Writing a performance-portable matrix multiplication-Reference-Cited by-同舟云学术

Writing a performance-portable matrix multiplication

Published:2016-02 Issue: Volume:52 Page:65-77
ISSN:0167-8191
Container-title:Parallel Computing
language:en
Short-container-title:Parallel Computing

Author:

F. Fabeiro Jorge^ORCID,Andrade Diego^ORCID,Fraguela Basilio B.

Publisher

Elsevier BV

Subject

Artificial Intelligence,Computer Graphics and Computer-Aided Design,Computer Networks and Communications,Hardware and Architecture,Theoretical Computer Science,Software

Reference25 articles.

1. Evaluating performance and portability of OpenCL programs;Komatsu,2010

2. Improving performance of GPU specific OpenCL program on CPUs;Lan,2012

3. Performance traps in OpenCL for CPUs;Shen,2013

4. Exploiting heterogeneous parallelism with the heterogeneous programming library;Viñas;J. Parallel Distrib. Comput.,2013

5. OpenCL Programming Guide;Munshi,2011

Cited by 9 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. Low precision matrix multiplication for efficient deep learning in NVIDIA Carmel processors;The Journal of Supercomputing;2021-03-22

2. An automatic optimizer for heterogeneous devices;Future Generation Computer Systems;2020-05

3. Portability Study of an OpenCL Algorithm for Automatic Target Detection in Hyperspectral Images;IEEE Transactions on Geoscience and Remote Sensing;2019-11

4. Portable and efficient FFT and DCT algorithms with the Heterogeneous Butterfly Processing Library;Journal of Parallel and Distributed Computing;2019-03

5. Heterogeneous distributed computing based on high-level abstractions;Concurrency and Computation: Practice and Experience;2018-08-02