Lijuan Jiang, Chao Yang 0002, Wenjing Ma. Enabling Highly Efficient Batched Matrix Multiplications on SW26010 Many-core Processor. TACO, 17(1), 2020. [doi]
@article{JiangYM20,
title = {Enabling Highly Efficient Batched Matrix Multiplications on SW26010 Many-core Processor},
author = {Lijuan Jiang and Chao Yang 0002 and Wenjing Ma},
year = {2020},
doi = {10.1145/3378176},
url = {https://doi.org/10.1145/3378176},
researchr = {https://researchr.org/publication/JiangYM20},
cites = {0},
citedby = {0},
journal = {TACO},
volume = {17},
number = {1},
}