mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-19 14:29:05 +00:00
8daf6ea302
* Added bias_bnorm_clamp instances. * fwd_bias_bnorm_clamp comp instances * fwd_bias_bnorm_mem_inter and mem_intra instances * fwd_bias_bnorm_merged_group_instances * fwd_bias_bnorm_clamp_conv3d_bf16 and f16 instances * Device level changes for fwd_bias_bnorm_clamp * Added the test to the regression test list. * Removed the part 2 and 2x instances * Removed the irrelevant checks in wmma * Refactored the instances to adapt to new device implementation * Updated the reference and include files * enabling tests * Added missing profiler * Added missing instance entry , deleted by mistake * Reduce bias bnorm clamp instances to only a single generic one. * Clean up cmakelists file * clang-format * Change bias bnorm clamp tests to use monotone initialization values to avoid tiny off-integer gemm results on RDNA3 from blowing up. * Renaming some instance lists and add functions to be more standardized. * Commented out non default instances. --------- Co-authored-by: kiefer <kiefer.van.teutem@streamhpc.com>
327 lines
13 KiB
CMake
327 lines
13 KiB
CMake
# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
include_directories(BEFORE
|
|
${PROJECT_SOURCE_DIR}/
|
|
${PROJECT_SOURCE_DIR}/profiler/include
|
|
)
|
|
|
|
include(gtest)
|
|
|
|
add_custom_target(tests)
|
|
|
|
# list of tests that are labelled as REGRESSION_TEST for make regression (runtime more than 30 seconds)
|
|
# all other tests are labelled as SMOKE_TEST
|
|
set(REGRESSION_TESTS
|
|
test_gemm_standalone_xdl_fp16
|
|
test_gemm_fp16
|
|
test_gemm_splitk
|
|
test_gemm_universal_wmma_fp16
|
|
test_gemm_universal_xdl_fp16
|
|
test_gemm_universal_streamk_fp16
|
|
test_gemm_universal_streamk_bf16
|
|
test_gemm_universal_streamk_fp8
|
|
test_batched_gemm_softmax_gemm_fp16
|
|
test_batched_gemm_softmax_gemm_permute_fp16
|
|
test_batched_gemm_bias_softmax_gemm_permute_fp16
|
|
test_batched_gemm_softmax_gemm_permute_bf16
|
|
test_batched_gemm_bias_softmax_gemm_permute_bf16
|
|
test_grouped_gemm_splitk
|
|
test_batched_gemm_b_scale_wmma
|
|
test_reduce_no_index
|
|
test_reduce_with_index
|
|
test_convnd_fwd
|
|
test_convnd_bwd_data
|
|
test_grouped_convnd_fwd
|
|
test_grouped_convnd_fwd_bias_bnorm_clamp
|
|
test_grouped_convnd_fwd_scaleadd_ab
|
|
test_grouped_convnd_bwd_weight
|
|
test_softmax_rank3
|
|
test_softmax_rank4
|
|
test_batchnorm_fwd_rank_4
|
|
test_batchnorm_bwd_rank_4
|
|
test_grouped_convnd_bwd_data_xdl
|
|
test_grouped_convnd_bwd_data_wmma
|
|
test_grouped_convnd_bwd_data_wmma_large_cases
|
|
test_grouped_conv_bwd_data_wmma_scale
|
|
test_conv_tensor_rearrange
|
|
test_gemm_mx
|
|
test_ck_tile_batched_transpose
|
|
test_ck_tile_fmha_bwd_fp32
|
|
test_ck_tile_fmha_bwd_bf16
|
|
test_ck_tile_fmha_bwd_fp16
|
|
