The Design and Performance of Batched BLAS on Modern High-Performance Computing Systems

Author:

Dongarra Jack,Hammarling Sven,Higham Nicholas J.,Relton Samuel D.,Valero-Lara Pedro,Zounon Mawussi

Publisher

Elsevier BV

Subject

General Engineering

Reference15 articles.

1. Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, et al. TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. Software available from http://tensorflow.org.

2. Numerical linear algebra on emerging architectures: The PLASMA and MAGMA projects;Agullo;Journal of Physics: Conference Series,2009

3. Emmanuel Agullo, Luc Giraud, and Mawussi Zounon. On the resilience of parallel sparse hybrid solvers. In 22nd IEEE International Conference on High Performance Computing, HiPC 2015, Bengaluru, India, December 16-19, 2015, pages 75–84, 2015.

4. Rami Al-Rfou, Guillaume Alain, Amjad Almahairi, Christof Angermueller, Dzmitry Bahdanau, et al. Theano: A Python framework for fast computation of mathematical expressions. arXiv e-prints, abs/1605.02688, May 2016.

5. A set of level 3 basic linear algebra subprograms;Dongarra;ACM Trans. Math. Softw.,1990

Cited by 48 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. BLAS Kütüphanelerinin GPU Mimarilerindeki Nicel Performans Analizi;Deu Muhendislik Fakultesi Fen ve Muhendislik;2024-01-23

2. MatRIS: Multi-level Math Library Abstraction for Heterogeneity and Performance Portability using IRIS Runtime;Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis;2023-11-12

3. Integrating batched sparse iterative solvers for the collision operator in fusion plasma simulations on GPUs;Journal of Parallel and Distributed Computing;2023-08

4. Speedup deep learning models on GPU by taking advantage of efficient unstructured pruning and bit-width reduction;Journal of Computational Science;2023-03

5. A Case Study on DaCe Portability & Performance for Batched Discrete Fourier Transforms;Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region;2023-02-27

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