mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-15 18:42:06 +00:00
1f4d13b2b5
* parse examples inside the add_example_executable function
* fix the example 64 cmake file
* add xdl flag to the gemm_bias_softmax_gemm_permute example
* add filtering of tests based on architecture type
* enable test_grouped_gemm for gfx9 only
* enable test_transpose only for gfx9
* only linnk test_transpose if it gets built
* split the gemm instances by architectures
* split gemm_bilinear,grouped_conv_bwd_weight instances by targets
* split instances by architecture
* split grouped_conv instances by architecture
* fix clang format
* fix the if-else logic in group_conv headers
* small fix for grouped convolution instances
* fix the grouped conv bwd weight dl instances
* fix client examples
* only enable client examples 3 and 4 on gfx9
* set the gfx9 macro
* make sure the architecture macros are set by cmake
* use separate set of xdl/wmma flags for host code
* sinmplify the main cmake file
* add conv_fwd_bf8 instance declaration
[ROCm/composable_kernel commit: ae57e5938e]
11 lines
754 B
CMake
11 lines
754 B
CMake
add_executable(client_tensor_transform_using_wrapper tensor_transform_using_wrapper.cpp)
|
|
target_link_libraries(client_tensor_transform_using_wrapper PRIVATE composable_kernel::device_other_operations)
|
|
add_executable(client_wrapper_img2col wrapper_img2col.cpp)
|
|
target_link_libraries(client_wrapper_img2col PRIVATE composable_kernel::device_other_operations)
|
|
if(GPU_TARGETS MATCHES "gfx9")
|
|
add_executable(client_wrapper_basic_gemm wrapper_basic_gemm.cpp)
|
|
target_link_libraries(client_wrapper_basic_gemm PRIVATE composable_kernel::device_other_operations)
|
|
add_executable(client_wrapper_optimized_gemm wrapper_optimized_gemm.cpp)
|
|
target_link_libraries(client_wrapper_optimized_gemm PRIVATE composable_kernel::device_other_operations)
|
|
endif()
|