mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-11 00:40:09 +00:00
bba085d2b5
* refactor cmake files for the tests * refactor cmake files for examples * fix cmake for gemm example * fix the cmake file for all examples * add splitting by data types in gemm_splitk instance header * rename test to reflect only dl instances are used * clean up CI workspace, update cmake for instances * change the jenkinsfile syntax * build all instances except DL on gfx11 * move workspace cleanup after stages * clean up workspace after every stage * isolate data types in grouped_conv_fwd header * isolate dl instances for grouped_conv2d_fwd * fix syntax * fix cmake and batchnorm instances * fix typo * fix reduction instances * fix grouped_conv headers * fix syntax * replace parsing logic for instances, replace bfp16 with bf16 * fix the client examples build * clean up DTYPES from instances cmake files * update the parsing logic in cmake files * make an exception for reduction kernels * update few remaining cmake files to handle DTYPES * fix syntax * fix cmake conflicts * replace f8 with fp8 test name * resolve conflicts for dpp instances
19 lines
809 B
CMake
19 lines
809 B
CMake
list(APPEND gpu_list1 gfx908 gfx90a gfx940 gfx941 gfx942)
|
|
|
|
set(target 0)
|
|
foreach(gpu IN LISTS GPU_TARGETS)
|
|
if(gpu IN_LIST gpu_list1 AND target EQUAL 0)
|
|
add_example_executable(example_batched_gemm_gemm_xdl_fp32 batched_gemm_gemm_xdl_fp32.cpp)
|
|
add_example_executable(example_batched_gemm_gemm_xdl_fp16 batched_gemm_gemm_xdl_fp16.cpp)
|
|
add_example_executable(example_batched_gemm_gemm_xdl_bf16 batched_gemm_gemm_xdl_bf16.cpp)
|
|
if(USE_BITINT_EXTENSION_INT4)
|
|
add_example_executable(example_batched_gemm_gemm_xdl_int4 batched_gemm_gemm_xdl_int4.cpp)
|
|
endif(USE_BITINT_EXTENSION_INT4)
|
|
set(target 1)
|
|
endif()
|
|
endforeach()
|
|
|
|
if(NOT GPU_TARGETS MATCHES "gfx94" AND NOT GPU_TARGETS MATCHES "gfx1")
|
|
add_example_executable(example_batched_gemm_gemm_xdl_int8 batched_gemm_gemm_xdl_int8.cpp)
|
|
endif()
|