|
1 | 1 | all:
|
2 | 2 | - title: "ElasticRoom: Multi-Tenant DNN Inference Engine via Co-design with Resource-constrained Compilation and Strong Priority Scheduling"
|
3 | 3 | id: 19
|
4 |
| - speakers: |
| 4 | + authors: |
5 | 5 | - name: "Lixian Ma"
|
6 | 6 |
|
7 | 7 | affiliation: "Institute of Computing Technology, CAS"
|
|
23 | 23 |
|
24 | 24 | - title: "GNNOne: A Unified System Optimizations for GNN Kernels"
|
25 | 25 | id: 42
|
26 |
| - speakers: |
| 26 | + authors: |
27 | 27 | - name: "Yidong Gong"
|
28 | 28 |
|
29 | 29 | affiliation: "William & Mary"
|
|
33 | 33 |
|
34 | 34 | - title: "Efficient all-to-all Collective Communication Schedules for Direct-connect Topologies"
|
35 | 35 | id: 71
|
36 |
| - speakers: |
| 36 | + authors: |
37 | 37 | - name: "Prithwish Basu"
|
38 | 38 |
|
39 | 39 | affiliation: "RTX BBN Technologies"
|
|
55 | 55 |
|
56 | 56 | - title: "ESG: Pipeline-Conscious Efficient Scheduling of DNN Workflows on Serverless Platforms with Shareable GPUs"
|
57 | 57 | id: 77
|
58 |
| - speakers: |
| 58 | + authors: |
59 | 59 | - name: "Xinning Hui"
|
60 | 60 |
|
61 | 61 | affiliation: "North Carolina State University"
|
|
71 | 71 |
|
72 | 72 | - title: "ETS: Deep Learning Training Iteration Time Prediction based on Execution Trace Sliding Window"
|
73 | 73 | id: 96
|
74 |
| - speakers: |
| 74 | + authors: |
75 | 75 | - name: "Zichao Yang"
|
76 | 76 |
|
77 | 77 | affiliation: "University of Chinese Academy of Sciences"
|
|
99 | 99 |
|
100 | 100 | - title: "IDT: Intelligent Data Placement for Multi-tiered Main Memory with Reinforcement Learning"
|
101 | 101 | id: 104
|
102 |
| - speakers: |
| 102 | + authors: |
103 | 103 | - name: "Juneseo Chang"
|
104 | 104 |
|
105 | 105 | affiliation: "Seoul National University"
|
|
118 | 118 |
|
119 | 119 | - title: "FPBOXer: Efficient Input-Generation for Targeting Floating-Point Exceptions in GPU Programs"
|
120 | 120 | id: 114
|
121 |
| - speakers: |
| 121 | + authors: |
122 | 122 | - name: "Anh Tran"
|
123 | 123 |
|
124 | 124 | affiliation: "University of Utah"
|
|
131 | 131 |
|
132 | 132 | - title: "FaaSKeeper: Learning from Building Serverless Services with ZooKeeper as an Example"
|
133 | 133 | id: 115
|
134 |
| - speakers: |
| 134 | + authors: |
135 | 135 | - name: "Marcin Copik"
|
136 | 136 |
|
137 | 137 | affiliation: "ETH Zurich"
|
|
150 | 150 |
|
151 | 151 | - title: "A Portable, Fast, DCT-based Compressor for AI Accelerators"
|
152 | 152 | id: 116
|
153 |
| - speakers: |
| 153 | + authors: |
154 | 154 | - name: "Milan Shah"
|
155 | 155 |
|
156 | 156 | affiliation: "North Carolina State University, Argonne National Laboratory"
|
|
169 | 169 |
|
170 | 170 | - title: "Accelerating Function-Centric Applications by Discovering, Distributing, and Retaining Reusable Context in Workflow Systems"
|
171 | 171 | id: 117
|
172 |
| - speakers: |
| 172 | + authors: |
173 | 173 | - name: "Thanh Son Phung"
|
174 | 174 |
|
175 | 175 | affiliation: "University of Notre Dame"
|
|
188 | 188 |
|
189 | 189 | - title: "ADTopk: All-Dimension Top-k Compression for High-Performance Data-Parallel DNN Training"
|
190 | 190 | id: 118
|
191 |
| - speakers: |
| 191 | + authors: |
192 | 192 | - name: "Zhangqiang Ming"
|
193 | 193 |
|
194 | 194 | affiliation: "Huazhong University of Science and Technology"
|
|
210 | 210 |
|
211 | 211 | - title: "EvoStore: Towards Scalable Storage of Evolving Learning Models"
|
212 | 212 | id: 122
|
213 |
| - speakers: |
| 213 | + authors: |
214 | 214 | - name: "Robert Underwood"
|
215 | 215 |
|
216 | 216 | affiliation: "Argonne National Laboratory"
|
|
226 | 226 |
|
227 | 227 | - title: "HAM-SpMSpV: an Optimized Parallel Algorithm for Masked Sparse Matrix-Sparse Vector Multiplications on multi-core CPUs"
|
228 | 228 | id: 176
|
229 |
| - speakers: |
| 229 | + authors: |
230 | 230 | - name: "Lei Xu"
|
231 | 231 |
|
232 | 232 | affiliation: "Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences"