test_ck_tile_fmha_fwd_fp32
|
|
test_ck_tile_fmha_fwd_bf16
|
|
test_ck_tile_fmha_fwd_fp16
|
|
test_ck_tile_fmha_fwd_fp8
|
|
test_ck_tile_streamk_extended
|
|
)
|
|
|
|
function(add_test_executable TEST_NAME)
|
|
message(DEBUG "adding test ${TEST_NAME}")
|
|
set(result 1)
|
|
if(DEFINED DTYPES)
|
|
foreach(source IN LISTS ARGN)
|
|
get_filename_component(source_name ${source} NAME)
|
|
set(test 0)
|
|
if((source_name MATCHES "_fp16|_f16") AND NOT "fp16" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source_name MATCHES "_fp32|_f32") AND NOT "fp32" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source_name MATCHES "_tf32|_tf32") AND NOT "tf32" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source_name MATCHES "_fp64|_f64") AND NOT "fp64" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source_name MATCHES "_fp8|_f8") AND NOT "fp8" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source_name MATCHES "_bf8|_bf8") AND NOT "bf8" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source_name MATCHES "_bf16|_b16") AND NOT "bf16" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source_name MATCHES "_int8|_i8") AND NOT "int8" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if(test EQUAL 1)
|
|
message(DEBUG "removing test ${source} ")
|
|
list(REMOVE_ITEM ARGN "${source}")
|
|
endif()
|
|
endforeach()
|
|
endif()
|
|
|
|
set(TEST_TARGETS ${SUPPORTED_GPU_TARGETS})
|
|
|
|
foreach(source IN LISTS ARGN)
|
|
get_filename_component(source_name ${source} NAME)
|
|
if(NOT DEFINED DPP_KERNELS AND source_name MATCHES "_dpp")
|
|
message(DEBUG "removing dpp test ${source} ")
|
|
list(REMOVE_ITEM ARGN "${source}")
|
|
endif()
|
|
if(NOT DEFINED DL_KERNELS AND source_name MATCHES "_dl")
|
|
message(DEBUG "removing dl test ${source} ")
|
|
list(REMOVE_ITEM ARGN "${source}")
|
|
endif()
|
|
if(NOT TEST_TARGETS MATCHES "gfx9|gfx11|gfx12" AND source_name MATCHES "xdl")
|
|
message(DEBUG "removing xdl test ${source} ")
|
|
list(REMOVE_ITEM ARGN "${source}")
|
|
endif()
|
|
if(NOT TEST_TARGETS MATCHES "gfx11|gfx12" AND source_name MATCHES "wmma")
|
|
message(DEBUG "removing wmma test ${source} ")
|
|
list(REMOVE_ITEM ARGN "${source}")
|
|
endif()
|
|
endforeach()
|
|
#only continue if there are some source files left on the list
|
|
set(source_name_list "")
|
|
foreach(source IN LISTS ARGN)
|
|
get_filename_component(source_name ${source} NAME)
|
|
list(APPEND source_name_list ${source_name})
|
|
endforeach()
|
|
if(ARGN)
|
|
if(source_name_list MATCHES "_xdl")
|
|
list(REMOVE_ITEM TEST_TARGETS gfx900 gfx906 gfx906:xnack- gfx1030 gfx10-3-generic)
|
|
elseif(source_name_list MATCHES "_wmma")
|
|
list(REMOVE_ITEM TEST_TARGETS gfx900 gfx906 gfx906:xnack- gfx908:xnack+ gfx908:xnack- gfx90a:xnack+ gfx90a:xnack- gfx908 gfx90a gfx942 gfx1030 gfx950)
|
|
elseif(source_name_list MATCHES "_smfmac")
