mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-20 12:59:49 +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
[ROCm/composable_kernel commit: ae57e5938e]
This commit is contained in:
@@ -1,12 +1,3 @@
|
||||
# dlops
|
||||
add_example_executable(example_gemm_dl_quantization_int8 gemm_dl_quantization_int8.cpp)
|
||||
# xdlops
|
||||
list(APPEND gpu_list gfx908 gfx90a gfx940 gfx941 gfx942)
|
||||
set(target 0)
|
||||
foreach(gpu IN LISTS GPU_TARGETS)
|
||||
if(gpu IN_LIST gpu_list AND target EQUAL 0)
|
||||
add_example_executable(example_gemm_xdl_bias_relu_quantization_int8 gemm_xdl_bias_relu_quantization_int8.cpp)
|
||||
add_example_executable(example_gemm_xdl_quantization_int8 gemm_xdl_quantization_int8.cpp)
|
||||
set(target 1)
|
||||
endif()
|
||||
endforeach()
|
||||
add_example_executable(example_gemm_xdl_bias_relu_quantization_int8 gemm_xdl_bias_relu_quantization_int8.cpp)
|
||||
add_example_executable(example_gemm_xdl_quantization_int8 gemm_xdl_quantization_int8.cpp)
|
||||
|
||||
Reference in New Issue
Block a user