mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-18 12:00:07 +00:00
* start adding navi21 GEMM
* navi_gemm_km_kn_mn_fp32 compiles and passes one test.
* rename variables and functions in gridwise_gemm_dlops_v1r3
* add other 3 layouts; format instance
* adding more tuning parameters
add tuning parameters for other 3 layouts
* add gemm_dlops_f16
* tmp
* add dependence of DeviceGemm::IsSupportedArg() on arch
* minor changes
* minor changes
* minor changes
* minor changes
* minor changes
* minor changes
* minor changes
* push gemm_dlops into profiler
* minor changes
* if using xdl or dlops is moved into profiler_gemm_impl
* minor changes
* minor changes
* remove is_xdl from profile_gemm_impl
* make IsSupportedArg dependent on arch for other device_gemm
* minor changes
* minor changes
* fix a bug in f_generate_tensor_value
* add 64x64x64 for gemm_dlops_int8
* add 64x64x64 for gemm_dlops_int8
* comment out 3 layouts in gemm_dlops_int8; add 32x32x32 for gemm_dlops_int8; init A values to 1
* fix
* start fixing tuning parameters
* monir
* minor changes
* minor changes
* minor changes
* fixing
* adding example
* adding example
* adding example
* add gemm fp32 example
* clean up
* use 128x128x16 as MNK tile in navi21 gemm example
* bug fix
* fix test
* use new block c tile
* clean
* fix build
Co-authored-by: Chao Liu <chao.liu2@amd.com>
Co-authored-by: shaojiewang <wsjmessi@163.com>
[ROCm/composable_kernel commit: 40b59a63cc]
57 lines
2.5 KiB
CMake
57 lines
2.5 KiB
CMake
include_directories(BEFORE
|
|
${PROJECT_SOURCE_DIR}/include/ck
|
|
${PROJECT_SOURCE_DIR}/include/ck/utility
|
|
${PROJECT_SOURCE_DIR}/include/ck/host_utility
|
|
${PROJECT_SOURCE_DIR}/include/ck/tensor_description
|
|
${PROJECT_SOURCE_DIR}/include/ck/tensor
|
|
${PROJECT_SOURCE_DIR}/include/ck/problem_transform
|
|
${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/device
|
|
${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/grid
|
|
${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/block
|
|
${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/warp
|
|
${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/thread
|
|
${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/element
|
|
${PROJECT_SOURCE_DIR}/library/include/ck/library/host_tensor
|
|
${PROJECT_SOURCE_DIR}/library/include/ck/library/reference_tensor_operation/cpu
|
|
${PROJECT_SOURCE_DIR}/library/include/ck/library/reference_tensor_operation/gpu
|
|
${PROJECT_SOURCE_DIR}/library/include/ck/library/utility
|
|
${PROJECT_SOURCE_DIR}/external/include/half
|
|
)
|
|
|
|
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 host_tensor)
|
|
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 host_tensor)
|
|
add_dependencies(examples ${EXAMPLE_NAME})
|
|
endfunction(add_example_executable_no_testing EXAMPLE_NAME)
|
|
|
|
add_subdirectory(01_gemm)
|
|
add_subdirectory(02_gemm_alpha_beta)
|
|
add_subdirectory(03_gemm_bias_relu)
|
|
add_subdirectory(04_gemm_bias_relu_add)
|
|
add_subdirectory(06_conv2d_fwd_bias_relu)
|
|
add_subdirectory(07_conv2d_fwd_bias_relu_add)
|
|
add_subdirectory(09_convnd_fwd)
|
|
add_subdirectory(10_conv2d_bwd_data)
|
|
add_subdirectory(11_conv2d_bwd_weight)
|
|
add_subdirectory(12_reduce)
|
|
add_subdirectory(13_pool2d_fwd)
|
|
add_subdirectory(14_gemm_xdl_requant_relu_requant)
|
|
add_subdirectory(17_convnd_bwd_data_xdl)
|
|
add_subdirectory(15_grouped_gemm)
|
|
add_subdirectory(16_gemm_reduce)
|
|
add_subdirectory(18_batched_gemm_reduce)
|
|
add_subdirectory(19_binary_elementwise)
|
|
add_subdirectory(20_convnd_bwd_weight_xdl)
|