 22872, 22873, 22874, 22881, 22884, + 22885, 22886, 22889, 22913, 22917, 22921, 22929, 22932, 22933, 22934, 22936, 22937, 22949, 23044, 23048, 23061, + 23066, 23072, 23077, 23078, 23081, 23109, 23112, 23113, 23121, 23125, 23126, 23128, 23129, 23138, 23141, 23144, + 23146, 23169, 23178, 23186, 23189, 23190, 23192, 23194, 23201, 24581, 24596, 24598, 24601, 24613, 24644, 24656, + 24661, 24662, 24664, 24666, 24673, 24676, 24678, 24681, 24705, 24726, 24741, 24833, 24836, 24838, 24841, 24850, + 24853, 24865, 24866, 24870, 24873, 24901, 24905, 24913, 24917, 24918, 24921, 24933, 24934, 24938, 24964, 24970, + 24978, 24981, 24993, 24998, 25001, 25105, 25110, 25113, 25152, 25153, 25158, 25173, 25174, 25176, 25184, 25221, + 25233, 25238, 25253, 25617, 25618, 25621, 25622, 25626, 25633, 25638, 25641, 25664, 25666, 25669, 25672, 25674, + 25681, 25684, 25685, 25686, 25689, 25690, 25696, 25698, 25701, 25732, 25733, 25737, 25744, 25746, 25748, 25749, + 25750, 25752, 25754, 25761, 25764, 25769, 25861, 25864, 25866, 25873, 25877, 25878, 25881, 25924, 25925, 25926, + 25929, 25936, 25937, 25940, 25941, 25942, 25945, 25953, 25956, 25957, 25958, 25961, 25990, 25993, 25994, 26001, + 26005, 26006, 26009, 26010, 26018, 26021, 26022, 26024, 26114, 26121, 26133, 26144, 26150, 26152, 26153, 26176, + 26181, 26184, 26186, 26193, 26196, 26197, 26198, 26200, 26202, 26208, 26213, 26216, 26240, 26242, 26245, 26250, + 26260, 26262, 26264, 26265, 26272, 26276, 26278, 26282, 26646, 26649, 26661, 26689, 26706, 26709, 26714, 26721, + 26729, 26757, 26769, 26776, 26790, 26881, 26884, 26896, 26901, 26913, 26916, 26918, 26921, 26944, 26945, 26949, + 26950, 26952, 26961, 26964, 26965, 26966, 26969, 26976, 26981, 26986, 27010, 27012, 27018, 27029, 27041, 27044, + 27045, 27049, 27153, 27158, 27160, 27201, 27204, 27209, 27216, 27221, 27224, 27226, 27236, 27237, 27241, 27270, + 27284, 27288, 27290, 27302, 32768, 32770, 32776, 32778, 32800, 32802, 32808, 32810, 32837, 32848, 32849, 32852, + 32854, 32857, 32869, 32896, 32898, 32904, 32906, 32917, 32928, 32930, 32936, 32938, 33029, 33041, 33044, 33046, + 33049, 33061, 33089, 33092, 33097, 33104, 33106, 33109, 33110, 33112, 33113, 33124, 33126, 33129, 33157, 33161, + 33172, 33174, 33177, 33189, 33280, 33282, 33288, 33290, 33301, 33312, 33314, 33320, 33322, 33361, 33364, 33369, + 33381, 33408, 33410, 33416, 33418, 33429, 33440, 33442, 33448, 33450, 33812, 33817, 33857, 33860, 33873, 33877, + 33882, 33889, 33892, 33897, 33940, 33945, 34049, 34057, 34066, 34069, 34074, 34086, 34089, 34112, 34113, 34117, + 34120, 34129, 34132, 34133, 34134, 34137, 34138, 34149, 34150, 34152, 34154, 34177, 34180, 34182, 34185, 34192, + 34194, 34197, 34200, 34214, 34321, 34326, 34329, 34341, 34369, 34372, 34377, 34378, 34384, 34389, 34393, 34394, + 34401, 34406, 34410, 34437, 34449, 34458, 34468, 34816, 34818, 34824, 34826, 34837, 34848, 34850, 34856, 34858, + 34881, 34885, 34897, 34900, 34905, 34917, 34921, 34944, 34946, 34952, 34954, 34965, 34976, 34978, 34984, 34986, + 35077, 35078, 35089, 35092, 35094, 35109, 35137, 35140, 35142, 35145, 35152, 35154, 35157, 35162, 35169, 35172, + 35205, 35222, 35225, 35237, 35328, 35330, 35336, 35338, 35349, 35360, 35362, 35368, 35370, 35397, 35409, 35412, + 35414, 35456, 35458, 35464, 35466, 35477, 35488, 35490, 35496, 35498, 36869, 36881, 36886, 36888, 36889, 36901, + 36929, 36934, 36937, 36949, 36952, 36954, 36969, 36970, 36997, 37009, 37012, 37014, 37017, 37029, 37121, 37124, + 37126, 37129, 37136, 37141, 37144, 37146, 37153, 37156, 37158, 37161, 37184, 37189, 37200, 37201, 37204, 37205, + 37206, 37209, 37218, 37221, 37252, 37254, 37266, 37269, 37272, 37281, 37284, 37286, 37289, 37381, 37393, 37396, + 37401, 37413, 37444, 37446, 37449, 37456, 37458, 37461, 37464, 37478, 37481, 37509, 37524, 37526, 37545, 37889, + 37892, 37894, 37904, 37909, 37912, 37926, 37952, 37962, 37969, 37972, 37973, 37974, 37976, 37977, 37984, 37985, + 37986, 37989, 38020, 38022, 38034, 38036, 38037, 38040, 38049, 38057, 38144, 38149, 38152, 38154, 38160, 38161, + 38164, 38165, 38166, 38169, 38177, 38181, 38185, 38186, 38209, 38212, 38213, 38214, 38217, 38224, 38225, 38226, + 38228, 38229, 38230, 38232, 38233, 38234, 38241, 38244, 38245, 38246, 38249, 38273, 38277, 38280, 38289, 38290, + 38292, 38293, 38294, 38297, 38298, 38304, 38306, 38309, 38312, 38314, 38401, 38404, 38416, 38421, 38425, 38432, + 38438, 38441, 38469, 38472, 38473, 38481, 38482, 38485, 38486, 38489, 38501, 38504, 38530, 38532, 38537, 38538, + 38546, 38548, 38549, 38564, 38566, 38569, 38917, 38934, 38937, 38949, 38977, 38982, 38992, 38994, 38997, 38998, + 39002, 39012, 39013, 39045, 39057, 39062, 39065, 39077, 39172, 39174, 39177, 39184, 39186, 39189, 39192, 39194, + 39200, 39201, 39204, 39206, 39232, 39234, 39237, 39240, 39242, 39249, 39252, 39253, 39254, 39257, 39266, 39269, + 39270, 39274, 39297, 39300, 39312, 39314, 39317, 39322, 39329, 39334, 39429, 39445, 39461, 39492, 39494, 39497, + 39504, 39509, 39512, 39521, 39557, 39569, 39572, 39573, 39574, 40960, 40962, 40968, 40970, 40981, 40992, 40994, + 41000, 41002, 41029, 41041, 41044, 41046, 41049, 41088, 41090, 41096, 41098, 41109, 41120, 41122, 41128, 41130, + 41221, 41225, 41233, 41236, 41238, 41241, 41242, 41286, 41289, 41297, 41301, 41304, 41306, 41313, 41316, 41349, + 41360, 41362, 41366, 41369, 41474, 41480, 41482, 41488, 41497, 41506, 41512, 41514, 41541, 41553, 41558, 41561, + 41573, 41600, 41602, 41608, 41610, 41621, 41632, 41634, 41640, 41642, 42009, 42021, 42049, 42052, 42064, 42068, + 42069, 42072, 42074, 42081, 42085, 42086, 42088, 42089, 42117, 42246, 42249, 42256, 42258, 42261, 42264, 42278, + 42281, 42306, 42309, 42321, 42324, 42325, 42326, 42329, 42341, 42346, 42369, 42372, 42373, 42374, 42377, 42386, + 42389, 42392, 42501, 42513, 42518, 42522, 42529, 42533, 42564, 42566, 42570, 42578, 42581, 42582, 42584, 42592, + 42594, 42630, 42640, 42645, 42646, 42649, 42657, 42660, 42662, 43008, 43010, 43016, 43018, 43040, 43042, 43048, + 43050, 43089, 43092, 43094, 43097, 43136, 43138, 43144, 43146, 43157, 43168, 43170, 43176, 43178, 43269, 43284, + 43289, 43297, 43301, 43329, 43344, 43349, 43354, 43361, 43366, 43369, 43408, 43414, 43520, 43522, 43528, 43530, + 43552, 43554, 43560, 43562, 43601, 43604, 43606, 43648, 43650, 43656, 43658, 43669, 43680, 43682, 43688, 43690, }; static const uint16_t kgrid_2bit_1024[1024] = { 0, 2, 5, 8, 10, 17, 20, 22, 25, 32, 34, 37, 40, 65, 68, 70, @@ -10918,12 +10217,12 @@ void iq2xs_init_impl(enum ggml_type type) { const int nwant = type == GGML_TYPE_IQ1_S ? 3 : type == GGML_TYPE_IQ2_S ? 1 : 2; const uint16_t * kgrid = type == GGML_TYPE_IQ2_XXS ? kgrid_2bit_256 : type == GGML_TYPE_IQ2_XS ? kgrid_2bit_512 : - type == GGML_TYPE_IQ1_S ? kgrid_1bit_512 : kgrid_2bit_1024; + type == GGML_TYPE_IQ1_S ? kgrid_1bit_2048 : kgrid_2bit_1024; uint64_t * kgrid_q2xs; int * kmap_q2xs; uint16_t * kneighbors_q2xs; - printf("================================================================= %s(grid_size = %d)\n", __func__, grid_size); + //printf("================================================================= %s(grid_size = %d)\n", __func__, grid_size); uint64_t * the_grid = (uint64_t *)malloc(grid_size*sizeof(uint64_t)); for (int k = 0; k < grid_size; ++k) { int8_t * pos = (int8_t *)(the_grid + k); @@ -10978,7 +10277,7 @@ void iq2xs_init_impl(enum ggml_type type) { } num_neighbors += n; } - printf("%s: %d neighbours in total\n", __func__, num_neighbors); + //printf("%s: %d neighbours in total\n", __func__, num_neighbors); kneighbors_q2xs = (uint16_t *)malloc((num_neighbors + num_not_in_map)*sizeof(uint16_t)); iq2_data[gindex].neighbours = kneighbors_q2xs; int counter = 0; @@ -11401,8 +10700,7 @@ static void quantize_row_iq2_xs_impl(const float * restrict x, void * restrict v } } -size_t quantize_iq2_xxs(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { - (void)hist; +size_t quantize_iq2_xxs(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { GGML_ASSERT(n_per_row%QK_K == 0); int nblock = n_per_row/QK_K; char * qrow = (char *)dst; @@ -11414,8 +10712,7 @@ size_t quantize_iq2_xxs(const float * src, void * dst, int nrow, int n_per_row, return nrow * nblock * sizeof(block_iq2_xxs); } -size_t quantize_iq2_xs(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { - (void)hist; +size_t quantize_iq2_xs(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { GGML_ASSERT(n_per_row%QK_K == 0); int nblock = n_per_row/QK_K; char * qrow = (char *)dst; @@ -11519,7 +10816,7 @@ void iq3xs_init_impl(int grid_size) { int * kmap_q3xs; uint16_t * kneighbors_q3xs; - printf("================================================================= %s(grid_size = %d)\n", __func__, grid_size); + //printf("================================================================= %s(grid_size = %d)\n", __func__, grid_size); uint32_t * the_grid = (uint32_t *)malloc(grid_size*sizeof(uint32_t)); for (int k = 0; k < grid_size; ++k) { int8_t * pos = (int8_t *)(the_grid + k); @@ -11574,7 +10871,7 @@ void iq3xs_init_impl(int grid_size) { } num_neighbors += n; } - printf("%s: %d neighbours in total\n", __func__, num_neighbors); + //printf("%s: %d neighbours in total\n", __func__, num_neighbors); kneighbors_q3xs = (uint16_t *)malloc((num_neighbors + num_not_in_map)*sizeof(uint16_t)); iq3_data[gindex].neighbours = kneighbors_q3xs; int counter = 0; @@ -11857,8 +11154,7 @@ static void quantize_row_iq3_xxs_impl(int grid_size, const float * restrict x, v } } -size_t quantize_iq3_xxs(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { - (void)hist; +size_t quantize_iq3_xxs(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { GGML_ASSERT(n_per_row%QK_K == 0); int nblock = n_per_row/QK_K; char * qrow = (char *)dst; @@ -12064,8 +11360,7 @@ static void quantize_row_iq3_s_impl(int block_size, const float * restrict x, vo } #define IQ3S_BLOCK_SIZE 32 -size_t quantize_iq3_s(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { - (void)hist; +size_t quantize_iq3_s(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { GGML_ASSERT(n_per_row%QK_K == 0); int nblock = n_per_row/QK_K; float scales[QK_K/IQ3S_BLOCK_SIZE]; @@ -12095,7 +11390,7 @@ void quantize_row_iq3_s(const float * restrict x, void * restrict vy, int k) { void quantize_row_iq3_s_reference(const float * restrict x, block_iq3_s * restrict y, int k) { assert(k % QK_K == 0); - quantize_iq3_s(x, y, 1, k, NULL, NULL); + quantize_iq3_s(x, y, 1, k, NULL); } @@ -12161,12 +11456,70 @@ static int iq1_find_best_neighbour(const uint16_t * restrict neighbours, const u return grid_index; } +static int iq1_find_best_neighbour2(const uint16_t * restrict neighbours, const uint64_t * restrict grid, + const float * restrict xval, const float * restrict weight, float scale, const float * restrict xg, int8_t * restrict L, int ngrid) { + int num_neighbors = neighbours[0]; + GGML_ASSERT(num_neighbors > 0); + float best_score = FLT_MAX; + int grid_index = -1; + for (int j = 1; j <= num_neighbors; ++j) { + const int8_t * pg = (const int8_t *)(grid + neighbours[j]); + float d2 = 0; + for (int i = 0; i < 8; ++i) { + float q = xg[(pg[i] - 1)/2]; + float w = weight[i]; + float diff = scale*q - xval[i]; + d2 += w*diff*diff; + } + if (d2 < best_score) { + best_score = d2; + grid_index = neighbours[j]; + } + } + if (grid_index < 0) { + for (int i = 0; i < ngrid; ++i) { + const int8_t * grid_i = (const int8_t *)(grid + i); + float d2 = 0; + for (int j = 0; j < 8; ++j) { + float w = weight[j]; + float q = xg[(grid_i[j] - 1)/2]; + float diff = scale*q - xval[i]; + d2 += w*diff*diff; + } + if (d2 < best_score) { + best_score = d2; + grid_index = i; + } + } + } + if (grid_index < 0) { + printf("Oops, did not find grid point\n"); + printf("Have %d neighbours\n", num_neighbors); + for (int j = 1; j <= num_neighbors; ++j) { + const int8_t * pg = (const int8_t *)(grid + neighbours[j]); + float sumqx = 0, sumq2 = 0; + for (int i = 0; i < 8; ++i) { + float q = xg[(pg[i] - 1)/2]; + float w = weight[i]; + sumqx += w*q*xval[i]; + sumq2 += w*q*q; + } + printf(" neighbour %d: sumqx = %g sumq2 = %g\n", j, (double)sumqx, (double)sumq2); + } + } + GGML_ASSERT(grid_index >= 0); + const int8_t * pg = (const int8_t *)(grid + grid_index); + for (int i = 0; i < 8; ++i) L[i] = (pg[i] - 1)/2; + return grid_index; +} + static int iq1_sort_helper(const void * left, const void * right) { const float * l = left; const float * r = right; return *l < *r ? -1 : *l > *r ? 1 : 0; } +#define IQ1S_BLOCK_SIZE 32 static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy, int n, const float * restrict quant_weights) { const int gindex = iq2_data_index(GGML_TYPE_IQ1_S); @@ -12185,37 +11538,41 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy block_iq1_s * y = vy; - float scales[QK_K/8]; - float weight[8]; - int8_t L[8]; - float sumx[9]; - float sumw[9]; - float pairs[16]; + const float x_p[3] = {-1 + IQ1S_DELTA, IQ1S_DELTA, 1 + IQ1S_DELTA}; + const float x_m[3] = {-1 - IQ1S_DELTA, -IQ1S_DELTA, 1 - IQ1S_DELTA}; + + float scales[QK_K/IQ1S_BLOCK_SIZE]; + float weight[IQ1S_BLOCK_SIZE]; + int8_t L[IQ1S_BLOCK_SIZE]; + float sumx[IQ1S_BLOCK_SIZE+1]; + float sumw[IQ1S_BLOCK_SIZE+1]; + float pairs[2*IQ1S_BLOCK_SIZE]; int * idx = (int *)(pairs + 1); - uint8_t hbit[QK_K/8]; + uint16_t index[IQ1S_BLOCK_SIZE/8]; + int8_t shifts[QK_K/IQ1S_BLOCK_SIZE]; for (int ibl = 0; ibl < nbl; ++ibl) { y[ibl].d = GGML_FP32_TO_FP16(0.f); memset(y[ibl].qs, 0, QK_K/8); - memset(y[ibl].scales, 0, QK_K/16); + memset(y[ibl].qh, 0, QK_K/16); float max_scale = 0; const float * xbl = x + QK_K*ibl; float sumx2 = 0; for (int i = 0; i < QK_K; ++i) sumx2 += xbl[i]*xbl[i]; - float sigma2 = sumx2/QK_K; + float sigma2 = 2*sumx2/QK_K; - for (int ib = 0; ib < QK_K/8; ++ib) { - const float * xb = xbl + 8*ib; - const float * qw = quant_weights + QK_K*ibl + 8*ib; - for (int i = 0; i < 8; ++i) weight[i] = qw[i] * sqrtf(sigma2 + xb[i]*xb[i]); + for (int ib = 0; ib < QK_K/IQ1S_BLOCK_SIZE; ++ib) { + const float * xb = xbl + IQ1S_BLOCK_SIZE*ib; + const float * qw = quant_weights + QK_K*ibl + IQ1S_BLOCK_SIZE*ib; + for (int i = 0; i < IQ1S_BLOCK_SIZE; ++i) weight[i] = qw[i] * sqrtf(sigma2 + xb[i]*xb[i]); float max = fabsf(xb[0]); - for (int i = 1; i < 8; ++i) max = MAX(max, fabsf(xb[i])); + for (int i = 1; i < IQ1S_BLOCK_SIZE; ++i) max = MAX(max, fabsf(xb[i])); if (!max) { scales[ib] = 0; - memset(L, 1, 8); + memset(L, 1, IQ1S_BLOCK_SIZE); continue; } // Here we solve exactly the sum of squared difference (SSD) weighted minimization problem. @@ -12224,52 +11581,81 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy // in ascending order, compute Si = sum[weight[j] xb[j], j = 0...i] and // Wi = sum[weight[j], j = 0...i], and use these to quckly get get the optimum scale // for each possible and score for each split. - for (int j = 0; j < 8; ++j) { + for (int j = 0; j < IQ1S_BLOCK_SIZE; ++j) { pairs[2*j] = xb[j]; idx[2*j] = j; } - qsort(pairs, 8, 2*sizeof(float), iq1_sort_helper); + qsort(pairs, IQ1S_BLOCK_SIZE, 2*sizeof(float), iq1_sort_helper); { sumx[0] = sumw[0] = 0; - for (int j = 0; j < 8; ++j) { + for (int j = 0; j < IQ1S_BLOCK_SIZE; ++j) { int i = idx[2*j]; sumx[j+1] = sumx[j] + weight[i]*xb[i]; sumw[j+1] = sumw[j] + weight[i]; } } float best_score = 0, scale = max; - int