mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-19 14:29:05 +00:00
46f1d740f0
* wip: grouped_gemm implementation based on wmma kernel + example for fp16 * chore: clean up grouped_gem_wmma_splitk_fp16 example * chore: add cmake options to fully disable XDL or WMMA kernels * feat: add tests for grouped gemma wmma instances for f16 and bf16 (all layouts) * chore: add grouped gemm wmma bf16 example * refactor: reuse more code between instance factory functions * chore: turn test failure if not all batch sizes are supported into a warning * chore: made failing of test on unsupported instances conditional to not break old tests * chore: add log message to failure case where AK1/BK1/KBatch is too high for K value * fix: issue with new overloads of GridwiseGemm_wmma_cshuffle_v3::Run() * fix: stray comma after parameter list * fix: compilation issues on RDNA3 and tests failing due to unsupported problems still being ran * chore: update copyright in header comments * nit: minor feebdack * refactor: unified XDL / wma tests * fix: properly disable FP8 instances when ONLY targeting gfx11 * refactor: add v3 suffix to grouped_gemm device struct name * fix: small typos in example code * fix: fully exclude xdl/wmma instances when using the corresponding cmake flags * chore: remove unused destructor and added pipeline support checks to remove unnecessary paths * fix: make sure to not add instance library to group if library was skipped * fix: make sure xdl grouped gemm doesnt fail the new test * fix: explicitly exclude test if no xdl/wmma support, as pattern matching fails in this case * fix: examples not working since dependent types and functions were moved to ck namespace in develop * fix: tests failing when compiling for just gfx11 due to trying to run unsupported instances * chore: replace/add copyright headers with new format
22 lines
1.1 KiB
CMake
22 lines
1.1 KiB
CMake
# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
add_custom_target(test_grouped_gemm)
|
|
|
|
# NOTE: We test for XDL/WMMA support here instead of relying on the usual pattern matching in the parent CMakeLists. This is necessary
|
|
# as these tests are universal and dont have "xdl" or "wmma" in their name to signify their target arch. But they will fail to link
|
|
# the instance library if there's no instances present for the current arch.
|
|
if (CK_USE_XDL OR CK_USE_WMMA)
|
|
add_gtest_executable(test_grouped_gemm_splitk test_grouped_gemm_splitk.cpp)
|
|
if(result EQUAL 0)
|
|
target_link_libraries(test_grouped_gemm_splitk PRIVATE utility device_grouped_gemm_instance)
|
|
add_dependencies(test_grouped_gemm test_grouped_gemm_splitk)
|
|
endif()
|
|
endif()
|
|
|
|
add_gtest_executable(test_grouped_gemm_interface test_grouped_gemm_interface_xdl.cpp)
|
|
if(result EQUAL 0)
|
|
target_link_libraries(test_grouped_gemm_interface PRIVATE utility device_grouped_gemm_instance)
|
|
add_dependencies(test_grouped_gemm test_grouped_gemm_interface)
|
|
endif()
|