mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-19 22:39:03 +00:00
Split the instances by architecture. (#1223)
* 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
This commit is contained in:
@@ -2,9 +2,7 @@ add_executable(client_tensor_transform_using_wrapper tensor_transform_using_wrap
|
||||
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 "gfx908" OR GPU_TARGETS MATCHES "gfx90a" OR
|
||||
GPU_TARGETS MATCHES "gfx940" OR GPU_TARGETS MATCHES "gfx941" OR
|
||||
GPU_TARGETS MATCHES "gfx942")
|
||||
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)
|
||||
|
||||
Reference in New Issue
Block a user