besti1 = 0, besti2 = 0; - for (int i1 = 0; i1 <= 8; ++i1) { - for (int i2 = i1; i2 <= 8; ++i2) { - float sumqx = -(sumx[i1] - sumx[0]) + (sumx[8] - sumx[i2]); - float sumq2 = (sumw[i1] - sumw[0]) + (sumw[8] - sumw[i2]); + int besti1 = -1, besti2 = -1, best_shift = 0; + for (int i1 = 0; i1 <= IQ1S_BLOCK_SIZE; ++i1) { + for (int i2 = i1; i2 <= IQ1S_BLOCK_SIZE; ++i2) { + float sumqx = (sumx[i1] - sumx[0])*x_p[0] + (sumx[i2] - sumx[i1])*x_p[1] + (sumx[IQ1S_BLOCK_SIZE] - sumx[i2])*x_p[2]; + float sumq2 = (sumw[i1] - sumw[0])*x_p[0]*x_p[0] + (sumw[i2] - sumw[i1])*x_p[1]*x_p[1] + (sumw[IQ1S_BLOCK_SIZE] - sumw[i2])*x_p[2]*x_p[2]; if (sumq2 > 0 && sumqx*sumqx > best_score*sumq2) { scale = sumqx/sumq2; best_score = scale*sumqx; - besti1 = i1; besti2 = i2; + besti1 = i1; besti2 = i2; best_shift = 1; + } + sumqx = (sumx[i1] - sumx[0])*x_m[0] + (sumx[i2] - sumx[i1])*x_m[1] + (sumx[IQ1S_BLOCK_SIZE] - sumx[i2])*x_m[2]; + sumq2 = (sumw[i1] - sumw[0])*x_m[0]*x_m[0] + (sumw[i2] - sumw[i1])*x_m[1]*x_m[1] + (sumw[IQ1S_BLOCK_SIZE] - sumw[i2])*x_m[2]*x_m[2]; + if (sumq2 > 0 && sumqx*sumqx > best_score*sumq2) { + scale = sumqx/sumq2; best_score = scale*sumqx; + besti1 = i1; besti2 = i2; best_shift = -1; } } } + GGML_ASSERT(besti1 >= 0 && besti2 >= 0 && best_shift != 0); for (int j = 0; j < besti1; ++j) L[idx[2*j]] = 0; for (int j = besti1; j < besti2; ++j) L[idx[2*j]] = 1; - for (int j = besti2; j < 8; ++j) L[idx[2*j]] = 2; + for (int j = besti2; j < IQ1S_BLOCK_SIZE; ++j) L[idx[2*j]] = 2; if (scale < 0) { - for (int j = 0; j < 8; ++j) L[j] = 2 - L[j]; - scale = -scale; + for (int j = 0; j < IQ1S_BLOCK_SIZE; ++j) L[j] = 2 - L[j]; + scale = -scale; best_shift = -best_shift; + } + bool all_on_grid = true; + const float * xx = best_shift == 1 ? x_p : x_m; + for (int k = 0; k < IQ1S_BLOCK_SIZE/8; ++k) { + uint16_t u = 0; + for (int j = 0; j < 8; ++j) u |= (L[8*k+j] << 2*j); + int grid_index = kmap_q2xs[u]; + if (grid_index < 0) { + all_on_grid = false; + const uint16_t * neighbours = kneighbors_q2xs - kmap_q2xs[u] - 1; + grid_index = iq1_find_best_neighbour2(neighbours, kgrid_q2xs, xb + 8*k, weight + 8*k, scale, xx, L + 8*k, NGRID_IQ1S); + GGML_ASSERT(grid_index >= 0); + } + index[k] = grid_index; + } + if (!all_on_grid) { + float sumqx = 0, sumq2 = 0; + for (int k = 0; k < IQ1S_BLOCK_SIZE/8; ++k) { + const int8_t * pg = (const int8_t *)(kgrid_q2xs + index[k]); + for (int j = 0; j < 8; ++j) { + float w = weight[8*k + j]; + float q = xx[(pg[j] - 1)/2]; + sumqx += w*q*xb[8*k+j]; + sumq2 += w*q*q; + } + } + if (sumqx > 0 && sumq2 > 0) scale = sumqx/sumq2; + } + uint16_t h = 0; + for (int k = 0; k < IQ1S_BLOCK_SIZE/8; ++k) { + y[ibl].qs[(IQ1S_BLOCK_SIZE/8)*ib + k] = index[k] & 255; + h |= (index[k] >> 8) << 3*k; } - // Now we check if the solution found above corresponds to a grid point and, if not, use a neighbouring - // grid point that minimizes SSD. - uint16_t u = 0; - for (int j = 0; j < 8; ++j) u |= (L[j] << 2*j); - int grid_index = kmap_q2xs[u]; - if (grid_index < 0) { - const uint16_t * neighbours = kneighbors_q2xs - kmap_q2xs[u] - 1; - grid_index = iq1_find_best_neighbour(neighbours, kgrid_q2xs, xb, weight, &scale, L, NGRID_IQ2XXS); - GGML_ASSERT(grid_index >= 0); - } - y[ibl].qs[ib] = grid_index & 255; - hbit[ib] = grid_index >> 8; + y[ibl].qh[ib] = h; GGML_ASSERT(scale >= 0); scales[ib] = scale; + shifts[ib] = best_shift; max_scale = MAX(max_scale, scale); } @@ -12279,19 +11665,18 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy } float d = max_scale/15; - y[ibl].d = GGML_FP32_TO_FP16(d*1.085f); // 1.085f is another fudge factor. Don't ask me why it is needed. + y[ibl].d = GGML_FP32_TO_FP16(d*1.125f); // 1.085f is another fudge factor. Don't ask me why it is needed. float id = 1/d; - for (int ib = 0; ib < QK_K/8; ++ib) { + for (int ib = 0; ib < QK_K/IQ1S_BLOCK_SIZE; ++ib) { int l = nearest_int(0.5f*(id*scales[ib]-1)); l = MAX(0, MIN(7, l)); - if (hbit[ib]) l |= 8; - y[ibl].scales[ib/2] |= (l << 4*(ib%2)); + if (shifts[ib] == -1) l |= 8; + y[ibl].qh[ib] |= (l << 12); } } } -size_t quantize_iq1_s(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { - (void)hist; +size_t quantize_iq1_s(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { GGML_ASSERT(n_per_row%QK_K == 0); int nblock = n_per_row/QK_K; char * qrow = (char *)dst; @@ -12316,7 +11701,7 @@ static inline int best_index_int8(int n, const int8_t * val, float x) { return x - val[mu-1] < val[mu] - x ? mu-1 : mu; } -static void quantize_row_iq4_nl_impl(const int super_block_size, const int block_size, const float * GGML_RESTRICT x, +static void quantize_row_iq4_nl_impl(const int super_block_size, const int block_size, const float * restrict x, ggml_fp16_t * dh, uint8_t * q4, uint16_t * scales_h, uint8_t * scales_l, float * scales, float * weight, uint8_t * L, const int8_t * values, @@ -12424,8 +11809,7 @@ static void quantize_row_iq4_nl_impl(const int super_block_size, const int block } } -size_t quantize_iq4_nl(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { - (void)hist; +size_t quantize_iq4_nl(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { GGML_ASSERT(n_per_row%QK4_NL == 0); int nblock = n_per_row/QK4_NL; char * qrow = (char *)dst; @@ -12455,14 +11839,13 @@ void quantize_row_iq4_nl(const float * restrict x, void * restrict vy, int k) { void quantize_row_iq4_nl_reference(const float * restrict x, block_iq4_nl * restrict y, int k) { assert(k % QK4_NL == 0); - quantize_iq4_nl(x, y, 1, k, NULL, NULL); + quantize_iq4_nl(x, y, 1, k, NULL); } -size_t quantize_iq4_xs(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { +size_t quantize_iq4_xs(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { #if QK_K == 64 - return quantize_iq4_nl(src, dst, nrow, n_per_row, hist, quant_weights); + return quantize_iq4_nl(src, dst, nrow, n_per_row, quant_weights); #else - (void)hist; GGML_ASSERT(n_per_row%QK_K == 0); int nblock = n_per_row/QK_K; char * qrow = (char *)dst; @@ -12491,7 +11874,7 @@ void quantize_row_iq4_xs(const float * restrict x, void * restrict vy, int k) { void quantize_row_iq4_xs_reference(const float * restrict x, block_iq4_xs * restrict y, int k) { assert(k % QK_K == 0); - quantize_iq4_xs(x, y, 1, k, NULL, NULL); + quantize_iq4_xs(x, y, 1, k, NULL); } // =============================== 2.5625 bpw @@ -12664,8 +12047,7 @@ static void quantize_row_iq2_s_impl(const float * restrict x, void * restrict vy } } -size_t quantize_iq2_s(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) { - (void)hist; +size_t quantize_iq2_s(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) { GGML_ASSERT(n_per_row%QK_K == 0); int nblock = n_per_row/QK_K; char * qrow = (char *)dst; @@ -12679,7 +12061,7 @@ size_t quantize_iq2_s(const float * src, void * dst, int nrow, int n_per_row, in void quantize_row_iq2_s_reference(const float * restrict x, block_iq2_s * restrict y, int k) { assert(k % QK_K == 0); - quantize_iq2_s(x, y, 1, k, NULL, NULL); + quantize_iq2_s(x, y, 1, k, NULL); } void quantize_row_iq2_s(const float * restrict x, void * restrict vy, int k) { diff --git a/src/ggml-quants.h b/src/ggml-quants.h index 316e35687..aa7e54a16 100644 --- a/src/ggml-quants.h +++ b/src/ggml-quants.h @@ -1,247 +1,11 @@ #pragma once -#include "ggml-impl.h" +#define GGML_COMMON_DECL_C +#include "ggml-common.h" -// GGML internal header - -#include -#include - -#define QK4_0 32 -typedef struct { - ggml_fp16_t d; // delta - uint8_t qs[QK4_0 / 2]; // nibbles / quants -} block_q4_0; -static_assert(sizeof(block_q4_0) == sizeof(ggml_fp16_t) + QK4_0 / 2, "wrong q4_0 block size/padding"); - -#define QK4_1 32 -typedef struct { - ggml_fp16_t d; // delta - ggml_fp16_t m; // min - uint8_t qs[QK4_1 / 2]; // nibbles / quants -} block_q4_1; -static_assert(sizeof(block_q4_1) == 2 * sizeof(ggml_fp16_t) + QK4_1 / 2, "wrong q4_1 block size/padding"); - -#define QK5_0 32 -typedef struct { - ggml_fp16_t d; // delta - uint8_t qh[4]; // 5-th bit of quants - uint8_t qs[QK5_0 / 2]; // nibbles / quants -} block_q5_0; -static_assert(sizeof(block_q5_0) == sizeof(ggml_fp16_t) + sizeof(uint32_t) + QK5_0 / 2, "wrong q5_0 block size/padding"); - -#define QK5_1 32 -typedef struct { - ggml_fp16_t d; // delta - ggml_fp16_t m; // min - uint8_t qh[4]; // 5-th bit of quants - uint8_t qs[QK5_1 / 2]; // nibbles / quants -} block_q5_1; -static_assert(sizeof(block_q5_1) == 2 * sizeof(ggml_fp16_t) + sizeof(uint32_t) + QK5_1 / 2, "wrong q5_1 block size/padding"); - -#define QK8_0 32 -typedef struct { - ggml_fp16_t d; // delta - int8_t qs[QK8_0]; // quants -} block_q8_0; -static_assert(sizeof(block_q8_0) == sizeof(ggml_fp16_t) + QK8_0, "wrong q8_0 block size/padding"); - -#define QK8_1 32 -typedef struct { - float d; // delta - float s; // d * sum(qs[i]) - int8_t qs[QK8_1]; // quants -} block_q8_1; -static_assert(sizeof(block_q8_1) == 2*sizeof(float) + QK8_1, "wrong q8_1 block size/padding"); - -// -// Super-block quantization structures -// - -// Super-block size -#ifdef GGML_QKK_64 -#define QK_K 64 -#define K_SCALE_SIZE 4 -#else -#define QK_K 256 -#define K_SCALE_SIZE 12 -#endif - -// 2-bit quantization -// weight is represented as x = a * q + b -// 16 blocks of 16 elements each -// Effectively 2.625 bits per weight -typedef struct { - uint8_t scales[QK_K/16]; // scales and mins, quantized with 4 bits - uint8_t qs[QK_K/4]; // quants - ggml_fp16_t d; // super-block scale for quantized scales - ggml_fp16_t dmin; // super-block scale for quantized mins -} block_q2_K; -static_assert(sizeof(block_q2_K) == 2*sizeof(ggml_fp16_t) + QK_K/16 + QK_K/4, "wrong q2_K block size/padding"); - -// 3-bit quantization -// weight is represented as x = a * q -// 16 blocks of 16 elements each -// Effectively 3.4375 bits per weight -#ifdef GGML_QKK_64 -typedef struct { - uint8_t hmask[QK_K/8]; // quants - high bit - uint8_t qs[QK_K/4]; // quants - low 2 bits - uint8_t scales[2]; - ggml_fp16_t d; // super-block scale -} block_q3_K; -static_assert(sizeof(block_q3_K) == sizeof(ggml_fp16_t) + QK_K / 4 + QK_K / 8 + 2, "wrong q3_K block size/padding"); -#else -typedef struct { - uint8_t hmask[QK_K/8]; // quants - high bit - uint8_t qs[QK_K/4]; // quants - low 2 bits - uint8_t scales[12]; // scales, quantized with 6 bits - ggml_fp16_t d; // super-block scale -} block_q3_K; -static_assert(sizeof(block_q3_K) == sizeof(ggml_fp16_t) + QK_K / 4 + QK_K / 8 + 12, "wrong q3_K block size/padding"); -#endif - -// 4-bit quantization -// 8 blocks of 32 elements each -// weight is represented as x = a * q + b -// Effectively 4.5 bits per weight -#ifdef GGML_QKK_64 -typedef struct { - ggml_fp16_t d[2]; // super-block scales/mins - uint8_t scales[2]; // 4-bit block scales/mins - uint8_t qs[QK_K/2]; // 4--bit quants -} block_q4_K; -static_assert(sizeof(block_q4_K) == 2*sizeof(ggml_fp16_t) + QK_K/2 + 2, "wrong q4_K block size/padding"); -#else -typedef struct { - ggml_fp16_t d; // super-block scale for quantized scales - ggml_fp16_t dmin; // super-block scale for quantized mins - uint8_t scales[K_SCALE_SIZE]; // scales and mins, quantized with 6 bits - uint8_t qs[QK_K/2]; // 4--bit quants -} block_q4_K; -static_assert(sizeof(block_q4_K) == 2*sizeof(ggml_fp16_t) + K_SCALE_SIZE + QK_K/2, "wrong q4_K block size/padding"); -#endif - -// 5-bit quantization -// 8 blocks of 32 elements each -// weight is represented as x = a * q + b -// Effectively 5.5 bits per weight -#ifdef GGML_QKK_64 -typedef struct { - ggml_fp16_t d; // super-block scale - int8_t scales[QK_K/16]; // 8-bit block scales - uint8_t qh[QK_K/8]; // quants, high bit - uint8_t qs[QK_K/2]; // quants, low 4 bits -} block_q5_K; -static_assert(sizeof(block_q5_K) == sizeof(ggml_fp16_t) + QK_K/2 + QK_K/8 + QK_K/16, "wrong q5_K block size/padding"); -#else -typedef struct { - ggml_fp16_t d; // super-block scale for quantized scales - ggml_fp16_t dmin; // super-block scale for quantized mins - uint8_t scales[K_SCALE_SIZE]; // scales and mins, quantized with 6 bits - uint8_t qh[QK_K/8]; // quants, high bit - uint8_t qs[QK_K/2]; // quants, low 4 bits -} block_q5_K; -static_assert(sizeof(block_q5_K) == 2*sizeof(ggml_fp16_t) + K_SCALE_SIZE + QK_K/2 + QK_K/8, "wrong q5_K block size/padding"); -#endif - -// 6-bit quantization -// weight is represented as x = a * q -// 16 blocks of 16 elements each -// Effectively 6.5625 bits per weight -typedef struct { - uint8_t ql[QK_K/2]; // quants, lower 4 bits - uint8_t qh[QK_K/4]; // quants, upper 2 bits - int8_t scales[QK_K/16]; // scales, quantized with 8 bits - ggml_fp16_t d; // super-block scale -} block_q6_K; -static_assert(sizeof(block_q6_K) == sizeof(ggml_fp16_t) + QK_K / 16 + 3*QK_K/4, "wrong q6_K block size/padding"); - -// This is only used for intermediate quantization and dot products -typedef struct { - float d; // delta - int8_t qs[QK_K]; // quants - int16_t bsums[QK_K/16]; // sum of quants in groups of 16 -} block_q8_K; -static_assert(sizeof(block_q8_K) == sizeof(float) + QK_K + QK_K/16*sizeof(int16_t), "wrong q8_K block size/padding"); - -// (Almost) "true" 2-bit quantization. -// Due to the need to use blocks as per ggml design, it ends up using -// 2.0625 bpw because of the 16-bit scale for each block of 256. -typedef struct { - ggml_fp16_t d; - uint16_t qs[QK_K/8]; -} block_iq2_xxs; -static_assert(sizeof(block_iq2_xxs) == sizeof(ggml_fp16_t) + QK_K/8*sizeof(uint16_t), "wrong iq2_xxs block size/padding"); - -// 2.3125 bpw quants -typedef struct { - ggml_fp16_t d; - uint16_t qs[QK_K/8]; - uint8_t scales[QK_K/32]; -} block_iq2_xs; -static_assert(sizeof(block_iq2_xs) == sizeof(ggml_fp16_t) + QK_K/8*sizeof(uint16_t) + QK_K/32, "wrong iq2_xs block size/padding"); - -// 2.5625 bpw quants -typedef struct { - ggml_fp16_t d; - uint8_t qs[QK_K/4]; - uint8_t qh[QK_K/32]; - uint8_t scales[QK_K/32]; -} block_iq2_s; -static_assert(sizeof(block_iq2_s) == sizeof(ggml_fp16_t) + QK_K/4 + QK_K/16, "wrong iq2_s block size/padding"); - -// (Almost) "true" 3-bit quantization. -// Due to the need to use blocks as per ggml design, it ends up using -// 3.0625 bpw because of the 16-bit scale for each block of 256. -typedef struct { - ggml_fp16_t d; - uint8_t qs[3*QK_K/8]; -} block_iq3_xxs; -static_assert(sizeof(block_iq3_xxs) == sizeof(ggml_fp16_t) + 3*(QK_K/8), "wrong iq3_xxs block size/padding"); - -// 3.4375 bpw -#if QK_K == 64 -#define IQ3S_N_SCALE 2 -#else -#define IQ3S_N_SCALE QK_K/64 -#endif -typedef struct { - ggml_fp16_t d; - uint8_t qs[QK_K/4]; - uint8_t qh[QK_K/32]; - uint8_t signs[QK_K/8]; - uint8_t scales[IQ3S_N_SCALE]; -} block_iq3_s; -static_assert(sizeof(block_iq3_s) == sizeof(ggml_fp16_t) + 13*(QK_K/32) + IQ3S_N_SCALE, "wrong iq3_s block size/padding"); +#include "ggml.h" -typedef struct { - ggml_fp16_t d; - uint8_t qs[QK_K/8]; - uint8_t scales[QK_K/16]; -} block_iq1_s; -static_assert(sizeof(block_iq1_s) == sizeof(ggml_fp16_t) + QK_K/8 + QK_K/16, "wrong iq1_s block size/padding"); - -// Non-linear quants -#define QK4_NL 32 -typedef struct { - ggml_fp16_t d; - uint8_t qs[QK4_NL/2]; -} block_iq4_nl; -static_assert(sizeof(block_iq4_nl) == sizeof(ggml_fp16_t) + QK4_NL/2, "wrong iq4_nl block size/padding"); - -#if QK_K == 64 -#define block_iq4_xs block_iq4_nl -//typedef struct block_iq4_nl block_iq4_xs; -#else -typedef struct { - ggml_fp16_t d; - uint16_t scales_h; - uint8_t