Skip to content

Commit d871b5b

Browse files
authored
[HGEMM] optimize SMEM padding, up to 113 TFLOPS (xlite-dev#92)
* Update hgemm.py * Update hgemm.py * Update README.md * Update README.md * Update README.md * Update hgemm_wmma_stage.cu * Update hgemm.py * Update README.md
1 parent 82b94c5 commit d871b5b

File tree

3 files changed

+551
-673
lines changed

3 files changed

+551
-673
lines changed

0 commit comments

Comments
 (0)