Files
cutlass/tools
Fujun Han 1e4703cbab Support parallel split K mode for porfiling (#277)
* Support parallel split K mode for porfiling

Signed-off-by: Peter Han <fujun.han@iluvatar.ai>

* Parallel Split K support

  1. find gemm kernel by preference key
  2. switch m n for redution kernel

Signed-off-by: Peter Han <fujun.han@iluvatar.ai>

* parallel splitk for fp16 gemm

* add one missing file

Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
2022-01-27 10:37:37 -05:00
..
2021-11-19 13:26:35 -08:00
2021-07-27 17:58:30 -07:00