leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 25 Packages Projects Releases Wiki Activity

CUTLASS 2.10 updates (#622)

Browse Source 
Co-authored-by: Aniket Shivam <ashivam@nvidia.com>
This commit is contained in:
ANIKET SHIVAM
2022-09-12 21:26:30 -04:00
committed by GitHub
co-authored by Aniket Shivam
parent beae168f90
commit e773429f7e
96 changed files with 8365 additions and 1667 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/library/scripts/pycutlass/profile/gemm/gemm_f32_sm80.py
+2 -2
View File
@@ -49,7 +49,7 @@ if __name__ == '__main__':
tile_description = TileDescription(
threadblock_shape=[256, 128, 32],
stages=3, warp_count=[4, 2, 1],
math_instruction=math_inst, min_compute=80, max_compute=80
math_instruction=math_inst
)
A = TensorDescription(
@@ -67,7 +67,7 @@ if __name__ == '__main__':
element_epilogue = cutlass.float32
epilogue_functor = EpilogueFunctor.LinearCombination
epilogue_functor = LinearCombination(cutlass.float32, 4, cutlass.float32, cutlass.float32)
swizzling_functor = cutlass.IdentitySwizzle1