mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-17 03:19:48 +00:00
8fe0377e86
* [What] Rename the example
[Why] Prepare to add unary reduction
* Add global oparation to the parameter
* Add atomicmax
* Fix compile error
* Support atomicMax (hip library)
* Rename the reduction example
* Fix target name
* use p_d1_grid as the indicator directly
* Prevent performance issue. Let passthrough handle it.
* Implement the function template the specialize the float2
* No need to separate into two lines
* Remove empty line
* add comment
* Fix compile error due to merge from develop
* make the implementation of atomic_max / atomic_add explicit for each datatype
* Refine typo
* For future CI test
* Fix compiler error in ckProfiler
* Merge commit 'de2769e3a6695b38a20529261273ddc5cdaab2fe'
* simply use remove_pointer
* Rename type and var
* Refine example
* Modify reducemax example
* Fix bug in reduction
* Change initialize range
* Implement F64 version of atomicMax
* Move reduction code together
* Add buffer atomic_max
* Fix coding style by clang-format
* Integrate new api of DeviceGemmReduce_Xdl_CShuffle
* Integrate Batch gemm reduction
* Fix example
* fix example
* clean up
* Fix batch gemm tensor operation
* Fix coding style
* Fix template augument
* Fix clang format
* Keep flexible of different stride for each D tensor
* Fix compile error for ckProfiler
* Fix typo
* [What] Fix naming
[Why] Prepare to add out elementop
* Add DoutElementOp
Co-authored-by: Chao Liu <chao.liu2@amd.com>
Co-authored-by: rocking <chunylai@amd.com>
[ROCm/composable_kernel commit: 0ffe956ab1]
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_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)
|