|
|
list(REMOVE_ITEM TEST_TARGETS gfx900 gfx906 gfx906:xnack- gfx1030 gfx1100 gfx1101 gfx1102 gfx1103 gfx1150 gfx1151 gfx1152 gfx1153 gfx908 gfx90a gfx1200 gfx1201 gfx10-3-generic gfx11-generic gfx12-generic)
|
|
endif()
|
|
set_source_files_properties(${ARGN} PROPERTIES LANGUAGE HIP)
|
|
add_executable(${TEST_NAME} ${ARGN})
|
|
set_property(TARGET ${TEST_NAME} PROPERTY HIP_ARCHITECTURES ${TEST_TARGETS} )
|
|
target_link_libraries(${TEST_NAME} PRIVATE getopt::getopt)
|
|
add_test(NAME ${TEST_NAME} COMMAND $<TARGET_FILE:${TEST_NAME}>)
|
|
add_dependencies(tests ${TEST_NAME})
|
|
add_dependencies(check ${TEST_NAME})
|
|
rocm_install(TARGETS ${TEST_NAME} COMPONENT tests)
|
|
set(result 0)
|
|
endif()
|
|
message(DEBUG "add_test returns ${result}")
|
|
set(result ${result} PARENT_SCOPE)
|
|
if(result EQUAL 0 AND NOT "${TEST_NAME}" IN_LIST REGRESSION_TESTS)
|
|
set_tests_properties(${TEST_NAME} PROPERTIES LABELS "SMOKE_TEST")
|
|
add_dependencies(smoke ${TEST_NAME})
|
|
elseif(result EQUAL 0 AND "${TEST_NAME}" IN_LIST REGRESSION_TESTS)
|
|
set_tests_properties(${TEST_NAME} PROPERTIES LABELS "REGRESSION_TEST")
|
|
add_dependencies(regression ${TEST_NAME})
|
|
endif()
|
|
endfunction()
|
|
|
|
function(add_gtest_executable TEST_NAME)
|
|
message(DEBUG "adding gtest ${TEST_NAME}")
|
|
set(result 1)
|
|
if(DEFINED DTYPES)
|
|
foreach(source IN LISTS ARGN)
|
|
get_filename_component(source_name ${source} NAME)
|
|
set(test 0)
|
|
if((source_name MATCHES "_fp16|_f16") AND NOT "fp16" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source_name MATCHES "_fp32|_f32") AND NOT "fp32" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source_name MATCHES "_tf32|_tf32") AND NOT "tf32" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source_name MATCHES "_fp64|_f64") AND NOT "fp64" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source_name MATCHES "_fp8|_f8") AND NOT "fp8" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source_name MATCHES "_bf8|_bf8") AND NOT "bf8" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source_name MATCHES "_bf16|_b16") AND NOT "bf16" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source_name MATCHES "_int8|_i8") AND NOT "int8" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if(test EQUAL 1)
|
|
message(DEBUG "removing gtest ${source} ")
|
|
list(REMOVE_ITEM ARGN "${source}")
|
|
endif()
|
|
endforeach()
|
|
endif()
|
|
|
|
set(TEST_TARGETS ${SUPPORTED_GPU_TARGETS})
|
|
|
|
foreach(source IN LISTS ARGN)
|
|
get_filename_component(source_name ${source} NAME)
|
|
if(NOT DEFINED DL_KERNELS AND source_name MATCHES "_dl")
|
|
message(DEBUG "removing dl test ${source} ")
|
|
list(REMOVE_ITEM ARGN "${source}")
|
|
endif()
|
|
if(NOT TEST_TARGETS MATCHES "gfx9|gfx11|gfx12" AND source_name MATCHES "xdl")
|
|