scales_l[QK_K/64]; - uint8_t qs[QK_K/2]; -} block_iq4_xs; -static_assert(sizeof(block_iq4_xs) == sizeof(ggml_fp16_t) + sizeof(uint16_t) + QK_K/64 + QK_K/2, "wrong iq4_xs block size/padding"); -#endif +// GGML internal header #ifdef __cplusplus extern "C" { @@ -261,6 +25,7 @@ void quantize_row_q4_K_reference(const float * GGML_RESTRICT x, block_q4_K * GGM void quantize_row_q5_K_reference(const float * GGML_RESTRICT x, block_q5_K * GGML_RESTRICT y, int k); void quantize_row_q6_K_reference(const float * GGML_RESTRICT x, block_q6_K * GGML_RESTRICT y, int k); void quantize_row_q8_K_reference(const float * GGML_RESTRICT x, block_q8_K * GGML_RESTRICT y, int k); + void quantize_row_iq3_xxs_reference(const float * GGML_RESTRICT x, block_iq3_xxs * GGML_RESTRICT y, int k); void quantize_row_iq4_nl_reference (const float * GGML_RESTRICT x, block_iq4_nl * GGML_RESTRICT y, int k); void quantize_row_iq4_xs_reference (const float * GGML_RESTRICT x, block_iq4_xs * GGML_RESTRICT y, int k); @@ -280,6 +45,7 @@ void quantize_row_q4_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, in void quantize_row_q5_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k); void quantize_row_q6_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k); void quantize_row_q8_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k); + void quantize_row_iq3_xxs(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k); void quantize_row_iq4_nl (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k); void quantize_row_iq4_xs (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k); @@ -300,6 +66,7 @@ void dequantize_row_q4_K(const block_q4_K * GGML_RESTRICT x, float * GGML_RESTRI void dequantize_row_q5_K(const block_q5_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k); void dequantize_row_q6_K(const block_q6_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k); void dequantize_row_q8_K(const block_q8_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k); + void dequantize_row_iq2_xxs(const block_iq2_xxs * GGML_RESTRICT x, float * GGML_RESTRICT y, int k); void dequantize_row_iq2_xs (const block_iq2_xs * GGML_RESTRICT x, float * GGML_RESTRICT y, int k); void dequantize_row_iq2_s (const block_iq2_s * GGML_RESTRICT x, float * GGML_RESTRICT y, int k); @@ -321,6 +88,7 @@ void ggml_vec_dot_q3_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi void ggml_vec_dot_q4_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc); void ggml_vec_dot_q5_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc); void ggml_vec_dot_q6_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc); + void ggml_vec_dot_iq2_xxs_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc); void ggml_vec_dot_iq2_xs_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc); void ggml_vec_dot_iq2_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc); @@ -330,26 +98,26 @@ void ggml_vec_dot_iq4_nl_q8_0 (int n, float * GGML_RESTRICT s, size_t bs, const void ggml_vec_dot_iq4_xs_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc); void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc); -// // Quantization utilizing an importance matrix (a.k.a. "Activation aWare Quantization") -// -size_t quantize_iq2_xxs(const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_iq2_xs (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_iq2_s (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_iq3_xxs(const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_iq1_s (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_iq4_nl (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_iq4_xs (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_iq3_s (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_q2_K (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_q3_K (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_q4_K (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_q5_K (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_q6_K (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_q4_0 (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_q4_1 (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_q5_0 (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -size_t quantize_q5_1 (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); +size_t quantize_iq2_xxs(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq2_xs (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq2_s (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq3_xxs(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq1_s (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq4_nl (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq4_xs (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq3_s (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); + +size_t quantize_q2_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q3_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q4_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q5_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q6_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q4_0(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q4_1(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q5_0(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q5_1(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q8_0(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); void iq2xs_init_impl(enum ggml_type type); void iq2xs_free_impl(enum ggml_type type); diff --git a/src/ggml-sycl.cpp b/src/ggml-sycl.cpp index ddd951dd6..9f6506383 100644 --- a/src/ggml-sycl.cpp +++ b/src/ggml-sycl.cpp @@ -202,24 +202,29 @@ namespace dpct // Version string has the following format: // a. OpenCL // b. + // c. e.g gfx1030 std::string ver; ver = dev.get_info(); std::string::size_type i = 0; - while (i < ver.size()) - { - if (isdigit(ver[i])) - break; - i++; + while (i < ver.size()) { + if (isdigit(ver[i])) + break; + i++; } major = std::stoi(&(ver[i])); - while (i < ver.size()) - { - if (ver[i] == '.') - break; - i++; + while (i < ver.size()) { + if (ver[i] == '.') + break; + i++; + } + if (i < ver.size()) { + // a. and b. + i++; + minor = std::stoi(&(ver[i])); + } else { + // c. + minor = 0; } - i++; - minor = std::stoi(&(ver[i])); } template @@ -3144,6 +3149,9 @@ namespace dpct } // COPY from DPCT head files +#define GGML_COMMON_DECL_SYCL +#define GGML_COMMON_IMPL_SYCL +#include "ggml-common.h" static int g_ggml_sycl_debug=0; #define GGML_SYCL_DEBUG(...) do{if(g_ggml_sycl_debug) printf(__VA_ARGS__);}while(0) @@ -3310,66 +3318,6 @@ typedef void (*ggml_sycl_op_flatten_t)(const ggml_tensor *src0, const float *src1_dd, float *dst_dd, const dpct::queue_ptr &main_stream); -// QK = number of values after dequantization -// QR = QK / number of values before dequantization -// QI = number of 32 bit integers before dequantization - -#define QK4_0 32 -#define QR4_0 2 -#define QI4_0 (QK4_0 / (4 * QR4_0)) -typedef struct dpct_type_block_q4_0 { - sycl::half d; // delta - uint8_t qs[QK4_0 / 2]; // nibbles / quants -} block_q4_0; -static_assert(sizeof(block_q4_0) == sizeof(ggml_fp16_t) + QK4_0 / 2, "wrong q4_0 block size/padding"); - -#define QK4_1 32 -#define QR4_1 2 -#define QI4_1 (QK4_1 / (4 * QR4_1)) -typedef struct dpct_type_block_q4_1 { - sycl::half2 dm; // dm.x = delta, dm.y = min - uint8_t qs[QK4_1 / 2]; // nibbles / quants -} block_q4_1; -static_assert(sizeof(block_q4_1) == sizeof(ggml_fp16_t) * 2 + QK4_1 / 2, "wrong q4_1 block size/padding"); - -#define QK5_0 32 -#define QR5_0 2 -#define QI5_0 (QK5_0 / (4 * QR5_0)) -typedef struct dpct_type_block_q5_0 { - sycl::half d; // delta - uint8_t qh[4]; // 5-th bit of quants - uint8_t qs[QK5_0 / 2]; // nibbles / quants -} block_q5_0; -static_assert(sizeof(block_q5_0) == sizeof(ggml_fp16_t) + sizeof(uint32_t) + QK5_0 / 2, "wrong q5_0 block size/padding"); - -#define QK5_1 32 -#define QR5_1 2 -#define QI5_1 (QK5_1 / (4 * QR5_1)) -typedef struct dpct_type_block_q5_1 { - sycl::half2 dm; // dm.x = delta, dm.y = min - uint8_t qh[4]; // 5-th bit of quants - uint8_t qs[QK5_1 / 2]; // nibbles / quants -} block_q5_1; -static_assert(sizeof(block_q5_1) == 2 * sizeof(ggml_fp16_t) + sizeof(uint32_t) + QK5_1 / 2, "wrong q5_1 block size/padding"); - -#define QK8_0 32 -#define QR8_0 1 -#define QI8_0 (QK8_0 / (4 * QR8_0)) -typedef struct dpct_type_block_q8_0 { - sycl::half d; // delta - int8_t qs[QK8_0]; // quants -} block_q8_0; -static_assert(sizeof(block_q8_0) == sizeof(ggml_fp16_t) + QK8_0, "wrong q8_0 block size/padding"); - -#define QK8_1 32 -#define QR8_1 1 -#define QI8_1 (QK8_1 / (4 * QR8_1)) -typedef struct dpct_type_block_q8_1 { - sycl::half2 ds; // ds.x = delta, ds.y = sum - int8_t qs[QK8_0]; // quants -} block_q8_1; -static_assert(sizeof(block_q8_1) == 2*sizeof(ggml_fp16_t) + QK8_0, "wrong q8_1 block size/padding"); - typedef float (*vec_dot_q_sycl_t)(const void * __restrict__ vbq, const block_q8_1 * __restrict__ bq8_1, const int & iqs); typedef void (*allocate_tiles_sycl_t)(int **x_ql, sycl::half2 **x_dm, int **x_qh, int **x_sc); @@ -3386,112 +3334,6 @@ typedef float (*vec_dot_q_mul_mat_sycl_t)( const int *__restrict__ y_qs, const sycl::half2 *__restrict__ y_ms, const int &i, const int &j, const int &k); -//================================= k-quants - -#ifdef GGML_QKK_64 -#define QK_K 64 -#define K_SCALE_SIZE 4 -#else -#define QK_K 256 -#define K_SCALE_SIZE 12 -#endif - -#define QR2_K 4 -#define QI2_K (QK_K / (4*QR2_K)) -typedef struct dpct_type_block_q2_K { - uint8_t scales[QK_K/16]; // scales and mins, quantized with 4 bits - uint8_t qs[QK_K/4]; // quants - sycl::half2 dm; // super-block scale for quantized scales/mins -} block_q2_K; -static_assert(sizeof(block_q2_K) == 2*sizeof(ggml_fp16_t) + QK_K/16 + QK_K/4, "wrong q2_K block size/padding"); - -#define QR3_K 4 -#define QI3_K (QK_K / (4*QR3_K)) -typedef struct dpct_type_block_q3_K { - uint8_t hmask[QK_K/8]; // quants - high bit - uint8_t qs[QK_K/4]; // quants - low 2 bits -#ifdef GGML_QKK_64 - uint8_t scales[2]; // scales, quantized with 8 bits -#else - uint8_t scales[K_SCALE_SIZE]; // scales, quantized with 6 bits -#endif - sycl::half d; // super-block scale -} block_q3_K; -//static_assert(sizeof(block_q3_K) == sizeof(ggml_fp16_t) + QK_K / 4 + QK_K / 8 + K_SCALE_SIZE, "wrong q3_K block size/padding"); - -#define QR4_K 2 -#define QI4_K (QK_K / (4*QR4_K)) -#ifdef GGML_QKK_64 -typedef struct { - sycl::half dm[2]; // super-block scales/mins - uint8_t scales[2]; // 4-bit block scales/mins - uint8_t qs[QK_K/2]; // 4--bit quants -} block_q4_K; -static_assert(sizeof(block_q4_K) == sizeof(sycl::half2) + QK_K/2 + 2, "wrong q4_K block size/padding"); -#else -typedef struct dpct_type_block_q4_K { - sycl::half2 dm; // super-block scale for quantized scales/mins - uint8_t scales[3*QK_K/64]; // scales, quantized with 6 bits - uint8_t qs[QK_K/2]; // 4--bit quants -} block_q4_K; -static_assert(sizeof(block_q4_K) == 2*sizeof(ggml_fp16_t) + 3*QK_K/64 + QK_K/2, "wrong q4_K block size/padding"); -#endif - -#define QR5_K 2 -#define QI5_K (QK_K / (4*QR5_K)) -#ifdef GGML_QKK_64 -typedef struct { - sycl::half d; // super-block scale - int8_t scales[QK_K/16]; // block scales - uint8_t qh[QK_K/8]; // quants, high bit - uint8_t qs[QK_K/2]; // quants, low 4 bits -} block_q5_K; -static_assert(sizeof(block_q5_K) == sizeof(ggml_fp16_t) + QK_K/2 + QK_K/8 + QK_K/16, "wrong q5_K block size/padding"); -#else -typedef struct dpct_type_block_q5_K { - sycl::half2 dm; // super-block scale for quantized scales/mins - uint8_t scales[K_SCALE_SIZE]; // scales and mins, quantized with 6 bits - uint8_t qh[QK_K/8]; // quants, high bit - uint8_t qs[QK_K/2]; // quants, low 4 bits -} block_q5_K; -static_assert(sizeof(block_q5_K) == 2*sizeof(ggml_fp16_t) + K_SCALE_SIZE + QK_K/2 + QK_K/8, "wrong q5_K block size/padding"); -#endif - -#define QR6_K 2 -#define QI6_K (QK_K / (4*QR6_K)) -typedef struct dpct_type_block_q6_K { - uint8_t ql[QK_K/2]; // quants, lower 4 bits - uint8_t qh[QK_K/4]; // quants, upper 2 bits - int8_t scales[QK_K/16]; // scales - sycl::half d; // delta -} block_q6_K; -static_assert(sizeof(block_q6_K) == sizeof(ggml_fp16_t) + 13*QK_K/16, "wrong q6_K block size/padding"); - -#define QR2_XXS 8 -#define QI2_XXS (QK_K / (4*QR2_XXS)) -typedef struct dpct_type_block_iq2_xxs { - sycl::half d; - uint16_t qs[QK_K/8]; -} block_iq2_xxs; -static_assert(sizeof(block_iq2_xxs) == sizeof(ggml_fp16_t) + QK_K/8*sizeof(uint16_t), "wrong iq2_xxs block size/padding"); - -#define QR2_XS 8 -#define QI2_XS (QK_K / (4*QR2_XS)) -typedef struct dpct_type_block_iq2_xs { - sycl::half d; - uint16_t qs[QK_K/8]; - uint8_t scales[QK_K/32]; -} block_iq2_xs; -static_assert(sizeof(block_iq2_xs) == sizeof(ggml_fp16_t) + QK_K/8*sizeof(uint16_t) + QK_K/32, "wrong iq2_xs block size/padding"); - -#define QR3_XXS 8 -#define QI3_XXS (QK_K / (4*QR3_XXS)) -typedef struct dpct_type_block_iq3_xxs { - sycl::half d; - uint8_t qs[3*(QK_K/8)]; -} block_iq3_xxs; -static_assert(sizeof(block_iq3_xxs) == sizeof(ggml_fp16_t) + 3*(QK_K/8), "wrong iq3_xxs block size/padding"); - #define WARP_SIZE 32 #define MATRIX_ROW_PADDING 512 // last row of quant. matrices is a multiple of this to avoid out-of-bounds memory accesses @@ -4745,388 +4587,6 @@ static void dequantize_block_q6_K(const void * __restrict__ vx, dst_t * __restri #endif } -static dpct::global_memory - iq2xxs_grid(sycl::range<1>(256), - { - 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, - 0x0808080808082b08, 0x0808080808082b2b, 0x0808080808190819, - 0x0808080808191908, 0x08080808082b0808, 0x08080808082b082b, - 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819, - 0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, - 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808, - 0x080808082b08082b, 0x080808082b082b2b, 0x080808082b2b082b, - 0x0808081908080819, 0x0808081908081908, 0x0808081908190808, - 0x0808081908191919, 0x0808081919080808, 0x080808192b081908, - 0x080808192b192b08, 0x0808082b08080808, 0x0808082b0808082b, - 0x0808082b082b082b, 0x0808082b2b08082b, 0x0808190808080819, - 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819, - 0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, - 0x0808190819082b08, 0x08081908192b0808, 0x080819082b080819, - 0x080819082b081908, 0x080819082b190808, 0x080819082b2b1908, - 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08, - 0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, - 0x080819192b080808, 0x080819192b190819, 0x0808192b08082b19, - 0x0808192b08190808, 0x0808192b19080808, 0x0808192b2b081908, - 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919, - 0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, - 0x08082b0819080819, 0x08082b0819081908, 0x08082b0819190808, - 0x08082b081919082b, 0x08082b082b082b08, 0x08082b1908081908, - 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908, - 0x0819080808080819, 0x0819080808081908, 0x0819080808190808, - 0x08190808082b0819, 0x0819080819080808, 0x08190808192b0808, - 0x081908082b081908, 0x081908082b190808, 0x081908082b191919, - 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808, - 0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, - 0x0819082b082b1908, 0x0819082b19081919, 0x0819190808080808, - 0x0819190808082b08, 0x08191908082b0808, 0x08191908082b1919, - 