Skip to content

Fix conv2d scratch buffer allocation to match CMSIS-NN wrapper dispatch #17766

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
rascani wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Fix conv2d scratch buffer allocation to match CMSIS-NN wrapper dispatch #17766

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 20 additions & 16 deletions backends/cortex_m/ops/op_quantized_conv2d.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,24 +188,28 @@ Tensor& quantized_conv2d_out(
cmsis_context.buf = nullptr;
cmsis_context.size = 0;

const size_t buffer_bytes = static_cast<size_t>(
arm_convolve_s8_get_buffer_size(&input_dims, &filter_dims));
const int32_t buffer_bytes = arm_convolve_wrapper_s8_get_buffer_size(
&conv_params, &input_dims, &filter_dims, &output_dims);
if (buffer_bytes < 0) {
ET_LOG(
Error, "quantized_conv2d_out: CMSIS-NN buffer size calculation failed");
context.fail(Error::Internal);
return out;
}
if (buffer_bytes > 0) {
auto buffer_or_error =
context.allocate_temp(buffer_bytes, alignof(int16_t));
auto buffer_or_error = context.allocate_temp(
static_cast<size_t>(buffer_bytes), alignof(int16_t));
if (!buffer_or_error.ok()) {
if (buffer_or_error.error() != Error::NotFound) {
ET_LOG(
Error,
"quantized_conv2d_out: failed to allocate scratch buffer (%d)",
static_cast<int>(buffer_or_error.error()));
context.fail(buffer_or_error.error());
return out;
}
} else {
cmsis_context.buf = buffer_or_error.get();
cmsis_context.size = buffer_bytes;
ET_LOG(
Error,
"quantized_conv2d_out: failed to allocate scratch buffer (%d bytes, error %d)",
static_cast<int>(buffer_bytes),
static_cast<int>(buffer_or_error.error()));
context.fail(buffer_or_error.error());
return out;
}
cmsis_context.buf = buffer_or_error.get();
cmsis_context.size = buffer_bytes;
}

const arm_cmsis_nn_status status = arm_convolve_wrapper_s8(
Expand All @@ -224,7 +228,7 @@ Tensor& quantized_conv2d_out(
if (status != ARM_CMSIS_NN_SUCCESS) {
ET_LOG(
Error,
"quantized_conv2d_out: arm_convolve_s8 failed with status %d",
"quantized_conv2d_out: arm_convolve_wrapper_s8 failed with status %d",
status);
context.fail(Error::Internal);
}
Expand Down
Loading