@inproceedings{conf/ics/ChenXLTLOZDGC19,
added-at = {2019-09-25T00:00:00.000+0200},
author = {Chen, Jieyang and Xiong, Nan and Liang, Xin and Tao, Dingwen and Li, Sihuan and Ouyang, Kaiming and Zhao, Kai and DeBardeleben, Nathan and Guan, Qiang and Chen, Zizhong},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2cdb91d62c507e88dd95193ccde292eb2/dblp},
booktitle = {ICS},
crossref = {conf/ics/2019},
editor = {Eigenmann, Rudolf and Ding, Chen and McKee, Sally A.},
ee = {https://doi.org/10.1145/3330345.3330355},
interhash = {75c37e52d304ea1cd74253a1ee2a05bb},
intrahash = {cdb91d62c507e88dd95193ccde292eb2},
isbn = {978-1-4503-6079-1},
keywords = {dblp},
pages = {106-116},
publisher = {ACM},
timestamp = {2019-09-27T15:48:35.000+0200},
title = {TSM2: optimizing tall-and-skinny matrix-matrix multiplication on GPUs.},
url = {http://dblp.uni-trier.de/db/conf/ics/ics2019.html#ChenXLTLOZDGC19},
year = 2019
}