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08, - 0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, - 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808, - 0x08192b0819080808, 0x08192b082b080819, 0x08192b1908080808, - 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819, - 0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, - 0x082b080819081908, 0x082b0808192b0819, 0x082b08082b080808, - 0x082b08082b08082b, 0x082b0819082b2b19, 0x082b081919082b08, - 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819, - 0x082b190808081908, 0x082b190808190808, 0x082b190819080808, - 0x082b19081919192b, 0x082b191908080808, 0x082b191919080819, - 0x082b1919192b1908, 0x082b192b2b190808, 0x082b2b0808082b08, - 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908, - 0x1908080808080819, 0x1908080808081908, 0x1908080808190808, - 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908, - 0x1908080819080808, 0x1908080819082b08, 0x190808081919192b, - 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908, - 0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, - 0x19080819192b0819, 0x190808192b080808, 0x190808192b081919, - 0x1908082b08080819, 0x1908082b08190808, 0x1908082b19082b08, - 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808, - 0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, - 0x190819082b192b19, 0x190819190819082b, 0x19081919082b1908, - 0x1908192b08080808, 0x19082b0808080819, 0x19082b0808081908, - 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, - 0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, - 0x19082b192b08082b, 0x19082b2b19081919, 0x19082b2b2b190808, - 0x1919080808080808, 0x1919080808082b08, 0x1919080808190819, - 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808, - 0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, - 0x191908192b2b1908, 0x1919082b2b190819, 0x191919082b190808, - 0x191919082b19082b, 0x1919191908082b2b, 0x1919192b08080819, - 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819, - 0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, - 0x19192b2b08082b08, 0x192b080808081908, 0x192b080808190808, - 0x192b080819080808, 0x192b0808192b2b08, 0x192b081908080808, - 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808, - 0x192b190808080808, 0x192b190808081919, 0x192b191908190808, - 0x192b19190819082b, 0x192b19192b081908, 0x192b2b081908082b, - 0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808082b2b, - 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908, - 0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, - 0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, - 0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, - 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908, - 0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, - 0x2b082b080808082b, 0x2b082b1908081908, 0x2b082b2b08190819, - 0x2b19080808081908, 0x2b19080808190808, 0x2b190808082b1908, - 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b, - 0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, - 0x2b191908082b082b, 0x2b19190819081908, 0x2b19191919190819, - 0x2b192b082b080819, 0x2b192b19082b0808, 0x2b2b08080808082b, - 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19, - 0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, - 0x2b2b2b1908081908, - }); - -static dpct::global_memory - iq2xs_grid(sycl::range<1>(512), - { - 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, - 0x0808080808082b08, 0x0808080808082b2b, 0x0808080808190819, - 0x0808080808191908, 0x080808080819192b, 0x0808080808192b19, - 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919, - 0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, - 0x080808081908192b, 0x0808080819082b19, 0x0808080819190808, - 0x080808081919082b, 0x0808080819191919, 0x0808080819192b08, - 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808, - 0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, - 0x080808082b190819, 0x080808082b191908, 0x080808082b192b19, - 0x080808082b2b0808, 0x0808081908080819, 0x0808081908081908, - 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, - 0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, - 0x0808081908192b2b, 0x08080819082b0819, 0x08080819082b1908, - 0x0808081919080808, 0x080808191908082b, 0x0808081919081919, - 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908, - 0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, - 0x080808192b081908, 0x080808192b190808, 0x0808082b08080808, - 0x0808082b0808082b, 0x0808082b08081919, 0x0808082b08082b08, - 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808, - 0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, - 0x0808082b19191919, 0x0808082b2b080808, 0x0808082b2b082b2b, - 0x0808190808080819, 0x0808190808081908, 0x080819080808192b, - 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, - 0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, - 0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, - 0x0808190819081919, 0x0808190819082b08, 0x0808190819190819, - 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808, - 0x080819082b080819, 0x080819082b081908, 0x080819082b190808, - 0x0808191908080808, 0x080819190808082b, 0x0808191908081919, - 0x0808191908082b08, 0x0808191908190819, 0x0808191908191908, - 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908, - 0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, - 0x0808192b08080819, 0x0808192b08081908, 0x0808192b08190808, - 0x0808192b082b192b, 0x0808192b19080808, 0x0808192b1908082b, - 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b, - 0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, - 0x08082b0808190819, 0x08082b0808191908, 0x08082b08082b0808, - 0x08082b08082b1919, 0x08082b0819080819, 0x08082b0819081908, - 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808, - 0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, - 0x08082b1908081908, 0x08082b1908190808, 0x08082b1919080808, - 0x08082b192b080819, 0x08082b192b082b19, 0x08082b2b08080808, - 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b, - 0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, - 0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, - 0x081908080819082b, 0x0819080808191919, 0x0819080808192b08, - 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808, - 0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, - 0x0819080819190819, 0x0819080819191908, 0x08190808192b0808, - 0x08190808192b2b2b, 0x081908082b080819, 0x081908082b081908, - 0x081908082b190808, 0x0819081908080808, 0x081908190808082b, - 0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, - 0x0819081908191908, 0x08190819082b0808, 0x0819081919080819, - 0x0819081919081908, 0x0819081919190808, 0x081908192b080808, - 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819, - 0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, - 0x0819082b19080808, 0x0819082b192b0808, 0x0819190808080808, - 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08, - 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808, - 0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, - 0x0819190819190808, 0x08191908192b1908, 0x081919082b080808, - 0x0819191908080819, 0x0819191908081908, 0x0819191908190808, - 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908, - 0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, - 0x08192b0808190808, 0x08192b080819082b, 0x08192b0819080808, - 0x08192b0819191908, 0x08192b082b08192b, 0x08192b1908080808, - 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819, - 0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, - 0x082b080808081919, 0x082b080808082b08, 0x082b080808082b2b, - 0x082b080808190819, 0x082b080808191908, 0x082b0808082b0808, - 0x082b080819080819, 0x082b080819081908, 0x082b080819190808, - 0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, - 0x082b081908081908, 0x082b081908190808, 0x082b081919080808, - 0x082b081919082b08, 0x082b0819192b1919, 0x082b082b08080808, - 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08, - 0x082b190808080819, 0x082b190808081908, 0x082b190808190808, - 0x082b1908082b2b19, 0x082b190819080808, 0x082b191908080808, - 0x082b191919080819, 0x082b19191919082b, 0x082b19192b192b19, - 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b, - 0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, - 0x082b2b08082b0808, 0x082b2b0819191919, 0x082b2b082b082b08, - 0x082b2b082b2b082b, 0x082b2b19192b2b08, 0x082b2b192b190808, - 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b, - 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, - 0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, - 0x1908080808190808, 0x190808080819082b, 0x1908080808191919, - 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908, - 0x1908080819080808, 0x190808081908082b, 0x1908080819081919, - 0x1908080819082b08, 0x1908080819082b2b, 0x1908080819190819, - 0x1908080819191908, 0x19080808192b0808, 0x19080808192b1919, - 0x190808082b080819, 0x190808082b081908, 0x190808082b190808, - 0x1908081908080808, 0x190808190808082b, 0x1908081908081919, - 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908, - 0x19080819082b0808, 0x1908081919080819, 0x1908081919081908, - 0x1908081919190808, 0x190808192b080808, 0x190808192b081919, - 0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, - 0x1908082b08190808, 0x1908082b0819082b, 0x1908082b082b2b19, - 0x1908082b19080808, 0x1908190808080808, 0x190819080808082b, - 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819, - 0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, - 0x1908190819080819, 0x1908190819081908, 0x1908190819190808, - 0x190819082b080808, 0x190819082b191908, 0x1908191908080819, - 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908, - 0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, - 0x1908192b08082b2b, 0x1908192b19081908, 0x1908192b19190808, - 0x19082b0808080819, 0x19082b0808081908, 0x19082b0808190808, - 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908, - 0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, - 0x19082b1919081908, 0x19082b1919190808, 0x19082b19192b2b19, - 0x19082b2b08081908, 0x1919080808080808, 0x191908080808082b, - 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, - 0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, - 0x1919080819080819, 0x1919080819081908, 0x1919080819190808, - 0x191908082b080808, 0x1919081908080819, 0x1919081908081908, - 0x1919081908190808, 0x1919081908191919, 0x1919081919080808, - 0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, - 0x1919082b2b2b2b2b, 0x1919190808080819, 0x1919190808081908, - 0x1919190808190808, 0x19191908082b0819, 0x1919190819080808, - 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819, - 0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, - 0x191919192b082b08, 0x1919192b082b0819, 0x1919192b192b2b08, - 0x1919192b2b2b0819, 0x19192b0808080808, 0x19192b0808191908, - 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19, - 0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, - 0x19192b2b2b081919, 0x192b080808080819, 0x192b080808081908, - 0x192b080808190808, 0x192b080819080808, 0x192b080819191908, - 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19, - 0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, - 0x192b082b2b19082b, 0x192b190808080808, 0x192b19080819192b, - 0x192b191908190808, 0x192b191919080808, 0x192b191919081919, - 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b, - 0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, - 0x192b2b2b192b082b, 0x2b08080808080808, 0x2b0808080808082b, - 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819, - 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b, - 0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, - 0x2b0808082b080808, 0x2b0808082b08082b, 0x2b0808082b2b2b08, - 0x2b0808082b2b2b2b, 0x2b08081908080819, 0x2b08081908081908, - 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808, - 0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, - 0x2b08082b082b0808, 0x2b08082b2b080808, 0x2b08082b2b08082b, - 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08, 0x2b08190808080819, - 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b, - 0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, - 0x2b0819082b082b19, 0x2b08191908080808, 0x2b08191919081908, - 0x2b0819192b2b1919, 0x2b08192b08192b08, 0x2b08192b192b2b2b, - 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919, - 0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, - 0x2b082b082b2b2b08, 0x2b082b190808192b, 0x2b082b2b082b082b, - 0x2b082b2b2b080808, 0x2b082b2b2b082b08, 0x2b082b2b2b19192b, - 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908, - 0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, - 0x2b1908082b081908, 0x2b19081908080808, 0x2b190819082b082b, - 0x2b190819192b1908, 0x2b19082b1919192b, 0x2b19082b2b082b19, - 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908, - 0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, - 0x2b1919192b190808, 0x2b1919192b19082b, 0x2b19192b19080819, - 0x2b192b0819190819, 0x2b192b082b2b192b, 0x2b192b1919082b19, - 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808, - 0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, - 0x2b2b0808082b0808, 0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, - 0x2b2b081919190819, 0x2b2b081919192b19, 0x2b2b08192b2b192b, - 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08, - 0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, - 0x2b2b190819080808, 0x2b2b19082b191919, 0x2b2b192b192b1919, - 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b, 0x2b2b2b08082b0808, - 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808, - 0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, - 0x2b2b2b192b08192b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, - 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b, - }); - -static dpct::global_memory iq3xxs_grid( - sycl::range<1>(256), - { - 0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, - 0x04041404, 0x04041414, 0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, - 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14, 0x040c140c, 0x040c142c, - 0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404, - 0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c, - 0x04141c1c, 0x04141c3e, 0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c, - 0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c, 0x041c3e04, 0x04240c1c, - 0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c, - 0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04, - 0x043e0c24, 0x043e0c34, 0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c, - 0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c, 0x0c041c04, 0x0c041c14, - 0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c, - 0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14, - 0x0c14140c, 0x0c141c04, 0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404, - 0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c, 0x0c24042c, 0x0c242c04, - 0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414, - 0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404, - 0x14041414, 0x14041434, 0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c, - 0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c, 0x140c1c04, 0x140c341c, - 