mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-16 02:54:21 +00:00
a149a48358
* Add elementwise operation kernel and example
* Add comment
* Add template argument of dim . Prepare to support multiple dimension
* Rename example
* Support 1 dimension
* Add static assert
* Add comment
* Extract pad
* Remove redundant argument
* Support any dimension for elementwise operation
* Remove line
* Let it be the multiple number of CU
* Move thread per block to the parameter of constructor
* rename threadPerBlock with blockSize
* Support double
* rename kernel function name
* remove redundant include header
* Refine type
* Need to the final dimension
* Refine variable name
* Refine type
* Use index_t instead of int in API
Co-authored-by: rocking <chunylai@amd.com>
[ROCm/composable_kernel commit: aafc3ac27a]
55 lines
2.4 KiB
CMake
55 lines
2.4 KiB
CMake
include_directories(BEFORE
|
|
${PROJECT_SOURCE_DIR}/include/ck
|
|
${PROJECT_SOURCE_DIR}/include/ck/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 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)
|