message(DEBUG "removing xdl test ${source} ")
|
|
list(REMOVE_ITEM ARGN "${source}")
|
|
endif()
|
|
if(NOT TEST_TARGETS MATCHES "gfx95" AND source_name MATCHES "mx_")
|
|
message(DEBUG "removing microscaling test ${source} ")
|
|
list(REMOVE_ITEM ARGN "${source}")
|
|
endif()
|
|
if(NOT TEST_TARGETS MATCHES "gfx11|gfx12" AND source_name MATCHES "wmma")
|
|
message(DEBUG "removing wmma test ${source} ")
|
|
list(REMOVE_ITEM ARGN "${source}")
|
|
endif()
|
|
endforeach()
|
|
|
|
#only continue if there are some source files left on the list
|
|
set(source_name_list "")
|
|
foreach(source IN LISTS ARGN)
|
|
get_filename_component(source_name ${source} NAME)
|
|
list(APPEND source_name_list ${source_name})
|
|
endforeach()
|
|
if(ARGN)
|
|
if(source_name_list MATCHES "_xdl")
|
|
list(REMOVE_ITEM TEST_TARGETS gfx900 gfx906 gfx906:xnack- gfx1030 gfx10-3-generic)
|
|
elseif(source_name_list MATCHES "_wmma")
|
|
list(REMOVE_ITEM TEST_TARGETS gfx900 gfx906 gfx906:xnack- gfx908:xnack+ gfx908:xnack- gfx90a:xnack+ gfx90a:xnack- gfx908 gfx90a gfx942 gfx1030 gfx950)
|
|
elseif(source_name_list MATCHES "_smfmac")
|
|
list(REMOVE_ITEM TEST_TARGETS gfx900 gfx906 gfx906:xnack- gfx1030 gfx1100 gfx1101 gfx1102 gfx1103 gfx1150 gfx1151 gfx1152 gfx1153 gfx908 gfx90a gfx1200 gfx1201 gfx10-3-generic gfx11-generic gfx12-generic)
|
|
elseif(source_name_list MATCHES "_mx") #only build mx example for gfx950
|
|
list(REMOVE_ITEM TEST_TARGETS gfx900 gfx906 gfx906:xnack- gfx908:xnack+ gfx908:xnack- gfx90a:xnack+ gfx90a:xnack- gfx908 gfx90a gfx942 gfx1030 gfx1100 gfx1101 gfx1102 gfx1103 gfx1150 gfx1151 gfx1152 gfx1153 gfx1200 gfx1201 gfx10-3-generic gfx11-generic gfx12-generic)
|
|
endif()
|
|
set_source_files_properties(${ARGN} PROPERTIES LANGUAGE HIP)
|
|
add_executable(${TEST_NAME} ${ARGN})
|
|
set_property(TARGET ${TEST_NAME} PROPERTY HIP_ARCHITECTURES ${TEST_TARGETS} )
|
|
add_dependencies(tests ${TEST_NAME})
|
|
add_dependencies(check ${TEST_NAME})
|
|
|
|
# suppress gtest warnings
|
|
target_compile_options(${TEST_NAME} PRIVATE -Wno-global-constructors -Wno-undef)
|
|
target_link_libraries(${TEST_NAME} PRIVATE gtest_main getopt::getopt)
|
|
add_test(NAME ${TEST_NAME} COMMAND $<TARGET_FILE:${TEST_NAME}>)
|
|
rocm_install(TARGETS ${TEST_NAME} COMPONENT tests)
|
|
set(result 0)
|
|
endif()
|
|
message(DEBUG "add_gtest returns ${result}")
|
|
set(result ${result} PARENT_SCOPE)
|
|
if(result EQUAL 0 AND NOT "${TEST_NAME}" IN_LIST REGRESSION_TESTS)
|
|
set_tests_properties(${TEST_NAME} PROPERTIES LABELS "SMOKE_TEST")
|
|
add_dependencies(smoke ${TEST_NAME})
|
|
elseif(result EQUAL 0 AND "${TEST_NAME}" IN_LIST REGRESSION_TESTS)
|
|
set_tests_properties(${TEST_NAME} PROPERTIES LABELS "REGRESSION_TEST")
|
|
add_dependencies(regression ${TEST_NAME})
|
|
endif()
|
|
endfunction()
|
|
|
|
