mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-20 04:49:54 +00:00
cba606adf6
* added working example for 5D input using 1D kernel
* example with 5D input tensor and 2d kernel - not working: issues with arguments
* added updated version of 3d device op - changed descriptors/dims
* added example file to check kernel
* fixed descriptor and isSupportedArgument stride problem
* added and modified kernel for 3d - updated tids/loop
* adding some more 5d example files
* fixed some issues
* changes made for testing
* working version: fixed error in stride for A, still a bit inefficient
* cleaned up formatting/comments
* updating formatting
* more formatting fixes
* fixing cmake, adding back gpu targets in cmake script
* adding client example
* added instances for client example
* fixed errors in client example
* implemented client ex with device_elementwise.hpp and device_elementwise_3d_impl.hpp
* removed extra files
* minor formatting and naming fixes
* adding test files and profiler
* fixing minor error
* minor fix
* removed unneccesary comments, renamed files
* updated instance list for client example, added different layout example
* removing instances
* fixed error in instance generation
* remove comments
* update profiler and client example tensor layouts
* fixed errors in test/profiler
* updated vector dim access to enable vector load
* updated test/profiler files
* updated example with 1d kernel
* updating profiler
* renamed files
---------
Co-authored-by: Jing Zhang <jizha@amd.com>
[ROCm/composable_kernel commit: 3af8c81a72]
155 lines
5.6 KiB
CMake
155 lines
5.6 KiB
CMake
include_directories(BEFORE
|
|
${PROJECT_SOURCE_DIR}/
|
|
${PROJECT_SOURCE_DIR}/profiler/include
|
|
)
|
|
|
|
include(googletest)
|
|
|
|
add_custom_target(tests)
|
|
|
|
function(add_test_executable TEST_NAME)
|
|
message("adding test ${TEST_NAME}")
|
|
set(result 1)
|
|
if(DEFINED DTYPES)
|
|
foreach(source IN LISTS ARGN)
|
|
set(test 0)
|
|
if((source MATCHES "_fp16" OR source MATCHES "_f16") AND NOT "fp16" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source MATCHES "_fp32" OR source MATCHES "_f32") AND NOT "fp32" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source MATCHES "_fp64" OR source MATCHES "_f64") AND NOT "fp64" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source MATCHES "_fp8" OR source MATCHES "_f8") AND NOT "fp8" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source MATCHES "_bf8" OR source MATCHES "_bf8") AND NOT "bf8" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source MATCHES "_bf16" OR source MATCHES "_b16") AND NOT "bf16" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source MATCHES "_int8" OR source MATCHES "_i8") AND NOT "int8" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if(test EQUAL 1)
|
|
message("removing test ${source} ")
|
|
list(REMOVE_ITEM ARGN "${source}")
|
|
endif()
|
|
endforeach()
|
|
endif()
|
|
foreach(source IN LISTS ARGN)
|
|
if(NOT DEFINED DL_KERNELS AND source MATCHES "_dl")
|
|
message("removing dl test ${source} ")
|
|
list(REMOVE_ITEM ARGN "${source}")
|
|
endif()
|
|
endforeach()
|
|
|
|
#only continue if there are some source files left on the list
|
|
if(ARGN)
|
|
add_executable(${TEST_NAME} ${ARGN})
|
|
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("add_test returns ${result}")
|
|
set(result ${result} PARENT_SCOPE)
|
|
endfunction(add_test_executable TEST_NAME)
|
|
|
|
include(GoogleTest)
|
|
|
|
function(add_gtest_executable TEST_NAME)
|
|
message("adding gtest ${TEST_NAME}")
|
|
set(result 1)
|
|
if(DEFINED DTYPES)
|
|
foreach(source IN LISTS ARGN)
|
|
set(test 0)
|
|
if((source MATCHES "_fp16" OR source MATCHES "_f16") AND NOT "fp16" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source MATCHES "_fp32" OR source MATCHES "_f32") AND NOT "fp32" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source MATCHES "_fp64" OR source MATCHES "_f64") AND NOT "fp64" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source MATCHES "_fp8" OR source MATCHES "_f8") AND NOT "fp8" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source MATCHES "_bf8" OR source MATCHES "_bf8") AND NOT "bf8" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source MATCHES "_bf16" OR source MATCHES "_b16") AND NOT "bf16" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if((source MATCHES "_int8" OR source MATCHES "_i8") AND NOT "int8" IN_LIST DTYPES)
|
|
set(test 1)
|
|
endif()
|
|
if(test EQUAL 1)
|
|
message("removing gtest ${source} ")
|
|
list(REMOVE_ITEM ARGN "${source}")
|
|
endif()
|
|
endforeach()
|
|
endif()
|
|
foreach(source IN LISTS ARGN)
|
|
if(NOT DEFINED DL_KERNELS AND source MATCHES "_dl")
|
|
message("removing dl test ${source} ")
|
|
list(REMOVE_ITEM ARGN "${source}")
|
|
endif()
|
|
endforeach()
|
|
#only continue if there are some source files left on the list
|
|
if(ARGN)
|
|
add_executable(${TEST_NAME} ${ARGN})
|
|
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)
|
|
add_test(NAME ${TEST_NAME} COMMAND $<TARGET_FILE:${TEST_NAME}>)
|
|
rocm_install(TARGETS ${TEST_NAME} COMPONENT tests)
|
|
set(result 0)
|
|
endif()
|
|
#message("add_gtest returns ${result}")
|
|
set(result ${result} PARENT_SCOPE)
|
|
endfunction(add_gtest_executable TEST_NAME)
|
|
|
|
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_layernorm)
|
|
add_subdirectory(gemm_split_k)
|
|
add_subdirectory(gemm_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(grouped_gemm)
|
|
add_subdirectory(reduce)
|
|
add_subdirectory(convnd_fwd)
|
|
add_subdirectory(convnd_bwd_data)
|
|
add_subdirectory(grouped_convnd_fwd)
|
|
add_subdirectory(grouped_convnd_bwd_weight)
|
|
add_subdirectory(block_to_ctile_map)
|
|
add_subdirectory(softmax)
|
|
add_subdirectory(normalization_fwd)
|
|
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)
|
|
if(GPU_TARGETS MATCHES "gfx11")
|
|
add_subdirectory(wmma_op)
|
|
endif()
|