We are developing new features based on your feedback - please stay tuned!
A Coordinated Tiling and Batching Framework for Efficient GEMM on GPUs
Xiuhong Li, Yun Liang, Shengen Yan, Liancheng Jia, Yinghan Li
Where published: PPoPP'19
Article DOI: 10.1145/3293883.3295734
Artifact DOI: 10.1145/3300174
Unified artifact appendix: Link
Reproducible methodology: ACM and cTuning
ReproIndex JSON meta ]  [ paper ]