mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-13 17:55:48 +00:00
8a4253baaf
* add fused addition lyernorm * add fused addition lyernorm * changed CMakelist * removed annotates * modified descriptor of C * fixed bug in gridwise add layernorm * format the files * modified name from add&layernorm into elementwise&layernorm * created fused elementwise layernorm branch * change input into tuple type * add sweep once to reduce load & read of C from global memory * modified Argument api * modified way to malloc c in global memory * changed gamma and beta to m_k_desc * fixed bug when sweep once and move CDataType when define device level struct * add src dim for gamma and beta * implement optimization for coalesced * delete a annotation line * fixed some bug to meet the requirements of ck * add bandwidth computing in example, and fixed the time unit * move device_elementwise_layernorm_impl.hpp into device/impl * fixed bug in device_elementwise_layernorm_impl.hpp * changed name from layernorm into normalization * clang-format the changed files * changed the names * moved immidiate results into lds, it become faster in non-sweeponce cases * changed naming of C into X to make the defination more clear * changed naming in example * add tests for elementwise normalization * move example_elementwise_layernorm_blockwise into folder 44_elementwise_normalization * move test_elementwise_layernorm_fp16 into new folder * move elementwise_normalization_instances into a new folder * add more tests in test_elementwise_layernorm_fp16.cpp * added some corner cases in test * fixed method to compute lds size for matrix X * changed name of 44_elementwise_normalization into 45_elementwise_normalization * modified some comments * modified some other confused comments * reduce redundant tests in test_elementwise_layernorm_fp16.cpp
56 lines
1.8 KiB
CMake
56 lines
1.8 KiB
CMake
include_directories(BEFORE
|
|
${PROJECT_SOURCE_DIR}/
|
|
)
|
|
|
|
include(googletest)
|
|
|
|
add_custom_target(tests)
|
|
|
|
function(add_test_executable TEST_NAME)
|
|
message("adding test ${TEST_NAME}")
|
|
add_executable(${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)
|
|
endfunction(add_test_executable TEST_NAME)
|
|
|
|
include(GoogleTest)
|
|
|
|
function(add_gtest_executable TEST_NAME)
|
|
message("adding gtest ${TEST_NAME}")
|
|
add_executable(${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)
|
|
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_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_weight)
|
|
add_subdirectory(convnd_bwd_data)
|
|
add_subdirectory(grouped_convnd_fwd)
|
|
add_subdirectory(block_to_ctile_map)
|
|
add_subdirectory(softmax)
|
|
add_subdirectory(normalization)
|
|
add_subdirectory(data_type)
|
|
add_subdirectory(elementwise_normalization)
|