A versatile software systolic execution model for GPU memory-bound kernels
Author:
Affiliation:
1. National Institute of Advanced Industrial Science and Technology
2. RIKEN Center for Computational, Science, Hyogo, Japan
Funder
JST-CREST
Publisher
ACM
Link
https://dl.acm.org/doi/pdf/10.1145/3295500.3356162
Reference62 articles.
1. A Predictive Model for Solving Small Linear Algebra Problems in GPU Registers
2. A view of the parallel computing landscape
3. Compiler-Directed Transformation for Higher-Order Stencils
4. Tal Ben-Nun Johannes de Fine Licht Alexandros Nikolaos Ziogas Timo Schneider and Torsten Hoefler. 2019. Stateful Dataflow Multigraphs: A Data-Centric Model for High-Performance Parallel Programs. arXiv preprint arXiv:1902.10345 (2019). Tal Ben-Nun Johannes de Fine Licht Alexandros Nikolaos Ziogas Timo Schneider and Torsten Hoefler. 2019. Stateful Dataflow Multigraphs: A Data-Centric Model for High-Performance Parallel Programs. arXiv preprint arXiv:1902.10345 (2019).
5. Fast Multiplication in Binary Fields on GPUs via Register Cache
Cited by 14 articles. 订阅此论文施引文献 订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. POPA: Expressing High and Portable Performance across Spatial and Vector Architectures for Tensor Computations;Proceedings of the 2024 ACM/SIGDA International Symposium on Field Programmable Gate Arrays;2024-04
2. ConvStencil: Transform Stencil Computation to Matrix Multiplication on Tensor Cores;Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming;2024-02-20
3. PERKS: a Locality-Optimized Execution Model for Iterative Memory-bound GPU Applications;Proceedings of the 37th International Conference on Supercomputing;2023-06-21
4. Revisiting Temporal Blocking Stencil Optimizations;Proceedings of the 37th International Conference on Supercomputing;2023-06-21
5. Reducing shared memory footprint to leverage high throughput on Tensor Cores and its flexible API extension library;Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region;2023-02-27
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3