mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-19 04:19:36 +00:00
9d42129ff3
* refactor
* start
* add device gemm file
* add BatchStrideD0
* add stridd0
* add gridwise file
* add d0 parameters to gridwise gemm
* add c layout transformer
* add d0 threadwise copy
* init kernel
* init kernel
* regular code
* nm desc put to out
* kernel parameter can not use reference
* host add bias+gelu
* run right for bias+gelu
* change AddFastGelu into another file
* interface add d1 bias parameters
* add d1 parameter to argument
* add d1 parameter to gridwise
* first all code,not verify
* gelu change to relu and GetElementSpaceSize bug
* add instance
* start add to ckprofiler
* ckprofiler finish code
* change input parameter for ckProfiler
* fix host bias+gelu bug
* show help for ckProfiler
* fix bug for lunch kernel ignore parametes
* add pad and fix about bug
* mutiple d0
* add dynamic d0_element_op
* change profiler and instance to mutiple d0
* example have 2 d0
* remove some comments not using
* change 2 d0 have self parameters
* change d element_op name
* change class name(multiple_d)
* fix bug
* fix bug that don't find file
* update profiler
* refactor
* update profiler
* clean
* revert example change
* add gon layout
* optimize parameter for gno
* add gon to gemm+gemm
* change helping input parameters
* change to GemmPadder_v2
* using ForEach
* fix gb_per_sec
Co-authored-by: Chao Liu <lc.roy86@gmail.com>
Co-authored-by: ltqin <letaoqin@amd.com>
[ROCm/composable_kernel commit: 370efa6c08]
57 lines
2.1 KiB
CMake
57 lines
2.1 KiB
CMake
include_directories(BEFORE
|
|
${PROJECT_SOURCE_DIR}/include
|
|
${PROJECT_SOURCE_DIR}/library/include
|
|
)
|
|
|
|
add_custom_target(examples)
|
|
|
|
function(add_example_executable EXAMPLE_NAME FILE_NAME)
|
|
message("adding example ${EXAMPLE_NAME}")
|
|
add_executable(${EXAMPLE_NAME} ${FILE_NAME})
|
|
target_link_libraries(${EXAMPLE_NAME} PRIVATE utility)
|
|
add_test(NAME ${EXAMPLE_NAME} COMMAND $<TARGET_FILE:${EXAMPLE_NAME}> ${ARGN})
|
|
add_dependencies(examples ${EXAMPLE_NAME})
|
|
add_dependencies(check ${EXAMPLE_NAME})
|
|
endfunction(add_example_executable EXAMPLE_NAME)
|
|
|
|
function(add_example_executable_no_testing EXAMPLE_NAME FILE_NAME)
|
|
message("adding example ${EXAMPLE_NAME}")
|
|
add_executable(${EXAMPLE_NAME} ${FILE_NAME})
|
|
target_link_libraries(${EXAMPLE_NAME} PRIVATE utility)
|
|
add_dependencies(examples ${EXAMPLE_NAME})
|
|
endfunction(add_example_executable_no_testing EXAMPLE_NAME)
|
|
|
|
add_subdirectory(01_gemm)
|
|
add_subdirectory(02_gemm_bilinear)
|
|
add_subdirectory(03_gemm_bias_relu)
|
|
add_subdirectory(04_gemm_add_add_fastgelu)
|
|
add_subdirectory(09_convnd_fwd)
|
|
add_subdirectory(10_convnd_fwd_multiple_d_multiple_reduce)
|
|
add_subdirectory(12_reduce)
|
|
add_subdirectory(13_pool2d_fwd)
|
|
add_subdirectory(14_gemm_xdl_requant_relu_requant)
|
|
add_subdirectory(15_grouped_gemm)
|
|
add_subdirectory(16_gemm_multi_d_multi_reduces)
|
|
add_subdirectory(17_convnd_bwd_data)
|
|
add_subdirectory(18_batched_gemm_reduce)
|
|
add_subdirectory(19_binary_elementwise)
|
|
add_subdirectory(20_convnd_bwd_weight)
|
|
add_subdirectory(21_gemm_layernorm)
|
|
add_subdirectory(22_cgemm)
|
|
add_subdirectory(23_softmax)
|
|
add_subdirectory(24_batched_gemm)
|
|
add_subdirectory(25_gemm_bias_e_permute)
|
|
add_subdirectory(26_contraction)
|
|
add_subdirectory(27_layernorm)
|
|
add_subdirectory(28_grouped_gemm_bias_e_permute)
|
|
add_subdirectory(29_batched_gemm_bias_e_permute)
|
|
add_subdirectory(30_grouped_convnd_fwd_bias_relu_add)
|
|
add_subdirectory(31_batched_gemm_gemm)
|
|
add_subdirectory(32_batched_gemm_scale_softmax_gemm)
|
|
add_subdirectory(33_multiple_reduce)
|
|
add_subdirectory(34_batchnorm)
|
|
add_subdirectory(35_splitK_gemm)
|
|
add_subdirectory(36_sparse_embedding)
|
|
add_subdirectory(37_batched_gemm_add_add_relu_gemm_add)
|
|
add_subdirectory(41_grouped_conv_conv_fwd)
|