mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-20 12:59:49 +00:00
fb513ac42b
* add gridwise_multi_abd
* move element_op into RunRead
* merge element_wise op with data read
* add multiABD example
* allow packed elementwise_op
* changed example
* clean
* clean
* add is_detected
* fix
* minor fix
* add scaleAdd_vec4 example
---------
Co-authored-by: Jing Zhang <jizha@amd.com>
[ROCm/composable_kernel commit: 11676c7e49]
11 lines
334 B
CMake
11 lines
334 B
CMake
if(DTYPES MATCHES "fp16" OR NOT DEFINED DTYPES)
|
|
list(APPEND gpu_list2 gfx908 gfx90a gfx940 gfx941 gfx942)
|
|
set(target 0)
|
|
foreach(gpu IN LISTS GPU_TARGETS)
|
|
if(gpu IN_LIST gpu_list2 AND target EQUAL 0)
|
|
add_example_executable(example_gemm_multiABD_xdl_fp16 gemm_multiABD_xdl_fp16.cpp)
|
|
set(target 1)
|
|
endif()
|
|
endforeach()
|
|
endif()
|