ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-15 18:42:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

add --offload-compress compiler flag (#1433)

Browse Source 
* add --offload-compress compiler flag

* only apply the --offload-compress flag to the ckProfiler

* move the --offload-compress flag back to main cmake file

* add offload-compress to target compile option of ckProfiler

---------

Co-authored-by: carlushuang <carlus.huang@amd.com>

[ROCm/composable_kernel commit: 7f57b2e02c]
This commit is contained in:
Illia Silin
2024-08-05 08:26:01 -07:00
committed by GitHub
parent a5c15d2b51
commit 1152542dab
2 changed files with 12 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
library/src/tensor_operation_instance/gpu/CMakeLists.txt
View File

@@ -87,6 +87,13 @@ function(add_instance_library INSTANCE_NAME)
endforeach()
add_library(${INSTANCE_NAME} OBJECT ${INST_OBJ})
target_compile_features(${INSTANCE_NAME} PUBLIC)
# flags to compress the library
if(NOT WIN32 AND ${hip_VERSION_FLAT} GREATER 600241132)
message("Adding --offload-compress flag for ${INSTANCE_NAME}")
target_compile_options(${INSTANCE_NAME} PRIVATE --offload-compress)
endif()
set_target_properties(${INSTANCE_NAME} PROPERTIES POSITION_INDEPENDENT_CODE ON)
clang_tidy_check(${INSTANCE_NAME})
set(result 0)

5
profiler/src/CMakeLists.txt
View File

@@ -82,6 +82,11 @@ set(PROFILER_EXECUTABLE ckProfiler)
add_executable(${PROFILER_EXECUTABLE} ${PROFILER_SOURCES})
target_compile_options(${PROFILER_EXECUTABLE} PRIVATE -Wno-global-constructors)
# flags to compress the library
if(NOT WIN32 AND ${hip_VERSION_FLAT} GREATER 600241132)
message("Adding --offload-compress flag for ${PROFILER_EXECUTABLE}")
target_compile_options(${PROFILER_EXECUTABLE} PRIVATE --offload-compress)
endif()
target_link_libraries(${PROFILER_EXECUTABLE} PRIVATE utility getopt::getopt)
target_link_libraries(${PROFILER_EXECUTABLE} PRIVATE device_gemm_instance)