0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e, - 0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c, - 0x141c0c04, 0x141c0c24, 0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c, - 0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24, 0x143e040c, 0x143e041c, - 0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c, - 0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414, - 0x1c0c1404, 0x1c0c1c0c, 0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c, - 0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14, 0x1c1c0c0c, 0x1c1c1c1c, - 0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414, - 0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404, - 0x24040424, 0x24040c3e, 0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e, - 0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404, 0x24143404, 0x24143434, - 0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c, - 0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04, - 0x2c040c14, 0x2c04240c, 0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434, - 0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14, 0x2c1c0414, 0x2c1c2c1c, - 0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c, - 0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434, - 0x34043424, 0x340c140c, 0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04, - 0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14, 0x34341c1c, 0x343e041c, - 0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14, - 0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14, - 0x3e1c0404, 0x3e1c0c2c, 0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c, - 0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04, - }); - -static dpct::global_memory ksigns_iq2xs( - sycl::range<1>(128), - { - 0, 129, 130, 3, 132, 5, 6, 135, 136, 9, 10, 139, 12, - 141, 142, 15, 144, 17, 18, 147, 20, 149, 150, 23, 24, 153, - 154, 27, 156, 29, 30, 159, 160, 33, 34, 163, 36, 165, 166, - 39, 40, 169, 170, 43, 172, 45, 46, 175, 48, 177, 178, 51, - 180, 53, 54, 183, 184, 57, 58, 187, 60, 189, 190, 63, 192, - 65, 66, 195, 68, 197, 198, 71, 72, 201, 202, 75, 204, 77, - 78, 207, 80, 209, 210, 83, 212, 85, 86, 215, 216, 89, 90, - 219, 92, 221, 222, 95, 96, 225, 226, 99, 228, 101, 102, 231, - 232, 105, 106, 235, 108, 237, 238, 111, 240, 113, 114, 243, 116, - 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255, - }); - -static dpct::global_memory - ksigns64(sycl::range<1>(128), - { - 0x0000000000000000, 0xff000000000000ff, 0xff0000000000ff00, - 0x000000000000ffff, 0xff00000000ff0000, 0x0000000000ff00ff, - 0x0000000000ffff00, 0xff00000000ffffff, 0xff000000ff000000, - 0x00000000ff0000ff, 0x00000000ff00ff00, 0xff000000ff00ffff, - 0x00000000ffff0000, 0xff000000ffff00ff, 0xff000000ffffff00, - 0x00000000ffffffff, 0xff0000ff00000000, 0x000000ff000000ff, - 0x000000ff0000ff00, 0xff0000ff0000ffff, 0x000000ff00ff0000, - 0xff0000ff00ff00ff, 0xff0000ff00ffff00, 0x000000ff00ffffff, - 0x000000ffff000000, 0xff0000ffff0000ff, 0xff0000ffff00ff00, - 0x000000ffff00ffff, 0xff0000ffffff0000, 0x000000ffffff00ff, - 0x000000ffffffff00, 0xff0000ffffffffff, 0xff00ff0000000000, - 0x0000ff00000000ff, 0x0000ff000000ff00, 0xff00ff000000ffff, - 0x0000ff0000ff0000, 0xff00ff0000ff00ff, 0xff00ff0000ffff00, - 0x0000ff0000ffffff, 0x0000ff00ff000000, 0xff00ff00ff0000ff, - 0xff00ff00ff00ff00, 0x0000ff00ff00ffff, 0xff00ff00ffff0000, - 0x0000ff00ffff00ff, 0x0000ff00ffffff00, 0xff00ff00ffffffff, - 0x0000ffff00000000, 0xff00ffff000000ff, 0xff00ffff0000ff00, - 0x0000ffff0000ffff, 0xff00ffff00ff0000, 0x0000ffff00ff00ff, - 0x0000ffff00ffff00, 0xff00ffff00ffffff, 0xff00ffffff000000, - 0x0000ffffff0000ff, 0x0000ffffff00ff00, 0xff00ffffff00ffff, - 0x0000ffffffff0000, 0xff00ffffffff00ff, 0xff00ffffffffff00, - 0x0000ffffffffffff, 0xffff000000000000, 0x00ff0000000000ff, - 0x00ff00000000ff00, 0xffff00000000ffff, 0x00ff000000ff0000, - 0xffff000000ff00ff, 0xffff000000ffff00, 0x00ff000000ffffff, - 0x00ff0000ff000000, 0xffff0000ff0000ff, 0xffff0000ff00ff00, - 0x00ff0000ff00ffff, 0xffff0000ffff0000, 0x00ff0000ffff00ff, - 0x00ff0000ffffff00, 0xffff0000ffffffff, 0x00ff00ff00000000, - 0xffff00ff000000ff, 0xffff00ff0000ff00, 0x00ff00ff0000ffff, - 0xffff00ff00ff0000, 0x00ff00ff00ff00ff, 0x00ff00ff00ffff00, - 0xffff00ff00ffffff, 0xffff00ffff000000, 0x00ff00ffff0000ff, - 0x00ff00ffff00ff00, 0xffff00ffff00ffff, 0x00ff00ffffff0000, - 0xffff00ffffff00ff, 0xffff00ffffffff00, 0x00ff00ffffffffff, - 0x00ffff0000000000, 0xffffff00000000ff, 0xffffff000000ff00, - 0x00ffff000000ffff, 0xffffff0000ff0000, 0x00ffff0000ff00ff, - 0x00ffff0000ffff00, 0xffffff0000ffffff, 0xffffff00ff000000, - 0x00ffff00ff0000ff, 0x00ffff00ff00ff00, 0xffffff00ff00ffff, - 0x00ffff00ffff0000, 0xffffff00ffff00ff, 0xffffff00ffffff00, - 0x00ffff00ffffffff, 0xffffffff00000000, 0x00ffffff000000ff, - 0x00ffffff0000ff00, 0xffffffff0000ffff, 0x00ffffff00ff0000, - 0xffffffff00ff00ff, 0xffffffff00ffff00, 0x00ffffff00ffffff, - 0x00ffffffff000000, 0xffffffffff0000ff, 0xffffffffff00ff00, - 0x00ffffffff00ffff, 0xffffffffffff0000, 0x00ffffffffff00ff, - 0x00ffffffffffff00, 0xffffffffffffffff, - }); -//#endif - -static dpct::global_memory - kmask_iq2xs(sycl::range<1>(8), {1, 2, 4, 8, 16, 32, 64, 128}); - template static void dequantize_block_iq2_xxs(const void * __restrict__ vx, dst_t * __restrict__ yy, const sycl::nd_item<3> &item_ct1, @@ -5213,6 +4673,65 @@ static void dequantize_block_iq3_xxs(const void * __restrict__ vx, dst_t * __res } +template +static void dequantize_block_iq3_s(const void * __restrict__ vx, dst_t * __restrict__ yy, + const sycl::nd_item<3> &item_ct1, + const uint32_t *iq3s_grid, + const uint8_t *ksigns_iq2xs, + const uint8_t *kmask_iq2xs) { + + const int i = item_ct1.get_group(2); + const block_iq3_s * x = (const block_iq3_s *) vx; + + const int tid = item_ct1.get_local_id(2); +#if QK_K == 256 + const int il = tid/8; // 0...3 + const int ib = tid%8; // 0...7 + dst_t * y = yy + i*QK_K + 32*ib + 8*il; + const uint8_t * qs = x[i].qs + 8*ib; + const uint8_t * grid1 = (const uint8_t *)(iq3s_grid + qs[2*il+0]); + const uint8_t * grid2 = (const uint8_t *)(iq3s_grid + qs[2*il+1]); + const float d = (float)x[i].d * (1 + 2*((x[i].scales[ib/2] >> 4*(ib%2)) & 0xf)); + const uint8_t signs = x[i].signs[4*ib + il]; + for (int j = 0; j < 4; ++j) { + y[j+0] = d * grid1[j] * (signs & kmask_iq2xs[j+0] ? -1.f : 1.f); + y[j+4] = d * grid2[j] * (signs & kmask_iq2xs[j+4] ? -1.f : 1.f); + } +#else + assert(false); +#endif + +} + +template +static void dequantize_block_iq1_s(const void * __restrict__ vx, dst_t * __restrict__ yy, + const sycl::nd_item<3> &item_ct1, + const uint32_t *iq1s_grid, + const uint8_t *ksigns_iq2xs, + const uint8_t *kmask_iq2xs) { + const int i = item_ct1.get_group(2); + const block_iq1_s * x = (const block_iq1_s *) vx; + + const int tid = item_ct1.get_local_id(2); +#if QK_K == 256 + const int il = tid/8; // 0...3 + const int ib = tid%8; // 0...7 + dst_t * y = yy + i*QK_K + 32*ib + 8*il; + const uint8_t * qs = x[i].qs + 8*ib; + const uint8_t * grid1 = (const uint8_t *)(iq1s_grid + qs[2*il+0]); + const uint8_t * grid2 = (const uint8_t *)(iq1s_grid + qs[2*il+1]); + const float d = (float)x[i].d * (2*((x[i].qh[ib] >> 12) & 0xf) + 1); + const uint8_t signs = ksigns_iq2xs[(x[i].qh[ib] >> 3*il) & 7]; + for (int j = 0; j < 4; ++j) { + y[j+0] = d * grid1[j] * (signs & kmask_iq2xs[j+0] ? -1.f : 1.f); + y[j+4] = d * grid2[j] * (signs & kmask_iq2xs[j+4] ? -1.f : 1.f); + } +#else + assert(false); +#endif + +} + /* DPCT1110:4: The total declared local variable size in device function dequantize_mul_mat_vec_q2_k exceeds 128 bytes and may cause high register @@ -8059,6 +7578,75 @@ vec_dot_iq3_xxs_q8_1(const void *__restrict__ vbq, #endif } +static __dpct_inline__ float +vec_dot_iq3_s_q8_1(const void *__restrict__ vbq, + const block_q8_1 *__restrict__ bq8_1, const int &iqs, + const uint32_t *iq3s_grid, const uint64_t *ksigns64) { +#if DPCT_COMPATIBILITY_TEMP >= \ + MIN_CC_DP4A // lowest compute capability for integer intrinsics +#if QK_K == 256 + const block_iq3_s * bq2 = (const block_iq3_s *) vbq; + + const int ib32 = iqs; + const uint8_t * qs = bq2->qs + 8*ib32; + const int8_t * q8 = bq8_1[ib32].qs; + int sumi = 0; + for (int l = 0; l < 4; ++l) { + const uint32_t * grid1 = iq3s_grid + (qs[2*l+0] | ((bq2->qh[ib32] << (8 - 2*l)) & 256)); + const uint32_t * grid2 = iq3s_grid + (qs[2*l+1] | ((bq2->qh[ib32] << (7 - 2*l)) & 256)); + uint32_t signs0 = dpct::vectorized_binary( + ((bq2->signs[4*ib32+l] & 0xf) * 0x01010101) & 0x08040201, 0x08040201, std::equal_to<>()); + uint32_t signs1 = dpct::vectorized_binary( + ((bq2->signs[4*ib32+l] >> 4) * 0x01010101) & 0x08040201, 0x08040201, std::equal_to<>()); + const int grid_l = dpct::vectorized_binary( + grid1[0] ^ signs0, signs0, std::minus<>()); + const int grid_h = dpct::vectorized_binary( + grid2[0] ^ signs1, signs1, std::minus<>()); + sumi = dpct::dp4a(grid_l, *((int *)q8 + 0), sumi); + sumi = dpct::dp4a(grid_h, *((int *)q8 + 1), sumi); + q8 += 8; + } + const float d = (float)bq2->d * (1 + 2*((bq2->scales[ib32/2] >> 4*(ib32%2)) & 0xf)) * bq8_1[ib32].ds[0]; + return d * sumi; +#else + assert(false); + return 0.f; +#endif +#else + assert(false); + return 0.f; +#endif +} + +static __dpct_inline__ float +vec_dot_iq1_s_q8_1(const void *__restrict__ vbq, + const block_q8_1 *__restrict__ bq8_1, const int &iqs, + const uint32_t *iq1s_grid, const uint64_t *ksigns64) { +#if QK_K == 256 + const block_iq1_s * bq1 = (const block_iq1_s *) vbq; + + const int ib32 = iqs; + const uint8_t * qs = bq1->qs + 4*ib32; + const int8_t * q8 = bq8_1[ib32].qs; + int sumi = 0; + for (int l = 0; l < 4; ++l) { + const uint32_t * grid = (const uint32_t *)(iq1s_grid + qs[l]); + const uint32_t * signs = (const uint32_t *)(ksigns64 + (qs[l] >> 8)); + const int grid_l = dpct::vectorized_binary( + grid[0] ^ signs[0], signs[0], std::minus<>()); + const int grid_h = dpct::vectorized_binary( + grid[1] ^ signs[1], signs[1], std::minus<>()); + sumi = dpct::dp4a(grid_l, *((int *)q8 + 0), sumi); + sumi = dpct::dp4a(grid_h, *((int *)q8 + 1), sumi); + q8 += 8; + } + const float d = (float)bq1->d * bq8_1[ib32].ds[0] * 0.25f; + return d * sumi; +#else + assert(false); + return 0.f; +#endif +} template +static void mul_mat_vec_q_iq3_s_q8_1(const void * __restrict__ vx, const void * __restrict__ vy, float * __restrict__ dst, const int ncols, const int nrows, + const sycl::nd_item<3> &item_ct1, + const uint32_t *iq3s_grid_ptr, const uint64_t *ksigns64_ptr ) { + const int row = item_ct1.get_group(2) * item_ct1.get_local_range(1) + + item_ct1.get_local_id(1); + + if (row >= nrows) { + return; + } + + const int blocks_per_row = ncols / qk; + const int blocks_per_warp = vdr * WARP_SIZE / qi; + +// partial sum for each thread + float tmp = 0.0f; + + const block_q_t * x = (const block_q_t *) vx; + const block_q8_1 * y = (const block_q8_1 *) vy; + + for (int i = item_ct1.get_local_id(2) / (qi / vdr); i < blocks_per_row; + i += blocks_per_warp) { + const int ibx = row*blocks_per_row + i; // x block index + + const int iby = i * (qk/QK8_1); // y block index that aligns with ibx + + const int iqs = + vdr * + (item_ct1.get_local_id(2) % + (qi / vdr)); // x block quant index when casting the quants to int + + tmp += vec_dot_iq3_s_q8_1(&x[ibx], &y[iby], iqs, iq3s_grid_ptr, ksigns64_ptr); + } + + // sum up partial sums and write back result +#pragma unroll + for (int mask = 16; mask > 0; mask >>= 1) { + tmp += + dpct::permute_sub_group_by_xor(item_ct1.get_sub_group(), tmp, mask); + } + + if (item_ct1.get_local_id(2) == 0) { + dst[row] = tmp; + } +} + +template +static void mul_mat_vec_q_iq1_s_q8_1(const void * __restrict__ vx, const void * __restrict__ vy, float * __restrict__ dst, const int ncols, const int nrows, + const sycl::nd_item<3> &item_ct1, + const uint32_t *iq1s_grid_ptr, const uint64_t *ksigns64_ptr ) { + const int row = item_ct1.get_group(2) * item_ct1.get_local_range(1) + + item_ct1.get_local_id(1); + + if (row >= nrows) { + return; + } + + const int blocks_per_row = ncols / qk; + const int blocks_per_warp = vdr * WARP_SIZE / qi; + +// partial sum for each thread + float tmp = 0.0f; + + const block_q_t * x = (const block_q_t *) vx; + const block_q8_1 * y = (const block_q8_1 *) vy; + + for (int i = item_ct1.get_local_id(2) / (qi / vdr); i < blocks_per_row; + i += blocks_per_warp) { + const int ibx = row*blocks_per_row + i; // x block index + + const int iby = i * (qk/QK8_1); // y block index that aligns with ibx + + const int iqs = + vdr * + (item_ct1.get_local_id(2) % + (qi / vdr)); // x block quant index when casting the quants to int + + tmp += vec_dot_iq1_s_q8_1(&x[ibx], &y[iby], iqs, iq1s_grid_ptr, ksigns64_ptr); + } + + // sum up partial sums and write back result +#pragma unroll + for (int mask = 16; mask > 0; mask >>= 1) { + tmp += + dpct::permute_sub_group_by_xor(item_ct1.get_sub_group(), tmp, mask); + } + + if (item_ct1.get_local_id(2) == 0) { + dst[row] = tmp; + } +} + template static void dequantize_mul_mat_vec(const void * __restrict__ vx, const dfloat * __restrict__ y, float * __restrict__ dst, const int ncols, const int nrows, const sycl::nd_item<3> &item_ct1) { @@ -10509,6 +10189,64 @@ static void dequantize_row_iq3_xxs_sycl(const void *vx, dst_t *y, const int k, } } +template +static void dequantize_row_iq3_s_sycl(const void *vx, dst_t *y, const int k, + dpct::queue_ptr stream) { + const int nb = k / QK_K; + { + iq3s_grid.init(*stream); + ksigns_iq2xs.init(*stream); + kmask_iq2xs.init(*stream); + + dpct::has_capability_or_fail(stream->get_device(), + {sycl::aspect::fp16}); + + stream->submit([&](sycl::handler &cgh) { + auto iq3s_grid_ptr_ct1 = iq3s_grid.get_ptr(); + auto ksigns_iq2xs_ptr_ct1 = ksigns_iq2xs.get_ptr(); + auto kmask_iq2xs_ptr_ct1 = kmask_iq2xs.get_ptr(); + + cgh.parallel_for(sycl::nd_range<3>(sycl::range<3>(1, 1, nb) * + sycl::range<3>(1, 1, 32), + sycl::range<3>(1, 1, 32)), + [=](sycl::nd_item<3> item_ct1) { + dequantize_block_iq3_s( + vx, y, item_ct1, iq3s_grid_ptr_ct1, + ksigns_iq2xs_ptr_ct1, kmask_iq2xs_ptr_ct1); + }); + }); + } +} + +template +static void dequantize_row_iq1_s_sycl(const void *vx, dst_t *y, const int k, + dpct::queue_ptr stream) { + const int nb = k / QK_K; + { + iq1s_grid_gpu.init(*stream); + ksigns_iq2xs.init(*stream); + kmask_iq2xs.init(*stream); + + dpct::has_capability_or_fail(stream->get_device(), + {sycl::aspect::fp16}); + + stream->submit([&](sycl::handler &cgh) { + auto iq1s_grid_ptr_ct1 = iq1s_grid_gpu.get_ptr(); + auto ksigns_iq2xs_ptr_ct1 = ksigns_iq2xs.get_ptr(); + auto kmask_iq2xs_ptr_ct1 = kmask_iq2xs.get_ptr(); + + cgh.parallel_for(sycl::nd_range<3>(sycl::range<3>(1, 1, nb) * + sycl::range<3>(1, 1, 32), + sycl::range<3>(1, 1, 32)), + [=](sycl::nd_item<3> item_ct1) { + dequantize_block_iq1_s( + vx, y, item_ct1, iq1s_grid_ptr_ct1, + ksigns_iq2xs_ptr_ct1, kmask_iq2xs_ptr_ct1); + }); + }); + } +} + template static void convert_unary_sycl(const void *__restrict__ vx, dst_t *__restrict__ y, const int k, @@ -10559,6 +10297,10 @@ static to_fp16_sycl_t ggml_get_to_fp16_sycl(ggml_type type) try { return dequantize_row_iq2_xs_sycl; case GGML_TYPE_IQ3_XXS: return dequantize_row_iq3_xxs_sycl; + case GGML_TYPE_IQ3_S: + return