mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-07-01 04:07:56 +00:00
4ebc48a3cd
* Summary:
- Refactor epilogue (with CShuffle) to support fused operations:
- EpilogueCShuffleBase holds common parts
- EpilogueCShuffle: runs CShuffle and write out
- EpilogueWelfordCShuffle: holds Welford specific arguments, runs CShuffle, write out, Welford first part and Welford write out
- Extend thread transfer v7r3:
- Support for intermediate data type different from src and dst type
- New functionality to write to dst buffer and keep data (to be able to use them for additional operations)
* Adress review comments
9 lines
434 B
CMake
9 lines
434 B
CMake
if(GPU_TARGETS MATCHES "gfx9|gfx11|gfx12")
|
|
add_gtest_executable(test_gemm_add_relu_add_layernorm_fp16 test_gemm_add_relu_add_layernorm_fp16.cpp)
|
|
if(result EQUAL 0)
|
|
add_custom_target(test_gemm_layernorm)
|
|
target_link_libraries(test_gemm_add_relu_add_layernorm_fp16 PRIVATE utility device_gemm_add_relu_add_layernorm_instance)
|
|
add_dependencies(test_gemm_layernorm test_gemm_add_relu_add_layernorm_fp16)
|
|
endif()
|
|
endif()
|