Matrix Multiplication in Multiword Arithmetic: Error Analysis and Application to GPU Tensor Cores

Author:

Fasi Massimiliano1ORCID,Higham Nicholas J.2ORCID,Lopez Florent3,Mary Theo4,Mikaitis Mantas2ORCID

Affiliation:

1. Department of Computer Science, Upper Mountjoy Campus, Durham University, Durham DH1 3LE, UK.

2. Department of Mathematics, University of Manchester, Manchester M13 9PL, UK.

3. Livermore Software Technology, ANSYS Company, Livermore, CA 94551 USA.

4. Sorbonne Université, CNRS, LIP6, Paris 75005, France.

Funder

Engineering and Physical Sciences Research Council

Wenner-Gren Stiftelserna

Royal Society

U.S. Department of Energy

Publisher

Society for Industrial & Applied Mathematics (SIAM)

Subject

Applied Mathematics,Computational Mathematics

Cited by 5 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. Efficient Mixed-Precision Matrix Factorization of the Inverse Overlap Matrix in Electronic Structure Calculations with AI-Hardware and GPUs;Journal of Chemical Theory and Computation;2024-08-13

2. Monotonicity of Multi-term Floating-Point Adders;IEEE Transactions on Computers;2024-06

3. Mixed Precision Randomized Low-Rank Approximation with GPU Tensor Cores;Lecture Notes in Computer Science;2024

4. Mixed-Precision S/DGEMM Using the TF32 and TF64 Frameworks on Low-Precision AI Tensor Cores;Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis;2023-11-12

5. CPFloat: A C Library for Simulating Low-precision Arithmetic;ACM Transactions on Mathematical Software;2023-06-17

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