dequantize_row_iq3_s_sycl; + case GGML_TYPE_IQ1_S: + return dequantize_row_iq1_s_sycl; case GGML_TYPE_F32: return convert_unary_sycl; default: @@ -10599,6 +10341,10 @@ static to_fp32_sycl_t ggml_get_to_fp32_sycl(ggml_type type) { return dequantize_row_iq2_xs_sycl; case GGML_TYPE_IQ3_XXS: return dequantize_row_iq3_xxs_sycl; + case GGML_TYPE_IQ3_S: + return dequantize_row_iq3_s_sycl; + case GGML_TYPE_IQ1_S: + return dequantize_row_iq1_s_sycl; case GGML_TYPE_F16: return convert_unary_sycl; default: @@ -11188,6 +10934,61 @@ static void mul_mat_vec_iq3_xxs_q8_1_sycl(const void *vx, const void *vy, } } +static void mul_mat_vec_iq3_s_q8_1_sycl(const void *vx, const void *vy, + float *dst, const int ncols, + const int nrows, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK_K == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + { + iq3s_grid.init(*stream); + ksigns64.init(*stream); + + stream->submit([&](sycl::handler &cgh) { + auto iq3s_grid_ptr_ct1 = iq3s_grid.get_ptr(); + auto ksigns64_ptr_ct1 = ksigns64.get_ptr(); + + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) + [[intel::reqd_sub_group_size(32)]] { + mul_mat_vec_q_iq3_s_q8_1( + vx, vy, dst, ncols, nrows, item_ct1, + iq3s_grid_ptr_ct1, ksigns64_ptr_ct1); + }); + }); + } +} + +static void mul_mat_vec_iq1_s_q8_1_sycl(const void *vx, const void *vy, + float *dst, const int ncols, + const int nrows, + dpct::queue_ptr stream) { + GGML_ASSERT(ncols % QK_K == 0); + const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y; + const sycl::range<3> block_nums(1, 1, block_num_y); + const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE); + { + iq1s_grid_gpu.init(*stream); + ksigns64.init(*stream); + + stream->submit([&](sycl::handler &cgh) { + auto iq1s_grid_ptr_ct1 = iq1s_grid_gpu.get_ptr(); + auto ksigns64_ptr_ct1 = ksigns64.get_ptr(); + + cgh.parallel_for( + sycl::nd_range<3>(block_nums * block_dims, block_dims), + [=](sycl::nd_item<3> item_ct1) + [[intel::reqd_sub_group_size(32)]] { + mul_mat_vec_q_iq1_s_q8_1( + vx, vy, dst, ncols, nrows, item_ct1, + iq1s_grid_ptr_ct1, ksigns64_ptr_ct1); + }); + }); + } +} static void ggml_mul_mat_q4_0_q8_1_sycl(const void *vx, const void *vy, float *dst, const int ncols_x, @@ -13936,8 +13737,11 @@ static int64_t get_row_rounding(ggml_type type, const std::array= VER_GEN9 ? 128 : 64; + case GGML_TYPE_IQ3_S: + return max_compute_capability >= VER_GEN9 ? 128 : 64; case GGML_TYPE_Q6_K: return 64; default: @@ -13998,6 +13802,12 @@ inline void ggml_sycl_op_mul_mat_vec_q( case GGML_TYPE_IQ3_XXS: mul_mat_vec_iq3_xxs_q8_1_sycl(src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, stream); break; + case GGML_TYPE_IQ3_S: + mul_mat_vec_iq3_s_q8_1_sycl(src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, stream); + break; + case GGML_TYPE_IQ1_S: + mul_mat_vec_iq1_s_q8_1_sycl(src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, stream); + break; default: GGML_ASSERT(false); break; @@ -17343,9 +17153,8 @@ GGML_CALL static bool ggml_backend_sycl_supports_op(ggml_backend_t backend, cons return false; } ggml_type a_type = a->type; - if (a_type == GGML_TYPE_IQ2_XXS || a_type == GGML_TYPE_IQ2_XS || a_type == GGML_TYPE_IQ3_XXS || - a_type == GGML_TYPE_IQ1_S || a_type == GGML_TYPE_IQ4_NL || a_type == GGML_TYPE_IQ3_S || - a_type == GGML_TYPE_IQ2_S || a_type == GGML_TYPE_IQ4_XS) { + if (a_type == GGML_TYPE_IQ4_NL || a_type == GGML_TYPE_IQ2_S || + a_type == GGML_TYPE_IQ4_XS) { return false; } return true; @@ -17440,13 +17249,18 @@ static ggml_backend_i ggml_backend_sycl_interface = { /* .get_default_buffer_type = */ ggml_backend_sycl_get_default_buffer_type, /* .set_tensor_async = */ ggml_backend_sycl_set_tensor_async, /* .get_tensor_async = */ ggml_backend_sycl_get_tensor_async, - /* .cpy_tensor_async = */ ggml_backend_sycl_cpy_tensor_async, + /* .cpy_tensor_async = */ NULL, //ggml_backend_sycl_cpy_tensor_async, // TODO: update for the new interface /* .synchronize = */ ggml_backend_sycl_synchronize, /* .graph_plan_create = */ NULL, /* .graph_plan_free = */ NULL, /* .graph_plan_compute = */ NULL, /* .graph_compute = */ ggml_backend_sycl_graph_compute, /* .supports_op = */ ggml_backend_sycl_supports_op, + /* .event_new = */ NULL, + /* .event_free = */ NULL, + /* .event_record = */ NULL, + /* .event_wait = */ NULL, + /* .event_synchronize = */ NULL, }; static ggml_guid_t ggml_backend_sycl_guid() { diff --git a/src/ggml-vulkan.cpp b/src/ggml-vulkan.cpp index 5a1b3f477..7cce616ba 100644 --- a/src/ggml-vulkan.cpp +++ b/src/ggml-vulkan.cpp @@ -4102,45 +4102,7 @@ static void ggml_vk_test_transfer(ggml_backend_vk_context * ctx, size_t ne, bool } static void ggml_vk_quantize_data(const float * from, void * to, size_t ne, ggml_type quant) { - std::vector hist_cur(1 << 4, 0); - - switch(quant) { - case GGML_TYPE_F32: - memcpy(to, from, sizeof(float) * ne); - break; - case GGML_TYPE_Q4_0: - ggml_quantize_q4_0(from, to, ne, ne, hist_cur.data()); - break; - case GGML_TYPE_Q4_1: - ggml_quantize_q4_1(from, to, ne, ne, hist_cur.data()); - break; - case GGML_TYPE_Q5_0: - ggml_quantize_q5_0(from, to, ne, ne, hist_cur.data()); - break; - case GGML_TYPE_Q5_1: - ggml_quantize_q5_1(from, to, ne, ne, hist_cur.data()); - break; - case GGML_TYPE_Q8_0: - ggml_quantize_q8_0(from, to, ne, ne, hist_cur.data()); - break; - case GGML_TYPE_Q2_K: - ggml_quantize_q2_K(from, to, ne, ne, hist_cur.data()); - break; - case GGML_TYPE_Q3_K: - ggml_quantize_q3_K(from, to, ne, ne, hist_cur.data()); - break; - case GGML_TYPE_Q4_K: - ggml_quantize_q4_K(from, to, ne, ne, hist_cur.data()); - break; - case GGML_TYPE_Q5_K: - ggml_quantize_q5_K(from, to, ne, ne, hist_cur.data()); - break; - case GGML_TYPE_Q6_K: - ggml_quantize_q6_K(from, to, ne, ne, hist_cur.data()); - break; - default: - GGML_ASSERT(false); - } + ggml_quantize_chunk(quant, from, to, 0, 1, ne, nullptr); } static void ggml_vk_test_dequant(ggml_backend_vk_context * ctx, size_t ne, ggml_type quant) { @@ -5731,6 +5693,11 @@ static ggml_backend_i ggml_backend_vk_interface = { /* .graph_plan_compute = */ NULL, /* .graph_compute = */ ggml_backend_vk_graph_compute, /* .supports_op = */ ggml_backend_vk_supports_op, + /* .event_new = */ NULL, + /* .event_free = */ NULL, + /* .event_record = */ NULL, + /* .event_wait = */ NULL, + /* .event_synchronize = */ NULL, }; static ggml_guid_t ggml_backend_vk_guid() { diff --git a/src/ggml.c b/src/ggml.c index 92b17ee6e..fbc66f65b 100644 --- a/src/ggml.c +++ b/src/ggml.c @@ -857,7 +857,7 @@ inline static float vaddvq_f32(float32x4_t v) { #define GGML_F16x8 float16x8_t #define GGML_F16x8_ZERO vdupq_n_f16(0.0f) #define GGML_F16x8_SET1(x) vdupq_n_f16(x) - #define GGML_F16x8_LOAD(x) vld1q_f16((const __fp16 *)(x)) + #define GGML_F16x8_LOAD(x) vld1q_f16((const ggml_fp16_internal_t *)(x)) #define GGML_F16x8_STORE vst1q_f16 #define GGML_F16x8_FMA(a, b, c) vfmaq_f16(a, b, c) #define GGML_F16x8_ADD vaddq_f16 @@ -900,7 +900,7 @@ inline static float vaddvq_f32(float32x4_t v) { #define GGML_F32Cx4 float32x4_t #define GGML_F32Cx4_ZERO vdupq_n_f32(0.0f) #define GGML_F32Cx4_SET1(x) vdupq_n_f32(x) - #define GGML_F32Cx4_LOAD(x) vcvt_f32_f16(vld1_f16((const __fp16 *)(x))) + #define GGML_F32Cx4_LOAD(x) vcvt_f32_f16(vld1_f16((const ggml_fp16_internal_t *)(x))) #define GGML_F32Cx4_STORE(x, y) vst1_f16(x, vcvt_f16_f32(y)) #define GGML_F32Cx4_FMA(a, b, c) vfmaq_f32(a, b, c) #define GGML_F32Cx4_ADD vaddq_f32 @@ -1841,6 +1841,8 @@ static const char * GGML_OP_NAME[GGML_OP_COUNT] = { "FLASH_ATTN", "FLASH_FF", "FLASH_ATTN_BACK", + "SSM_CONV", + "SSM_SCAN", "WIN_PART", "WIN_UNPART", "GET_REL_POS", @@ -1863,7 +1865,7 @@ static const char * GGML_OP_NAME[GGML_OP_COUNT] = { "CROSS_ENTROPY_LOSS_BACK", }; -static_assert(GGML_OP_COUNT == 74, "GGML_OP_COUNT != 74"); +static_assert(GGML_OP_COUNT == 76, "GGML_OP_COUNT != 76"); static const char * GGML_OP_SYMBOL[GGML_OP_COUNT] = { "none", @@ -1929,6 +1931,8 @@ static const char * GGML_OP_SYMBOL[GGML_OP_COUNT] = { "flash_attn(x)", "flash_ff(x)", "flash_attn_back(x)", + "ssm_conv(x)", + "ssm_scan(x)", "win_part(x)", "win_unpart(x)", "get_rel_pos(x)", @@ -1951,7 +1955,7 @@ static const char * GGML_OP_SYMBOL[GGML_OP_COUNT] = { "cross_entropy_loss_back(x,y)", }; -static_assert(GGML_OP_COUNT == 74, "GGML_OP_COUNT != 74"); +static_assert(GGML_OP_COUNT == 76, "GGML_OP_COUNT != 76"); static_assert(GGML_OP_POOL_COUNT == 2, "GGML_OP_POOL_COUNT != 2"); @@ -6154,6 +6158,108 @@ struct ggml_tensor * ggml_flash_attn_back( return result; } +// ggml_ssm_conv + +struct ggml_tensor * ggml_ssm_conv( + struct ggml_context * ctx, + struct ggml_tensor * s, + struct ggml_tensor * x, + struct ggml_tensor * c, + struct ggml_tensor * sq) { + GGML_ASSERT(ggml_is_3d(s)); + GGML_ASSERT(ggml_is_matrix(x)); + GGML_ASSERT(ggml_is_matrix(c)); + GGML_ASSERT(ggml_is_matrix(sq)); + GGML_ASSERT(sq->type == GGML_TYPE_I32); + + const int64_t d_conv = c->ne[0]; + const int64_t d_inner = c->ne[1]; + const int64_t n_tokens = x->ne[1]; + const int64_t n_kv = s->ne[2]; + + GGML_ASSERT( s->ne[0] == d_conv - 1); + GGML_ASSERT( s->ne[1] == d_inner); + GGML_ASSERT( x->ne[0] == d_inner); + GGML_ASSERT(sq->ne[0] == n_kv); + GGML_ASSERT(sq->ne[1] == n_tokens); + + bool is_node = false; + + if (s->grad || x->grad || c->grad || sq->grad) { + GGML_ASSERT(false); // TODO: implement + is_node = true; + } + + // 2-in-1 concatenated x and conv_states, {d_inner, n_tokens} with {d_conv, d_inner, n_kv} + struct ggml_tensor * result = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, (d_inner*n_tokens) + (d_conv*d_inner*n_kv)); + + result->op = GGML_OP_SSM_CONV; + result->grad = is_node ? ggml_dup_tensor(ctx, result) : NULL; + result->src[0] = s; + result->src[1] = x; + result->src[2] = c; + result->src[3] = sq; + + return result; +} + +// ggml_ssm_scan + +struct ggml_tensor * ggml_ssm_scan( + struct ggml_context * ctx, + struct ggml_tensor * s, + struct ggml_tensor * x, + struct ggml_tensor * dt, + struct ggml_tensor * A, + struct ggml_tensor * B, + struct ggml_tensor * C, + struct ggml_tensor * sq) { + GGML_ASSERT(ggml_is_contiguous(s)); + GGML_ASSERT(ggml_is_contiguous(x)); + GGML_ASSERT(ggml_is_contiguous(dt)); + GGML_ASSERT(ggml_is_contiguous(A)); + GGML_ASSERT(sq->type == GGML_TYPE_I32); + GGML_ASSERT(B->nb[0] == ggml_type_size(B->type)); + GGML_ASSERT(C->nb[0] == ggml_type_size(C->type)); + GGML_ASSERT(ggml_are_same_shape(x, dt)); + + { + const int64_t d_state = s->ne[0]; + const int64_t d_inner = s->ne[1]; + const int64_t n_tokens = x->ne[1]; + + GGML_ASSERT(x->ne[0] == d_inner); + GGML_ASSERT(A->ne[0] == d_state); + GGML_ASSERT(A->ne[1] == d_inner); + GGML_ASSERT(B->ne[0] == d_state); + GGML_ASSERT(B->ne[1] == n_tokens); + GGML_ASSERT(C->ne[0] == d_state); + GGML_ASSERT(C->ne[1] == n_tokens); + } + + bool is_node = false; + + if (s->grad || x->grad || dt->grad || A->grad || B->grad || C->grad || sq->grad) { + GGML_ASSERT(false); // TODO: implement + is_node = true; + } + + // 2-in-1 concatenated y and ssm_states, {d_inner, n_tokens} with {d_state, d_inner, n_kv} + struct ggml_tensor * result = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, ggml_nelements(x) + ggml_nelements(s)); + + result->op = GGML_OP_SSM_SCAN; + result->grad = is_node ? ggml_dup_tensor(ctx, result) : NULL; + result->src[0] = s; + result->src[1] = x; + result->src[2] = dt; + result->src[3] = A; + result->src[4] = B; + result->src[5] = C; + result->src[6] = sq; + + return result; +} + // ggml_win_part struct ggml_tensor * ggml_win_part( @@ -11454,8 +11560,6 @@ static void ggml_compute_forward_get_rows_q( const struct ggml_tensor * src0 = dst->src[0]; const struct ggml_tensor * src1 = dst->src[1]; - assert(params->ith == 0); - if (params->type == GGML_TASK_TYPE_INIT || params->type == GGML_TASK_TYPE_FINALIZE) { return; } @@ -11463,7 +11567,7 @@ static void ggml_compute_forward_get_rows_q( GGML_TENSOR_BINARY_OP_LOCALS const int64_t nc = ne00; - const int64_t nr = ggml_nelements(src1); GGML_UNUSED(nr); + const int64_t nr = ggml_nelements(src1); const enum ggml_type type = src0->type; ggml_to_float_t const dequantize_row_q = type_traits[type].to_float; @@ -11473,17 +11577,25 @@ static void ggml_compute_forward_get_rows_q( assert(nb00 == ggml_type_size(type)); assert(ggml_nrows(dst) == nr); - // TODO: multi-thread - for (int64_t i12 = 0; i12 < ne12; ++i12) { - for (int64_t i11 = 0; i11 < ne11; ++i11) { - for (int64_t i10 = 0; i10 < ne10; ++i10) { - const int64_t i01 = *(int32_t *) ((char *) src1->data + i10*nb10 + i11*nb11 + i12*nb12); + const int ith = params->ith; + const int nth = params->nth; + + // rows per thread + const int dr = (nr + nth - 1)/nth; - dequantize_row_q( - (const void *) ((char *) src0->data + i01*nb01 + i11*nb02 + i12*nb03), - (float *) ((char *) dst->data + i10*nb1 + i11*nb2 + i12*nb3), nc); - } - } + // row range for this thread + const int ir0 = dr*ith; + const int ir1 = MIN(ir0 + dr, nr); + + for (int64_t i = ir0; i < ir1; ++i) { + const int64_t i12 = i/(ne11*ne10); + const int64_t i11 = (i - i12*ne11*ne10)/ne10; + const int64_t i10 = (i - i12*ne11*ne10 - i11*ne10); + const int64_t i01 = *(int32_t *) ((char *) src1->data + i10*nb10 + i11*nb11 + i12*nb12); + + dequantize_row_q( + (const void *) ((char *) src0->data + i01*nb01 + i11*nb02 + i12*nb03), + (float *) ((char *) dst->data + i10*nb1 + i11*nb2 + i12*nb3), nc); } } @@ -11494,8 +11606,6 @@ static void ggml_compute_forward_get_rows_f16( const struct ggml_tensor * src0 = dst->src[0]; const struct ggml_tensor * src1 = dst->src[1]; - assert(params->ith == 0); - if (params->type == GGML_TASK_TYPE_INIT || params->type == GGML_TASK_TYPE_FINALIZE) { return; } @@ -11503,24 +11613,32 @@ static void ggml_compute_forward_get_rows_f16( GGML_TENSOR_BINARY_OP_LOCALS const int64_t nc = ne00; - const int64_t nr = ggml_nelements(src1); GGML_UNUSED(nr); + const int64_t nr = ggml_nelements(src1); assert(ne0 == nc); assert(ne02 == ne11); assert(nb00 == sizeof(ggml_fp16_t)); assert(ggml_nrows(dst) == nr); - // TODO: multi-thread - for (int64_t i12 = 0; i12 < ne12; ++i12) { - for (int64_t i11 = 0; i11 < ne11; ++i11) { - for (int64_t i10 = 0; i10 < ne10; ++i10) { - const int64_t i01 = *(int32_t *) ((char *) src1->data + i10*nb10 + i11*nb11 + i12*nb12); + const int ith = params->ith; + const int nth = params->nth; - ggml_fp16_to_fp32_row( - (const void *) ((char *) src0->data + i01*nb01 + i11*nb02 + i12*nb03), - (float *) ((char *) dst->data + i10*nb1 + i11*nb2 + i12*nb3), nc); - } - } + // rows per thread + const int dr = (nr + nth - 1)/nth; + + // row range for this thread + const int ir0 = dr*ith; + const int ir1 = MIN(ir0 + dr, nr); + + for (int64_t i = ir0; i < ir1; ++i) { + const int64_t i12 = i/(ne11*ne10); + const int64_t i11 = (i - i12*ne11*ne10)/ne10; + const int64_t i10 = (i - i12*ne11*ne10 - i11*ne10); + const int64_t i01 = *(int32_t *) ((char *) src1->data + i10*nb10 + i11*nb11 + i12*nb12); + + ggml_fp16_to_fp32_row( + (const void *) ((char *) src0->data + i01*nb01 + i11*nb02 + i12*nb03), + (float *) ((char *) dst->data + i10*nb1 + i11*nb2 + i12*nb3), nc); } } @@ -11531,8 +11649,6 @@ static void ggml_compute_forward_get_rows_f32( const struct ggml_tensor * src0 = dst->src[0]; const struct ggml_tensor * src1 = dst->src[1]; - assert(params->ith == 0); - if (params->type == GGML_TASK_TYPE_INIT || params->type == GGML_TASK_TYPE_FINALIZE) { return; } @@ -11540,24 +11656,32 @@ static void ggml_compute_forward_get_rows_f32( GGML_TENSOR_BINARY_OP_LOCALS const int64_t nc = ne00; - const int64_t nr = ggml_nelements(src1); GGML_UNUSED(nr); + const int64_t nr = ggml_nelements(src1); assert(ne0 == nc); assert(ne02 == ne11); assert(nb00 == sizeof(float)); assert(ggml_nrows(dst) == nr); - // TODO: multi-thread - for (int64_t i12 = 0; i12 < ne12; ++i12) { - for (int64_t i11 = 0; i11 < ne11; ++i11) { - for (int64_t i10 = 0; i10 < ne10; ++i10) { - const int64_t i01 = *(int32_t *) ((char *) src1->data + i10*nb10 + i11*nb11 + i12*nb12); + const int ith = params->ith; + const int nth = params->nth; - ggml_vec_cpy_f32(nc, - (float *) ((char *) dst->data + i10*nb1 + i11*nb2 + i12*nb3), - (float *) ((char *) src0->data + i01*nb01 + i11*nb02 + i12*nb03)); - } - } + // rows per thread + const int dr = (nr + nth - 1)/nth; + + // row range for this thread + const int ir0 = dr*ith; + const int ir1 = MIN(ir0 + dr, nr); + + for (int64_t i = ir0; i < ir1; ++i) { + const int64_t i12 = i/(ne11*ne10); + const int64_t i11 = (i - i12*ne11*ne10)/ne10; + const int64_t i10 = (i - i12*ne11*ne10 - i11*ne10); + const int64_t i01 = *(int32_t *) ((char *) src1->data + i10*nb10 + i11*nb11 + i12*nb12); + + ggml_vec_cpy_f32(nc, + (float *) ((char *) dst->data + i10*nb1 + i11*nb2 + i12*nb3), + (float *) ((char *) src0->data + i01*nb01 + i11*nb02 + i12*nb03)); } } @@ -14771,6 +14895,257 @@ static void ggml_compute_forward_flash_attn_back( } } +// ggml_compute_forward_ssm_conv + +static void ggml_compute_forward_ssm_conv_f32( + const struct ggml_compute_params * params, + struct ggml_tensor * dst) { + if (params->type == GGML_TASK_TYPE_INIT || params->type == GGML_TASK_TYPE_FINALIZE) { + return; + } + + const struct ggml_tensor * src0 = dst->src[0]; // conv_state + const struct ggml_tensor * src1 = dst->src[1]; // x + const struct ggml_tensor * src2 = dst->src[2]; // conv1d.weight + const struct ggml_tensor * src3 = dst->src[3]; // state_seq + + const int ith = params->ith; + const int nth = params->nth; + + const int nc = src2->ne[0]; // d_conv + const int nr = src0->ne[1]; // d_inner + const int n_t = src1->ne[1]; // n_tokens + const int n_kv = src0->ne[2]; // max number of sequences in the batch + + GGML_ASSERT((nr*n_t) + (nc*nr*n_kv) == ggml_nelements(dst)); + GGML_ASSERT(src0->nb[0] == sizeof(float)); + GGML_ASSERT(src1->nb[0] == sizeof(float)); + GGML_ASSERT(src2->nb[0] == sizeof(float)); + GGML_ASSERT(src3->nb[0] == sizeof(int32_t)); + GGML_ASSERT(src0->nb[1] == src0->ne[0]*sizeof(float)); + // for use with the destination state offset between sequences + GGML_ASSERT(src2->nb[2] == src2->ne[1]*src2->ne[0]*sizeof(float)); + + // rows per thread + const int dr = (nr + nth - 1)/nth; + + // row range for this thread + const int ir0 = dr*ith; + const int ir1 = MIN(ir0 + dr, nr); + const int ir = ir1 - ir0; + + if (n_kv > 1) { + // multiple sequences means it's hard to know when it's the first time a state is read, + // so copy them all over to the destination, just to be sure. + for (int i3 = 0; i3 < n_kv; ++i3) { + float * s0 = (float *) ((char *) src0->data + ir0*(src0->nb[1]) + i3*(src0->nb[2])); + float * s = (float *) ((char *) dst->data + ir0*(src2->nb[1]) + i3*(src2->nb[2]) + nr*n_t*sizeof(float)); + // can't use memcpy because of d_conv vs d_conv - 1 + for (int i1 = 0; i1 < ir; ++i1) { + for (int i0 = 0; i0 < nc - 1; ++i0) { + // copy s0 to last (d_conv - 1) columns of s + s[1 + i0 + i1*nc] = s0[i0 + i1*(nc - 1)]; + } + } + } + } + + for (int i2 = 0; i2 < n_t; ++i2) { + int32_t * sq = (int32_t *) ((char *) src3->data + i2*(src3->nb[1])); // {n_kv, n_tokens} + float * x = (float *) ((char *) dst->data + ir0*sizeof(float) + i2*(nr*sizeof(float))); // {d_inner, n_tokens} + float * s = (float *) ((char *) dst->data + ir0*(src2->nb[1]) + sq[0]*(src2->nb[2]) + nr*n_t*sizeof(float)); // {d_conv, d_inner, n_kv} + float * s0; // {d_conv - 1, d_inner, n_kv} + float * x0 = (float *) ((char *) src1->data + ir0*(src1->nb[0]) + i2*(src1->nb[1])); // {d_inner, n_tokens} + float * c = (float *) ((char *) src2->data + ir0*(src2->nb[1])); // {d_conv, d_inner} + int ne0s0; + + GGML_ASSERT(0 <= sq[0] && sq[0] < n_kv); + + // avoid needing to copy the state for the first token + if (i2 == 0) { + s0 = (float *) ((char *) src0->data + ir0*(src0->nb[1]) + sq[0]*(src0->nb[2])); // {d_conv - 1, d_inner, n_kv} + ne0s0 = src0->ne[0]; + } else { + // the source is the last (d_conv - 1) columns of the destination + s0 = s + 1; + ne0s0 = nc; + } + + // d_inner + for (int i1 = 0; i1 < ir; ++i1) { + // shift state left + for (int i0 = 0; i0 < nc - 1; ++i0) { + s[i0 + i1*nc] = s0[i0 + i1*ne0s0]; + } + // insert x on the last column + s[(nc - 1) + i1*nc] = x0[i1]; + } + + // handle copies when there are multiple output states + for (int i3 = 1; i3 < n_kv; ++i3) { + int32_t seq = sq[i3]; + if (0 <= seq && seq < n_kv) { + float * s1 = s + (seq - sq[0])*nc*nr; + memcpy(s1, s, nc*ir*sizeof(float)); + } else { + // stop at negative or too big seq_ids + break; + } + } + + // it seems a little faster when this is separate from the state shift + for (int i1 = 0; i1 < ir; ++i1) { + // rowwise dot product + float sumf = 0.0f; + for (int i0 = 0; i0 < nc; ++i0) { + int i = i0 + i1*nc; + sumf += s[i] * c[i]; + } + x[i1] = sumf; + } + } +} + +static void ggml_compute_forward_ssm_conv( + const struct ggml_compute_params * params, + struct ggml_tensor * dst) { + switch (dst->src[0]->type) { + case GGML_TYPE_F32: + { + ggml_compute_forward_ssm_conv_f32(params, dst); + } break; + default: + { + GGML_ASSERT(false); + } break; + } +} + +// ggml_compute_forward_ssm_scan + +static void ggml_compute_forward_ssm_scan_f32( + const struct ggml_compute_params * params, + struct ggml_tensor * dst) { + if (params->type == GGML_TASK_TYPE_INIT || params->type == GGML_TASK_TYPE_FINALIZE) { + return; + } + + const struct ggml_tensor * src0 = dst->src[0]; // s + const struct ggml_tensor * src1 = dst->src[1]; // x + const struct ggml_tensor * src2 = dst->src[2]; // dt + const struct ggml_tensor * src3 = dst->src[3]; // A + const struct ggml_tensor * src4 = dst->src[4]; // B + const struct ggml_tensor * src5 = dst->src[5]; // C + const struct ggml_tensor * src6 = dst->src[6]; // sq + + const int ith = params->ith; + const int nth = params->nth; + + const int64_t nc = src0->ne[0]; // d_state + const int64_t nr = src0->ne[1]; // d_inner + const int64_t n_t = src1->ne[1]; // number of tokens in the batch + const int64_t n_kv = src0->ne[2]; // max number of sequences in the batch + + GGML_ASSERT(ggml_nelements(src1) + ggml_nelements(src0) == ggml_nelements(dst)); + GGML_ASSERT(src0->nb[0] == sizeof(float)); + GGML_ASSERT(src1->nb[0] == sizeof(float)); + GGML_ASSERT(src2->nb[0] == sizeof(float)); + GGML_ASSERT(src3->nb[0] == sizeof(float)); + GGML_ASSERT(src4->nb[0] == sizeof(float)); + GGML_ASSERT(src5->nb[0] == sizeof(float)); + // required for the dot product between s and C, and when copying the states + GGML_ASSERT(src0->nb[1] == src0->ne[0]*sizeof(float)); + // required for per-sequence offsets for states + GGML_ASSERT(src0->nb[2] == src0->ne[0]*src0->ne[1]*sizeof(float)); + // required to get correct offset for state destination (i.e. src1->nb[2]) + GGML_ASSERT(src1->nb[2] == src1->ne[0]*src1->ne[1]*sizeof(float)); + + // rows per thread + const int dr = (nr + nth - 1)/nth; + + // row range for this thread + const int ir0 = dr*ith; + const int ir1 = MIN(ir0 + dr, nr); + const int ir = ir1 - ir0; + + if (n_kv > 1) { + // it's hard to know if the source states have already been copied + // when there are multiple, so copy them already. + for (int i3 = 0; i3 < n_kv; ++i3) { + float * s0 = (float *) ((char *) src0->data + ir0*(src0->nb[1]) + i3*(src0->nb[2])); + float * s = (float *) ((char *) dst->data + ir0*(src0->nb[1]) + i3*(src0->nb[2]) + src1->nb[2]); + memcpy(s, s0, nc*ir*sizeof(float)); + } + } + + for (int i2 = 0; i2 < n_t; ++i2) { + int32_t * sq = (int32_t *) ((char *) src6->data + i2*(src6->nb[1])); // {n_kv, n_tokens} + float * y = (float *) ((char *) dst->data + ir0*(src1->nb[0]) + i2*(src1->nb[1])); // {d_inner, n_tokens} + float * s = (float *) ((char *) dst->data + ir0*(src0->nb[1]) + sq[0]*(src0->nb[2]) + src1->nb[2]); // {d_state, d_inner, n_kv} + float * s0; + float * x = (float *) ((char *) src1->data + ir0*(src1->nb[0]) + i2*(src1->nb[1])); // {d_inner, n_tokens} + float * dt = (float *) ((char *) src2->data + ir0*(src2->nb[0]) + i2*(src2->nb[1])); // {d_inner, n_tokens} + float * A = (float *) ((char *) src3->data + ir0*(src3->nb[1])); // {d_state, d_inner} + float * B = (float *) ((char *) src4->data + i2*(src4->nb[1])); // {d_state, n_tokens} + float * C = (float *) ((char *) src5->data + i2*(src5->nb[1])); // {d_state, n_tokens} + + GGML_ASSERT(0 <= sq[0] && sq[0] < n_kv); + + // avoid needing to copy the state for the first token + if (i2 == 0) { + s0 = (float *) ((char *) src0->data + ir0*(src0->nb[1]) + sq[0]*(src0->nb[2])); // {d_state, d_inner, n_kv} + } else { + // otherwise the source is the same as the destination + s0 = s; + } + + // d_inner + for (int i1 = 0; i1 < ir; ++i1) { + // ref: https://github.com/state-spaces/mamba/blob/34076d664838588a3c97727b263478ab9f621a07/mamba_ssm/ops/triton/selective_state_update.py#L78 + float dt_soft_plus = dt[i1] <= 20.0f ? log1pf(expf(dt[i1])) : dt[i1]; + float x_dt = x[i1] * dt_soft_plus; + float sumf = 0.0f; + // d_state + for (int i0 = 0; i0 < nc; ++i0) { + int i = i0 + i1*nc; + // state = prev_state * dA + dB * x + float state = (s0[i] * expf(dt_soft_plus * A[i])) + (B[i0] * x_dt); + // y = rowwise_dotprod(state, C) + sumf += state * C[i0]; + s[i] = state; + } + y[i1] = sumf; + } + + // handle copies when there are multiple output states + for (int i3 = 1; i3 < n_kv; ++i3) { + int32_t seq = sq[i3]; + if (0 <= seq && seq < n_kv) { + float * s1 = s + (seq - sq[0])*nc*nr; + memcpy(s1, s, nc*ir*sizeof(float)); + } else { + // stop at negative or too big seq_ids + break; + } + } + } +} + +static void ggml_compute_forward_ssm_scan( + const struct ggml_compute_params * params, + struct ggml_tensor * dst) { + switch (dst->src[0]->type) { + case GGML_TYPE_F32: + { + ggml_compute_forward_ssm_scan_f32(params, dst); + } break; + default: + { + GGML_ASSERT(false); + } break; + } +} + // ggml_compute_forward_win_part static void ggml_compute_forward_win_part_f32( @@ -15830,6 +16205,14 @@ static void ggml_compute_forward(struct ggml_compute_params * params, struct ggm bool masked = t != 0; ggml_compute_forward_flash_attn_back(params, masked, tensor); } break; + case GGML_OP_SSM_CONV: + { + ggml_compute_forward_ssm_conv(params, tensor); + } break; + case GGML_OP_SSM_SCAN: + { + ggml_compute_forward_ssm_scan(params, tensor); + } break; case GGML_OP_WIN_PART: { ggml_compute_forward_win_part(params, tensor); @@ -16884,6 +17267,11 @@ static void ggml_compute_backward(struct ggml_context * ctx, struct ggml_tensor { GGML_ASSERT(false); // not supported } break; + case GGML_OP_SSM_CONV: + case GGML_OP_SSM_SCAN: + { + GGML_ASSERT(false); // TODO: not implemented + } break; case GGML_OP_WIN_PART: case GGML_OP_WIN_UNPART: case GGML_OP_UNARY: @@ -17426,7 +17814,7 @@ static void ggml_graph_compute_perf_stats_node(struct ggml_tensor * node, const node->perf_time_us += time_us_cur; } -static int ggml_get_n_tasks(struct ggml_tensor * node, int n_threads) { +static int ggml_get_n_tasks(struct ggml_tensor * node, int n_threads, int n_cur_threads) { int n_tasks = 0; switch (node->op) { @@ -17507,6 +17895,12 @@ static int ggml_get_n_tasks(struct ggml_tensor * node, int n_threads) { { n_tasks = n_threads; } break; + case GGML_OP_GET_ROWS: + { + // FIXME: the cost of launching additional threads decreases performance with GPU offloading + //n_tasks = MIN(n_threads, ggml_nelements(node->src[1])); + n_tasks = MIN(n_cur_threads, ggml_nelements(node->src[1])); + } break; case GGML_OP_SCALE: case GGML_OP_SET: case GGML_OP_CONT: @@ -17514,7 +17908,6 @@ static int ggml_get_n_tasks(struct ggml_tensor * node, int n_threads) { case GGML_OP_VIEW: case GGML_OP_PERMUTE: case GGML_OP_TRANSPOSE: - case GGML_OP_GET_ROWS: case GGML_OP_GET_ROWS_BACK: case GGML_OP_DIAG: { @@ -17590,6 +17983,11 @@ static int ggml_get_n_tasks(struct ggml_tensor * node, int n_threads) { { n_tasks = n_threads; } break; + case GGML_OP_SSM_CONV: + case GGML_OP_SSM_SCAN: + { + n_tasks = n_threads; + } break; case GGML_OP_WIN_PART: case GGML_OP_WIN_UNPART: case GGML_OP_GET_REL_POS: @@ -17727,7 +18125,7 @@ static thread_ret_t ggml_graph_compute_thread(void * data) { /* FINALIZE */ struct ggml_tensor * node = cgraph->nodes[node_n]; if (GGML_OP_HAS_FINALIZE[node->op]) { - params.nth = ggml_get_n_tasks(node, n_threads); + params.nth = ggml_get_n_tasks(node, n_threads, state->shared->n_threads); ggml_compute_forward(¶ms, node); } ggml_graph_compute_perf_stats_node(node, state->shared); @@ -17737,7 +18135,7 @@ static thread_ret_t ggml_graph_compute_thread(void * data) { while (++node_n < cgraph->n_nodes) { GGML_PRINT_DEBUG_5("%s: %d/%d\n", __func__, node_n, cgraph->n_nodes); struct ggml_tensor * node = cgraph->nodes[node_n]; - const int n_tasks = ggml_get_n_tasks(node, n_threads); + const int n_tasks = ggml_get_n_tasks(node, n_threads, state->shared->n_threads); state->shared->perf_node_start_cycles = ggml_perf_cycles(); state->shared->perf_node_start_time_us = ggml_perf_time_us(); @@ -17785,7 +18183,7 @@ static thread_ret_t ggml_graph_compute_thread(void * data) { /* INIT & COMPUTE */ struct ggml_tensor * node = cgraph->nodes[node_n]; - const int n_tasks = ggml_get_n_tasks(node, n_threads); + const int n_tasks = ggml_get_n_tasks(node, n_threads, state->shared->n_threads); struct ggml_compute_params params = { /*.type =*/ GGML_TASK_TYPE_INIT, @@ -17850,7 +18248,7 @@ struct ggml_cplan ggml_graph_plan(const struct ggml_cgraph * cgraph, int n_threa for (int i = 0; i < cgraph->n_nodes; i++) { struct ggml_tensor * node = cgraph->nodes[i]; - const int n_tasks = ggml_get_n_tasks(node, n_threads); + const int n_tasks = ggml_get_n_tasks(node, n_threads, 1); max_tasks = MAX(max_tasks, n_tasks); @@ -19784,133 +20182,6 @@ void ggml_quantize_free(void) { ggml_critical_section_end(); } -size_t ggml_quantize_q4_0(const float * src, void * dst, int n, int k, int64_t * hist) { - assert(k % QK4_0 == 0); - const int nb = k / QK4_0; - - for (int b = 0; b < n; b += k) { - block_q4_0 * restrict y = (block_q4_0 *) dst + b/QK4_0; - - quantize_row_q4_0_reference(src + b, y, k); - - for (int i = 0; i < nb; i++) { - for (int j = 0; j < QK4_0; j += 2) { - const uint8_t vi0 = y[i].qs[j/2] & 0x0F; - const uint8_t vi1 = y[i].qs[j/2] >> 4; - - hist[vi0]++; - hist[vi1]++; - } - } - } - - return (n/QK4_0*sizeof(block_q4_0)); -} - -size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int64_t * hist) { - assert(k % QK4_1 == 0); - const int nb = k / QK4_1; - - for (int b = 0; b < n; b += k) { - block_q4_1 * restrict y = (block_q4_1 *) dst + b/QK4_1; - - quantize_row_q4_1_reference(src + b, y, k); - - for (int i = 0; i < nb; i++) { - for (int j = 0; j < QK4_1; j += 2) { - const uint8_t vi0 = y[i].qs[j/2] & 