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

CUTLASS 3.5.1 (#1623)

Browse Source 
* CUTLASS 3.5.1

* updates, optimizations, fixes
This commit is contained in:
Vijay Thakkar
2024-07-29 08:46:24 -04:00
committed by GitHub
parent 56b46e2d13
commit be60a0b272
312 changed files with 19793 additions and 6775 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
python/cutlass_library/gemm_operation.py
View File

@@ -178,16 +178,28 @@ class GemmOperation:
if self.is_complex():
extended_name = "${core_name}"
else:
# e.g. f16_f16_f32_void_f32 kernel
if self.C.element != self.tile_description.math_instruction.element_accumulator and \
self.A.element != self.tile_description.math_instruction.element_accumulator:
self.A.element != self.tile_description.math_instruction.element_accumulator:
extended_name = "${element_c}_${core_name}_${element_a}"
if self.is_mixed_input():
extended_name += "_${element_b}"
# e.g. f32_f32_f32_void_f32 kernel
elif self.C.element != self.tile_description.math_instruction.element_accumulator and \
self.A.element == self.tile_description.math_instruction.element_accumulator:
extended_name = "${element_c}_${core_name}"
if self.is_mixed_input():
extended_name += "_${element_b}"
# e.g. f16_f16_f32_f32_f32 kernel
elif self.C.element == self.tile_description.math_instruction.element_accumulator and \
self.A.element != self.tile_description.math_instruction.element_accumulator:
self.A.element != self.tile_description.math_instruction.element_accumulator:
extended_name = "${core_name}_${element_a}"
if self.is_mixed_input():
extended_name += "_${element_b}"
# e.g. f32_f32_f32_f32_f32 kernel
else:
extended_name = "${core_name}"