mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-11 17:00:18 +00:00
15c89e81f0
* initial stub for standalone softmax * start device_softmax_mk_to_mk as a wrapper to device_reduce_mk_to_m * host softmax validates * compiles; to implement beta scaling * use NaN trick to efficiently ignore OOB values during sum of exponentials * freeload device_reduce's utility functions * clean up interface * adding prior value (beta scaling) * remove restriction related to perf considerations * apply clang-format * clean; disable diagnostics * resolve conflicts * add exp wrapper * honor HostTensorDesc interface; allow implicit cast from different vector<T> type * test softmax for fp16/fp32 * update readme * amend commit NaN trick * remove redundant param added during development * format * replace ScalarDataType with AccDataType * separate out test programs by precision type * move softmax sample code to its own folder * format * keep up with recent changes in reduction API * remove extra header
60 lines
2.6 KiB
CMake
60 lines
2.6 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_add_add_fastgelu)
|
|
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(15_grouped_gemm)
|
|
add_subdirectory(16_gemm_reduce)
|
|
add_subdirectory(17_convnd_bwd_data_xdl)
|
|
add_subdirectory(18_batched_gemm_reduce)
|
|
add_subdirectory(19_binary_elementwise)
|
|
add_subdirectory(20_convnd_bwd_weight_xdl)
|
|
add_subdirectory(21_gemm_layernorm)
|
|
add_subdirectory(22_cgemm)
|
|
add_subdirectory(23_softmax)
|