mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 02:02:46 +00:00
d6a0d8efcd
* fix relu
* clean up
* clean up
* adding 1x1 conv
* adding 1x1 conv
* added 1x1 conv
* refactor
* refactor
* refactor
* added profiler for conv+bias+relu+add
* clean up
* adding conv+bias+relu
* adding conv+bias+relu
* added conv+bias+relu
* Update README.md
* update cpu verification
* adding c shuffle
* update static_tensor for dealing with invalid element
* adding c shuffle
* debugging
* fix bug
* convert to fp16 before shuffle
* shuffle more than one M/NRepeat
* clean up
* remove coordinate step hack from GridwiseGemm_k0mk1_k0nk1_mn_xdlops_v3r1
* clean up
* remove coordinate step hack from all gridwise gemm xdl
* clean up coordinate step hack
* clean up coordinate step hack
* ThreadwiseTensorSliceTransfer_v3r2 support pointwise op on both src and dst
* adding output shuffle in conv+bias+relu+add
* update
* added conv+bias+relu+add with c shuffle
* added conv+bias+relu+add with c shuffle
* fix forward_sweep bugs in threadwise copy
* clean up
* refactor
* clean up
* clean up
* added conv_c_shuffle+bias_relu
* clean up
* added conv+bias+relu+atomic_add
* clean up
* clean up
* clean up
* clean up
* clean up
* clean up
* misc fixes; add 1x1 specialization
* clean up
* delete unused device op
* clean up
* add support for odd C value
[ROCm/composable_kernel commit: acbd7bd7c5]
34 lines
1.9 KiB
CMake
34 lines
1.9 KiB
CMake
include_directories(BEFORE
|
|
${PROJECT_SOURCE_DIR}
|
|
${PROJECT_SOURCE_DIR}/host/host_tensor/include
|
|
${PROJECT_SOURCE_DIR}/host/device/include
|
|
${PROJECT_SOURCE_DIR}/device_operation/include
|
|
${PROJECT_SOURCE_DIR}/composable_kernel/include
|
|
${PROJECT_SOURCE_DIR}/composable_kernel/include/utility
|
|
${PROJECT_SOURCE_DIR}/composable_kernel/include/tensor_description
|
|
${PROJECT_SOURCE_DIR}/composable_kernel/include/tensor_operation
|
|
${PROJECT_SOURCE_DIR}/composable_kernel/include/problem_transform
|
|
${PROJECT_SOURCE_DIR}/external/rocm/include
|
|
)
|
|
|
|
set(GEMM_XDL_SOURCE 1_gemm_xdl/gemm_xdl.cpp)
|
|
set(GEMM_XDL_BIAS_RELU_ADD_SOURCE 3_gemm_xdl_bias_relu_add/gemm_xdl_bias_relu_add.cpp)
|
|
set(CONV2D_FWD_XDL_SOURCE 4_conv2d_fwd_xdl/conv2d_fwd_xdl.cpp)
|
|
set(CONV2D_FWD_XDL_BIAS_RELU_SOURCE 5_conv2d_fwd_xdl_bias_relu/conv2d_fwd_xdl_bias_relu.cpp)
|
|
set(CONV2D_FWD_XDL_BIAS_RELU_ADD_SOURCE 6_conv2d_fwd_xdl_bias_relu_add/conv2d_fwd_xdl_bias_relu_add.cpp)
|
|
set(CONV2D_FWD_XDL_BIAS_RELU_ATOMIC_ADD_SOURCE 7_conv2d_fwd_xdl_bias_relu_atomic_add/conv2d_fwd_xdl_bias_relu_atomic_add.cpp)
|
|
|
|
add_executable(gemm_xdl ${GEMM_XDL_SOURCE})
|
|
add_executable(gemm_xdl_bias_relu_add ${GEMM_XDL_BIAS_RELU_ADD_SOURCE})
|
|
add_executable(conv2d_fwd_xdl ${CONV2D_FWD_XDL_SOURCE})
|
|
add_executable(conv2d_fwd_xdl_bias_relu ${CONV2D_FWD_XDL_BIAS_RELU_SOURCE})
|
|
add_executable(conv2d_fwd_xdl_bias_relu_add ${CONV2D_FWD_XDL_BIAS_RELU_ADD_SOURCE})
|
|
add_executable(conv2d_fwd_xdl_bias_relu_atomic_add ${CONV2D_FWD_XDL_BIAS_RELU_ATOMIC_ADD_SOURCE})
|
|
|
|
target_link_libraries(gemm_xdl PRIVATE host_tensor)
|
|
target_link_libraries(gemm_xdl_bias_relu_add PRIVATE host_tensor)
|
|
target_link_libraries(conv2d_fwd_xdl PRIVATE host_tensor)
|
|
target_link_libraries(conv2d_fwd_xdl_bias_relu PRIVATE host_tensor)
|
|
target_link_libraries(conv2d_fwd_xdl_bias_relu_add PRIVATE host_tensor)
|
|
target_link_libraries(conv2d_fwd_xdl_bias_relu_atomic_add PRIVATE host_tensor)
|