mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-12 01:10:17 +00:00
fix macro for exp2; fix warpgemm a/b in transposedC
This commit is contained in:
@@ -30,9 +30,9 @@ set(EXAMPLE_FMHA_FWD_COMPILE_OPTIONS)
|
||||
# NOTE: we turn off undefined-func-template to let source compile without explicit declare function specializations
|
||||
# ... because they are auto-generated
|
||||
if(FMHA_FWD_FAST_EXP2)
|
||||
list(APPEND EXAMPLE_FMHA_FWD_COMPILE_OPTIONS -Wno-undefined-func-template -DCK_FMHA_FWD_FAST_EXP2=1 -fgpu-flush-denormals-to-zero -v --save-temps -Wno-gnu-line-marker)
|
||||
list(APPEND EXAMPLE_FMHA_FWD_COMPILE_OPTIONS -Wno-undefined-func-template -DCK_TILE_FMHA_FWD_FAST_EXP2=1 -fgpu-flush-denormals-to-zero)
|
||||
else()
|
||||
list(APPEND EXAMPLE_FMHA_FWD_COMPILE_OPTIONS -Wno-undefined-func-template -DCK_FMHA_FWD_FAST_EXP2=0 -v --save-temps -Wno-gnu-line-marker)
|
||||
list(APPEND EXAMPLE_FMHA_FWD_COMPILE_OPTIONS -Wno-undefined-func-template -DCK_TILE_FMHA_FWD_FAST_EXP2=0)
|
||||
endif()
|
||||
|
||||
# Allow comparing floating points directly in order to check sentinel values
|
||||
|
||||
Reference in New Issue
Block a user