|
|
245 | 245 |
|
246 | 246 | - title: "Faast: An Efficient Serverless Framework Made Snapshot-based Function Response Fast"
|
247 | 247 | id: 179
|
248 |
| - speakers: |
| 248 | + authors: |
249 | 249 | - name: "Yongshu Bai"
|
250 | 250 |
|
251 | 251 | affiliation: "Zhejiang Lab"
|
|
258 | 258 |
|
259 | 259 | - title: "DLHT: A Non-blocking Resizable Hashtable with Fast Deletes and Memory-awareness"
|
260 | 260 | id: 191
|
261 |
| - speakers: |
| 261 | + authors: |
262 | 262 | - name: "Antonios Katsarakis"
|
263 | 263 |
|
264 | 264 | affiliation: "Huawei Research"
|
|
271 | 271 |
|
272 | 272 | - title: "Extending Sparse Patterns to Improve Inverse Preconditioning on GPU Architectures"
|
273 | 273 | id: 272
|
274 |
| - speakers: |
| 274 | + authors: |
275 | 275 | - name: "Sergi Laut"
|
276 | 276 |
|
277 | 277 | affiliation: "Barcelona Supercomputing Center"
|
|
283 | 283 |
|
284 | 284 | - title: "FaaSRail: Employing Real Workloads to Generate Representative Load for Serverless Research"
|
285 | 285 | id: 273
|
286 |
| - speakers: |
| 286 | + authors: |
287 | 287 | - name: "Christos Katsakioris"
|
288 | 288 |
|
289 | 289 | affiliation: "National Technical University of Athens"
|
|
305 | 305 |
|
306 | 306 | - title: "DataStates-LLM: Lazy Asynchronous Checkpointing for Large Language Models"
|
307 | 307 | id: 283
|
308 |
| - speakers: |
| 308 | + authors: |
309 | 309 | - name: "Avinash Maurya"
|
310 | 310 |
|
311 | 311 | affiliation: "Rochester Institute of Technology"
|
|
324 | 324 |
|
325 | 325 | - title: "Reinforcement Learning-based Adaptive Mitigation of Uncorrected DRAM Errors in the Field"
|
326 | 326 | id: 292
|
327 |
| - speakers: |
| 327 | + authors: |
328 | 328 | - name: "Isaac Boixaderas"
|
329 | 329 |
|
330 | 330 | affiliation: "Barcelona Supercomputing Center"
|
|
349 | 349 |
|
350 | 350 | - title: "FASOP: Fast yet Accurate Automated Search for Optimal Parallelization of Transformers on Heterogeneous GPU Clusters"
|
351 | 351 | id: 296
|
352 |
| - speakers: |
| 352 | + authors: |
353 | 353 | - name: "Sunyeol Hwang"
|
354 | 354 |
|
355 | 355 | affiliation: "University of Seoul"
|
|
365 | 365 |
|
366 | 366 | - title: "Loki: A System for Serving ML Inference Pipelines with Hardware and Accuracy Scaling"
|
367 | 367 | id: 303
|
368 |
| - speakers: |
| 368 | + authors: |
369 | 369 | - name: "Sohaib Ahmad"
|
370 | 370 |
|
371 | 371 | affiliation: "University of Massachusetts Amherst"
|
|
377 | 377 | affiliation: "University of Massachusetts Amherst"
|
378 | 378 | - title: "Can Large Language Models Write Parallel Code?"
|
379 | 379 | id: 308
|
380 |
| - speakers: |
| 380 | + authors: |
381 | 381 | - name: "Daniel Nichols"
|
382 | 382 |
|
383 | 383 | affiliation: "University of Maryland, College Park"
|
|
396 | 396 |
|
397 | 397 | - title: "ScaleDFS: Accelerating Decentralized and Private File Sharing via Scaling Directed Acyclic Graph Processing"
|
398 | 398 | id: 417
|
399 |
| - speakers: |
| 399 | + authors: |
400 | 400 | - name: "Mansub Song"
|
401 | 401 |
|
402 | 402 | affiliation: "Seoul National University"
|
|
415 | 415 |
|
416 | 416 | - title: "CereSZ: Enabling and Scaling Error-bounded Lossy Compression on Cerebras CS-2"
|
417 | 417 | id: 450
|
418 |
| - speakers: |
| 418 | + authors: |
419 | 419 | - name: "Shihui Song"
|
420 | 420 |
|
421 | 421 | affiliation: "University of Iowa"
|
|
449 | 449 |
|
450 | 450 | - title: "SIMCoV-GPU: Accelerating an Agent-Based Model for Exascale"
|
451 | 451 | id: 506
|
452 |
| - speakers: |
| 452 | + authors: |
453 | 453 | - name: "Kirtus Leyba"
|
454 | 454 |
|
455 | 455 | affiliation: "Arizona State University"
|
|
468 | 468 |
|
469 | 469 | - title: "Near-Optimal Wafer-Scale Reduce"
|
470 | 470 | id: 516
|
471 |
| - speakers: |
| 471 | + authors: |
472 | 472 | - name: "Piotr Luczynski"
|
473 | 473 |
|
474 | 474 | affiliation: "ETH Zurich"
|
|
0 commit comments