High-performance implementation of the level-3 BLAS

Author:

Goto Kazushige1,Van De Geijn Robert1

Affiliation:

1. The University of Texas at Austin, Austin, TX

Abstract

A simple but highly effective approach for transforming high-performance implementations on cache-based architectures of matrix-matrix multiplication into implementations of other commonly used matrix-matrix computations (the level-3 BLAS) is presented. Exceptional performance is demonstrated on various architectures.

Funder

Division of Computing and Communication Foundations

Publisher

Association for Computing Machinery (ACM)

Subject

Applied Mathematics,Software

Cited by 172 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. IrGEMM: An Input-Aware Tuning Framework for Irregular GEMM on ARM and X86 CPUs;IEEE Transactions on Parallel and Distributed Systems;2024-09

2. Detailed Analysis and Optimization of Irregular-Shaped Matrix Multiplication on Multi-Core DSPs;Proceedings of the 53rd International Conference on Parallel Processing;2024-08-12

3. An efficient parallel approach for quad-constellation GNSS real-time precise orbit determination enabling 5-second intervals updating;Measurement;2024-06

4. Optimizing General Matrix Multiplications on Modern Multi-core DSPs;2024 IEEE International Parallel and Distributed Processing Symposium (IPDPS);2024-05-27

5. Automatic generation of ARM NEON micro-kernels for matrix multiplication;The Journal of Supercomputing;2024-03-12

同舟云学术

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