add_compile_options(-Wno-c++20-extensions)
|
|
add_subdirectory(ck_tile)
|
|
add_subdirectory(magic_number_division)
|
|
add_subdirectory(space_filling_curve)
|
|
add_subdirectory(conv_util)
|
|
add_subdirectory(reference_conv_fwd)
|
|
add_subdirectory(gemm)
|
|
add_subdirectory(gemm_add)
|
|
add_subdirectory(gemm_bias_add_reduce)
|
|
add_subdirectory(gemm_blockscale_wp)
|
|
add_subdirectory(gemm_layernorm)
|
|
add_subdirectory(gemm_multi_abd)
|
|
add_subdirectory(gemm_multiply_multiply_wp)
|
|
add_subdirectory(gemm_split_k)
|
|
add_subdirectory(gemm_universal)
|
|
add_subdirectory(gemm_universal_preshuffle)
|
|
add_subdirectory(gemm_ab_scale)
|
|
add_subdirectory(gemm_b_scale)
|
|
add_subdirectory(gemm_universal_streamk)
|
|
add_subdirectory(gemm_reduce)
|
|
add_subdirectory(gemm_universal_reduce)
|
|
add_subdirectory(batched_contraction)
|
|
add_subdirectory(batched_gemm)
|
|
add_subdirectory(batched_gemm_reduce)
|
|
add_subdirectory(batched_gemm_gemm)
|
|
add_subdirectory(batched_gemm_multiple_d_gemm_multiple_d)
|
|
add_subdirectory(batched_gemm_softmax_gemm)
|
|
add_subdirectory(batched_gemm_softmax_gemm_permute)
|
|
add_subdirectory(batched_gemm_b_scale)
|
|
add_subdirectory(grouped_gemm)
|
|
add_subdirectory(grouped_gemm_tile_loop)
|
|
add_subdirectory(reduce)
|
|
add_subdirectory(convnd_fwd)
|
|
add_subdirectory(convnd_bwd_data)
|
|
add_subdirectory(grouped_convnd_fwd)
|
|
add_subdirectory(grouped_convnd_fwd_activation)
|
|
add_subdirectory(grouped_convnd_bwd_weight)
|
|
add_subdirectory(block_to_ctile_map)
|
|
add_subdirectory(softmax)
|
|
add_subdirectory(normalization_fwd)
|
|
add_subdirectory(normalization_bwd_data)
|
|
add_subdirectory(normalization_bwd_gamma_beta)
|
|
add_subdirectory(data_type)
|
|
add_subdirectory(elementwise_normalization)
|
|
add_subdirectory(batchnorm)
|
|
add_subdirectory(contraction)
|
|
add_subdirectory(pool)
|
|
add_subdirectory(batched_gemm_multi_d)
|
|
add_subdirectory(grouped_convnd_bwd_data)
|
|
add_subdirectory(conv_tensor_rearrange)
|
|
add_subdirectory(transpose)
|
|
add_subdirectory(permute_scale)
|
|
add_subdirectory(wrapper)
|
|
add_subdirectory(quantization)
|
|
add_subdirectory(device_memory)
|
|
if(SUPPORTED_GPU_TARGETS MATCHES "gfx11")
|
|
add_subdirectory(wmma_op)
|
|
endif()
|
|
if(SUPPORTED_GPU_TARGETS MATCHES "gfx942" OR SUPPORTED_GPU_TARGETS MATCHES "gfx950") # smfmac needs ROCm6.2
|
|
add_subdirectory(smfmac_op)
|
|
endif()
|
|
if(SUPPORTED_GPU_TARGETS MATCHES "gfx950")
|
|
add_subdirectory(mx_mfma_op)
|
|
add_subdirectory(gemm_mx)
|
|
endif()
|
|
if(SUPPORTED_GPU_TARGETS MATCHES "gfx12")
|
|
add_subdirectory(s_prefetch_op)
|
|
endif()
|
|
add_subdirectory(position_embedding)
|
|
add_subdirectory(scatter_gather)
|
|
add_subdirectory(gpu_reference)
|
|
add_subdirectory(util)
|
|
add_subdirectory(gpu_verification)
|