ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-12 09:16:52 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
b0aab85baa7fd7fdf7883897aeea42ecc1f20779
composable_kernel/test/CMakeLists.txt
arai713 054fdb765c [CK_TILE] Stream-K operator() Reboot (#3064) 
* Persistent Stream-K Kernel Implementation

This change implements an operator() function in the
reboot::StreamKKernel class that is enabled when the Persistent flag is
set to true. In this case, the data-parallel portion and the Stream-K
portion of the kernel are fully persistent.

The changes were made in the reboot namespace. A future PR will remove
the old Stream-K kernel class and remove the reboot namespace.

* Unit Tests for Persistent Stream-K Kernel

This change contains the inital test suite for the Persitent Stream-K
Kernel. The files contain "reboot" in the name; a future PR will remove
tests for the old Stream-K Kernel and remove the "reboot" naming.

A future commit will add tests for the non-persistent kernel.

Also added estimate_num_wgs_per_tile to the StreamKTilePartitionerBase
class. This allows us to estimate the number of accumulations done per
macro tile in C to use during validation when computing relative and
absolute tolerance.

* Adding implementation for the Non-Persistent Stream-K kernel

This code is adding the operator() function for the Non-Persistent Stream-K
kernel. Persistency of the kernel is determined through a template argument.
The Non-Persistent kernel will allocate additional workgroups for the data
parallel section, leading to a different structure for processing the data
parallel and Stream-K sections.

There has been an addition to the TilePartitioner to get access to the whether
Persistent has been set to true or false in the StreamKKernel.

* Adding in the tests for the Non-Persistent Stream-K kernel

* Refactor Stream-K Reboot Unit Tests

This commit makes the following changes:
- Update test cases to determine M, N, and K based on the number of CUs.
  This ensures that each test case is one of Edge Case, SK Only, DP
Only, or DP + 2 Tile SK regardless of the architecture.
- Since the DP + 2 Tile SK test case takes long to run, this change
  moves this case into a separate .inc file and labels it as an extended
test.
- Since the extended test takes > 30 seconds to run, this test is added
  to the list of regression tests.

* Fix spelling errors in comments for test cases

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Changes based on review

Removed const volatile for typenames
Set up alias for is_tuple_t
Naming changes for clarity: GemmCommon -> BaseGemm
Moved std::enable_if_t out of template parameters and changed to a return type for operator()
Added constructor for StreamKKernelArgs to clarify UniversalGemm inheritance

---------

Co-authored-by: Emily Martins <emily.martins@amd.com>
Co-authored-by: Christopher Millette <63608002+cgmillette@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-10-27 09:14:17 -07:00

298 lines
12 KiB
CMake
Raw Blame History

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_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_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_reboot_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 "_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 ${source_name})
endforeach()
if(ARGN)
if(source_name_list MATCHES "_xdl")
list(REMOVE_ITEM TEST_TARGETS gfx900 gfx906 gfx906:xnack- gfx1030 gfx10-3-generic)
elseif(source_name_list MATCHES "_wmma")
list(REMOVE_ITEM TEST_TARGETS gfx900 gfx906 gfx906:xnack- gfx908:xnack+ gfx908:xnack- gfx90a:xnack+ gfx90a:xnack- gfx908 gfx90a gfx942 gfx1030 gfx950)
elseif(source_name_list MATCHES "_smfmac")
list(REMOVE_ITEM TEST_TARGETS gfx900 gfx906 gfx906:xnack- gfx1030 gfx1100 gfx1101 gfx1102 gfx1103 gfx1150 gfx1151 gfx1152 gfx908 gfx90a gfx1200 gfx1201 gfx10-3-generic gfx11-generic gfx12-generic)
endif()
set_source_files_properties(${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 "_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 ${source_name})
endforeach()
if(ARGN)
if(source_name_list MATCHES "_xdl")
list(REMOVE_ITEM TEST_TARGETS gfx900 gfx906 gfx906:xnack- gfx1030 gfx10-3-generic)
elseif(source_name_list MATCHES "_wmma")
list(REMOVE_ITEM TEST_TARGETS gfx900 gfx906 gfx906:xnack- gfx908:xnack+ gfx908:xnack- gfx90a:xnack+ gfx90a:xnack- gfx908 gfx90a gfx942 gfx1030 gfx950)
elseif(source_name_list MATCHES "_smfmac")
list(REMOVE_ITEM TEST_TARGETS gfx900 gfx906 gfx906:xnack- gfx1030 gfx1100 gfx1101 gfx1102 gfx1103 gfx1150 gfx1151 gfx1152 gfx908 gfx90a gfx1200 gfx1201 gfx10-3-generic gfx11-generic gfx12-generic)
elseif(source_name_list MATCHES "_mx") #only build mx example for gfx950
list(REMOVE_ITEM TEST_TARGETS gfx900 gfx906 gfx906:xnack- gfx908:xnack+ gfx908:xnack- gfx90a:xnack+ gfx90a:xnack- gfx908 gfx90a gfx942 gfx1030 gfx1100 gfx1101 gfx1102 gfx1103 gfx1150 gfx1151 gfx1152 gfx1200 gfx1201 gfx10-3-generic gfx11-generic gfx12-generic)
endif()
set_source_files_properties(${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_layernorm)
add_subdirectory(gemm_multi_abd)
add_subdirectory(gemm_split_k)
add_subdirectory(gemm_universal)
add_subdirectory(gemm_b_scale)
add_subdirectory(gemm_universal_streamk)
add_subdirectory(gemm_reduce)
add_subdirectory(gemm_universal_reduce)
add_subdirectory(batched_gemm)
add_subdirectory(batched_gemm_reduce)
add_subdirectory(batched_gemm_gemm)
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(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)
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()
add_subdirectory(position_embedding)
add_subdirectory(scatter_gather)
Reference in New Issue View Git Blame Copy Permalink