A coordinated tiling and batching framework for efficient GEMM on GPUs.
https://doi.org/10.1145/3293883.3295734
@inproceedings{DBLP:conf/ppopp/Li0YJL19,
author = {Xiuhong Li and
Yun Liang and
Shengen Yan and
Liancheng Jia and
Yinghan Li},
editor = {Jeffrey K. Hollingsworth and
Idit Keidar},
title = {A coordinated tiling and batching framework for efficient {GEMM} on
GPUs},
booktitle = {Proceedings of the 24th {ACM} {SIGPLAN} Symposium on Principles and
Practice of Parallel Programming, PPoPP 2019, Washington, DC, USA,
February 16-20, 2019},
pages = {229--241},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3293883.3295734},
doi = {10.1145/3293883.3295734},
timestamp = {Fri, 08 Feb 2019 09:59:28 +0100},
biburl = {https://dblp.org/rec/conf/ppopp/Li0YJL19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
本页面没有标签