0x0F; - const uint8_t vi1 = y[i].qs[j/2] >> 4; - - hist[vi0]++; - hist[vi1]++; - } - } - } - - return (n/QK4_1*sizeof(block_q4_1)); -} - -size_t ggml_quantize_q5_0(const float * src, void * dst, int n, int k, int64_t * hist) { - assert(k % QK5_0 == 0); - const int nb = k / QK5_0; - - for (int b = 0; b < n; b += k) { - block_q5_0 * restrict y = (block_q5_0 *)dst + b/QK5_0; - - quantize_row_q5_0_reference(src + b, y, k); - - for (int i = 0; i < nb; i++) { - uint32_t qh; - memcpy(&qh, &y[i].qh, sizeof(qh)); - - for (int j = 0; j < QK5_0; j += 2) { - const uint8_t vh0 = ((qh & (1u << (j/2 + 0 ))) >> (j/2 + 0 )) << 4; - const uint8_t vh1 = ((qh & (1u << (j/2 + 16))) >> (j/2 + 12)); - - // cast to 16 bins - const uint8_t vi0 = ((y[i].qs[j/2] & 0x0F) | vh0) / 2; - const uint8_t vi1 = ((y[i].qs[j/2] >> 4) | vh1) / 2; - - hist[vi0]++; - hist[vi1]++; - } - } - } - - return (n/QK5_0*sizeof(block_q5_0)); -} - -size_t ggml_quantize_q5_1(const float * src, void * dst, int n, int k, int64_t * hist) { - assert(k % QK5_1 == 0); - const int nb = k / QK5_1; - - for (int b = 0; b < n; b += k) { - block_q5_1 * restrict y = (block_q5_1 *)dst + b/QK5_1; - - quantize_row_q5_1_reference(src + b, y, k); - - for (int i = 0; i < nb; i++) { - uint32_t qh; - memcpy(&qh, &y[i].qh, sizeof(qh)); - - for (int j = 0; j < QK5_1; j += 2) { - const uint8_t vh0 = ((qh & (1u << (j/2 + 0 ))) >> (j/2 + 0 )) << 4; - const uint8_t vh1 = ((qh & (1u << (j/2 + 16))) >> (j/2 + 12)); - - // cast to 16 bins - const uint8_t vi0 = ((y[i].qs[j/2] & 0x0F) | vh0) / 2; - const uint8_t vi1 = ((y[i].qs[j/2] >> 4) | vh1) / 2; - - hist[vi0]++; - hist[vi1]++; - } - } - } - - return (n/QK5_1*sizeof(block_q5_1)); -} - -size_t ggml_quantize_q8_0(const float * src, void * dst, int n, int k, int64_t * hist) { - assert(k % QK8_0 == 0); - const int nb = k / QK8_0; - - for (int b = 0; b < n; b += k) { - block_q8_0 * restrict y = (block_q8_0 *)dst + b/QK8_0; - - quantize_row_q8_0_reference(src + b, y, k); - - for (int i = 0; i < nb; i++) { - for (int j = 0; j < QK8_0; ++j) { - const int8_t vi = y[i].qs[j]; - - hist[vi/16 + 8]++; - } - } - } - - return (n/QK8_0*sizeof(block_q8_0)); -} - bool ggml_quantize_requires_imatrix(enum ggml_type type) { return type == GGML_TYPE_IQ2_XXS || @@ -19918,177 +20189,52 @@ bool ggml_quantize_requires_imatrix(enum ggml_type type) { type == GGML_TYPE_IQ1_S; } -size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst, int start, - int nrows, int n_per_row, int64_t * hist, const float * imatrix) { +size_t ggml_quantize_chunk( + enum ggml_type type, + const float * src, + void * dst, + int start, + int nrows, + int n_per_row, + const float * imatrix) { + const int n = nrows * n_per_row; + + if (ggml_quantize_requires_imatrix(type)) { + GGML_ASSERT(imatrix != NULL); + } + + GGML_ASSERT(start % type_traits[type].blck_size == 0); + GGML_ASSERT(start % n_per_row == 0); + ggml_quantize_init(type); // this is noop if already initialized + + const size_t start_row = start / n_per_row; + const size_t row_size = ggml_row_size(type, n_per_row); + size_t result = 0; - int n = nrows * n_per_row; + switch (type) { - case GGML_TYPE_Q4_0: - { - GGML_ASSERT(start % QK4_0 == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_q4_0(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_Q4_1: - { - GGML_ASSERT(start % QK4_1 == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_q4_1(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_Q5_0: - { - GGML_ASSERT(start % QK5_0 == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_q5_0(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_Q5_1: - { - GGML_ASSERT(start % QK5_1 == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_q5_1(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_Q8_0: - { - GGML_ASSERT(start % QK8_0 == 0); - block_q8_0 * block = (block_q8_0*)dst + start / QK8_0; - result = ggml_quantize_q8_0(src + start, block, n, n, hist); - } break; - case GGML_TYPE_Q2_K: - { - GGML_ASSERT(start % QK_K == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_q2_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_Q3_K: - { - GGML_ASSERT(start % QK_K == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_q3_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_Q4_K: - { - GGML_ASSERT(start % QK_K == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_q4_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_Q5_K: - { - GGML_ASSERT(start % QK_K == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_q5_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_Q6_K: - { - GGML_ASSERT(start % QK_K == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_q6_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_IQ2_XXS: - { - GGML_ASSERT(start % QK_K == 0); - GGML_ASSERT(start % n_per_row == 0); - GGML_ASSERT(imatrix); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_iq2_xxs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_IQ2_XS: - { - GGML_ASSERT(start % QK_K == 0); - GGML_ASSERT(start % n_per_row == 0); - GGML_ASSERT(imatrix); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_iq2_xs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_IQ3_XXS: - { - GGML_ASSERT(start % QK_K == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_iq3_xxs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_IQ3_S: - { - GGML_ASSERT(start % QK_K == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_iq3_s(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_IQ2_S: - { - GGML_ASSERT(start % QK_K == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_iq2_s(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_IQ1_S: - { - GGML_ASSERT(start % QK_K == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_iq1_s(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; - case GGML_TYPE_IQ4_NL: + case GGML_TYPE_Q4_0: result = quantize_q4_0(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_Q4_1: result = quantize_q4_1(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_Q5_0: result = quantize_q5_0(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_Q5_1: result = quantize_q5_1(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_Q8_0: result = quantize_q8_0(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_Q2_K: result = quantize_q2_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_Q3_K: result = quantize_q3_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_Q4_K: result = quantize_q4_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_Q5_K: result = quantize_q5_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_Q6_K: result = quantize_q6_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_IQ2_XXS: result = quantize_iq2_xxs(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_IQ2_XS: result = quantize_iq2_xs (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_IQ3_XXS: result = quantize_iq3_xxs(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_IQ3_S: result = quantize_iq3_s (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_IQ2_S: result = quantize_iq2_s (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_IQ1_S: result = quantize_iq1_s (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_IQ4_NL: result = quantize_iq4_nl (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; #if QK_K == 64 - case GGML_TYPE_IQ4_XS: -#endif - { - GGML_ASSERT(start % QK4_NL == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_iq4_nl(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; -#if QK_K != 64 - case GGML_TYPE_IQ4_XS: - { - GGML_ASSERT(start % QK_K == 0); - GGML_ASSERT(start % n_per_row == 0); - size_t start_row = start / n_per_row; - size_t row_size = ggml_row_size(type, n_per_row); - result = quantize_iq4_xs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); - GGML_ASSERT(result == row_size * nrows); - } break; + case GGML_TYPE_IQ4_XS: result = quantize_iq4_nl (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; +#else + case GGML_TYPE_IQ4_XS: result = quantize_iq4_xs (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; #endif case GGML_TYPE_F16: { @@ -20105,6 +20251,9 @@ size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst, i default: assert(false); } + + GGML_ASSERT(result == nrows * row_size); + return result; } diff --git a/tests/test-backend-buffer.cpp b/tests/test-backend-buffer.cpp index d3c9fe0f9..19ba22a52 100644 --- a/tests/test-backend-buffer.cpp +++ b/tests/test-backend-buffer.cpp @@ -40,8 +40,8 @@ static void test_buffer(ggml_backend_t backend, ggml_backend_buffer_type_t buft) GGML_ASSERT(ggml_backend_buffer_get_alloc_size(buffer, tensor) >= n * sizeof(float)); - ggml_tallocr_t allocr = ggml_tallocr_new(buffer); - ggml_tallocr_alloc(allocr, tensor); + struct ggml_tallocr allocr = ggml_tallocr_new(buffer); + ggml_tallocr_alloc(&allocr, tensor); GGML_ASSERT(tensor->data != NULL); @@ -59,7 +59,6 @@ static void test_buffer(ggml_backend_t backend, ggml_backend_buffer_type_t buft) GGML_ASSERT(memcmp(data, data2, sizeof(data)) == 0); - ggml_tallocr_free(allocr); ggml_backend_buffer_free(buffer); ggml_free(ctx); } diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp index 8a6999f21..c2916c3e4 100644 --- a/tests/test-backend-ops.cpp +++ b/tests/test-backend-ops.cpp @@ -53,7 +53,6 @@ static void init_tensor_uniform(ggml_tensor * tensor, float min = -1.0f, float m } else if (ggml_is_quantized(tensor->type) || tensor->type == GGML_TYPE_F16) { GGML_ASSERT(size % ggml_blck_size(tensor->type) == 0); std::vector dataq(ggml_row_size(tensor->type, size)); - int64_t hist[16]; std::vector imatrix(tensor->ne[0], 1.0f); // dummy importance matrix const float * im = imatrix.data(); if (!ggml_quantize_requires_imatrix(tensor->type)) { @@ -63,7 +62,7 @@ static void init_tensor_uniform(ggml_tensor * tensor, float min = -1.0f, float m im = nullptr; } } - ggml_quantize_chunk(tensor->type, data.data(), dataq.data(), 0, size/tensor->ne[0], tensor->ne[0], hist, im); + ggml_quantize_chunk(tensor->type, data.data(), dataq.data(), 0, size/tensor->ne[0], tensor->ne[0], im); ggml_backend_tensor_set(tensor, dataq.data(), 0, dataq.size()); } else if (tensor->type == GGML_TYPE_I8 || tensor->type == GGML_TYPE_I16 || tensor->type == GGML_TYPE_I32) { // This is going to create some weird integers though. @@ -2223,8 +2222,8 @@ static void usage(char ** argv) { int main(int argc, char ** argv) { test_mode mode = MODE_TEST; - const char * op_name = NULL; - const char * backend = NULL; + const char * op_name_filter = NULL; + const char * backend_filter = NULL; for (int i = 1; i < argc; i++) { if (strcmp(argv[i], "test") == 0) { @@ -2233,14 +2232,14 @@ int main(int argc, char ** argv) { mode = MODE_PERF; } else if (strcmp(argv[i], "-o") == 0) { if (i + 1 < argc) { - op_name = argv[++i]; + op_name_filter = argv[++i]; } else { usage(argv); return 1; } } else if (strcmp(argv[i], "-b") == 0) { if (i + 1 < argc) { - backend = argv[++i]; + backend_filter = argv[++i]; } else { usage(argv); return 1; @@ -2259,7 +2258,7 @@ int main(int argc, char ** argv) { for (size_t i = 0; i < ggml_backend_reg_get_count(); i++) { printf("Backend %zu/%zu (%s)\n", i + 1, ggml_backend_reg_get_count(), ggml_backend_reg_get_name(i)); - if (backend != NULL && strcmp(backend, ggml_backend_reg_get_name(i)) != 0) { + if (backend_filter != NULL && strcmp(backend_filter, ggml_backend_reg_get_name(i)) != 0) { printf(" Skipping\n"); n_ok++; continue; @@ -2267,9 +2266,17 @@ int main(int argc, char ** argv) { ggml_backend_t backend = ggml_backend_reg_init_backend(i, NULL); GGML_ASSERT(backend != NULL); + + if (backend_filter == NULL && ggml_backend_is_cpu(backend)) { + printf(" Skipping CPU backend\n"); + ggml_backend_free(backend); + n_ok++; + continue; + } + printf(" Backend name: %s\n", ggml_backend_name(backend)); - bool ok = test_backend(backend, mode, op_name); + bool ok = test_backend(backend, mode, op_name_filter); printf(" Backend %s: ", ggml_backend_name(backend)); if (ok) { diff --git a/tests/test-conv1d.cpp b/tests/test-conv1d.cpp index 79d18b872..b6daa7b69 100644 --- a/tests/test-conv1d.cpp +++ b/tests/test-conv1d.cpp @@ -111,10 +111,10 @@ void load_model(test_model & model, bool use_gpu = false) { model.b = ggml_new_tensor_3d(model.ctx, GGML_TYPE_F32, IL, IC, N); // create a allocator - ggml_tallocr_t alloc = ggml_tallocr_new(model.buffer); + ggml_tallocr alloc = ggml_tallocr_new(model.buffer); // alloc memory - ggml_tallocr_alloc(alloc, model.a); + ggml_tallocr_alloc(&alloc, model.a); // load data to buffer if(ggml_backend_is_cpu(model.backend)) { @@ -124,7 +124,7 @@ void load_model(test_model & model, bool use_gpu = false) { } // alloc memory - ggml_tallocr_alloc(alloc, model.b); + ggml_tallocr_alloc(&alloc, model.b); if(ggml_backend_is_cpu(model.backend) #ifdef GGML_USE_METAL @@ -135,8 +135,6 @@ void load_model(test_model & model, bool use_gpu = false) { } else { ggml_backend_tensor_set(model.b, bdata, 0, ggml_nbytes(model.b)); } - - ggml_tallocr_free(alloc); } struct ggml_cgraph * build_graph(const test_model& model) { diff --git a/tests/test-conv2d.cpp b/tests/test-conv2d.cpp index 1aea5eef3..35d565444 100644 --- a/tests/test-conv2d.cpp +++ b/tests/test-conv2d.cpp @@ -111,10 +111,10 @@ void load_model(test_model & model, bool use_gpu = false) { model.b = ggml_new_tensor_4d(model.ctx, GGML_TYPE_F32, IW, IH, IC, N); // create a allocator - ggml_tallocr_t alloc = ggml_tallocr_new(model.buffer); + struct ggml_tallocr alloc = ggml_tallocr_new(model.buffer); // alloc memory - ggml_tallocr_alloc(alloc, model.a); + ggml_tallocr_alloc(&alloc, model.a); // load data to buffer if(ggml_backend_is_cpu(model.backend)) { @@ -124,7 +124,7 @@ void load_model(test_model & model, bool use_gpu = false) { } // alloc memory - ggml_tallocr_alloc(alloc, model.b); + ggml_tallocr_alloc(&alloc, model.b); if(ggml_backend_is_cpu(model.backend) #ifdef GGML_USE_METAL @@ -135,8 +135,6 @@ void load_model(test_model & model, bool use_gpu = false) { } else { ggml_backend_tensor_set(model.b, bdata, 0, ggml_nbytes(model.b)); } - - ggml_tallocr_free(alloc); } struct ggml_cgraph * build_graph(const test_model& model) { diff --git a/tests/test-mul-mat.cpp b/tests/test-mul-mat.cpp index f082dea16..07a6ffeba 100644 --- a/tests/test-mul-mat.cpp +++ b/tests/test-mul-mat.cpp @@ -85,10 +85,10 @@ void load_model(test_model & model, float* a, float* b, int M, int N, int K, boo printf("Matrix B: [%i, %i]\n", K, N); // create a allocator - ggml_tallocr_t alloc = ggml_tallocr_new(model.buffer); + struct ggml_tallocr alloc = ggml_tallocr_new(model.buffer); // alloc memory - ggml_tallocr_alloc(alloc, model.a); + ggml_tallocr_alloc(&alloc, model.a); // load data to buffer if(ggml_backend_is_cpu(model.backend) @@ -102,7 +102,7 @@ void load_model(test_model & model, float* a, float* b, int M, int N, int K, boo } // alloc memory - ggml_tallocr_alloc(alloc, model.b); + ggml_tallocr_alloc(&alloc, model.b); if(ggml_backend_is_cpu(model.backend) #ifdef GGML_USE_METAL @@ -113,8 +113,6 @@ void load_model(test_model & model, float* a, float* b, int M, int N, int K, boo } else { ggml_backend_tensor_set(model.b, b, 0, ggml_nbytes(model.b)); // cuda requires copy the data directly to device } - - ggml_tallocr_free(alloc); } struct ggml_cgraph * build_graph(const test_model& model) {