mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-16 19:09:59 +00:00
0df06e585c
* Initial adding of generic reduction
* Initial adding of generic reduction ...
* Updates to make compiling done
* clang-format all files
* clang-format some files again
* Renaming in profiler/include/profile_reduce.hpp
* Updates and make BlockWise cases passed
* Updates and make ThreadWise and MultiBlockTwoCall cases passed
* Remove the support for MUL and NORM1 reduceOp from the profiler and the device instances
* Change to replace the dim0_max_vector_size/dim1_max_vector_size template argument in the device reduce classes
* format
* adding pooling
* added max and average pooling
* comment out cout and kernel timing
* Tiny simplification in profiler/reduce_profiler.cpp
* Add example for reduce_blockwise
* Tiny updates
* Change to pass the ElementWiseOp from device layer to kernel
* Fix the vectorDim and vectorSize in Device layer
* Enable vector load on both dim0 and dim1 for Threadwise method
* Tiny updates
* Change to let the user to pass the preUnaryOp and posUnaryOp
* Make pooling example work
* split device_reduce_instance into two libraries
* Tiny update
* Replace nanPropaOpt enum by boolean propagate_nan
* Simplification in DeviceReduce layer codes
* update build
* Change to clarify the difference between ck::half_t and half_float::half
* Renaming in all the reduction codes
* Add VectorSize as template parameter for device layer
* Add BetaIsZero as kernel template and as AccDataType for alpha
* print
* Small updates for pooling
* Updates for host_generic_reduction for reference
* Update to make AVG pooling pass
* Update to make MAX pooling with indices output pass
* fix
* add OutDst vector store to threadwise reduction and pooling
* tweak
* turn off check_indices that caused build issue
* refactor pooling
* clean up
* turn off check_indices for building issue for php-compiler
* add more tile size for odd C
* tweak conv for odd C
* update script
* clean up elementwise op
* add hack in reduction_operator.hpp to avoid compile error. To fix it, need to use element_wise_op in reduction op
* Add OutVectorSize as device and kernel tunable, also update to Elementwise Operations
* Move reduce operator mapping to host layer file reduction_operator_mapping.hpp from reduction_operator.hpp
* Change to the unary operators
* Move the definitions of unary operations to element_wise_operation.hpp
* re-org files
* Refine in device interfaces and multiblock kernels
* Split the reduction configurations into instances for specific methods
* Update in getTypeString() of device pool2d
* Renaming in host and kernel
* Tiny update in profiler/src/profiler.cpp
* Uncomment in device_operation/CMakeLists.txt to enable the building of all operations
* Make check_indices a templated function to remove some linking issue
* Renaming in the profiler reduce module
* Add support for double Reduction (but disable MultiblockAtomicAdd for double)
* Tiny correction of literal string
* Rename DevicePoolFwd to DevicePool2dFwd
* Split device_reduce_instance_xxx.cpp files according to the data types to speed up compiling
* Add comments for lists of configurations, lists of instances and references of add_reduce_instances_xxx
* Remove un-used header file gridwise_generic_reduction_wrapper_common.hpp
* Renaming and refining in the Reduction codes
* Tiny change in the unary operators
* Renaming symbols and files
* Renaming symbols in the kernels
* Move kernel kernel_set_buffer_value to separate file
* Add IndexDataType template parameter for kernels and use int32_t as index data type in device layer
* Tiny update in the kernels
* Remove definition of sqrtf()/isnan()/abs() for half_t due to some ADL issue
* Simplify a helper function in device layer
* Tiny adjustment in testing data initialization
* Renaming in kernel/device/host
* Add two testing scripts for reduction
* Refine the Unary operators in element_wise_operation.hpp
* Update in the reduce profiler module
* Update to the reduction testing scripts
* reduce compile parallelism
* change CI docker to rocm5.0
* remove unused variables
* fix build
Co-authored-by: Chao Liu <chao.liu2@amd.com>
[ROCm/composable_kernel commit: e17c0d8008]
70 lines
4.0 KiB
CMake
70 lines
4.0 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}/reference_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
|
|
${PROJECT_SOURCE_DIR}/device_operation_reference/include
|
|
)
|
|
|
|
set(GEMM_XDL_SOURCE 1_gemm_xdl/gemm_xdl.cpp)
|
|
set(GEMM_XDL_INT8_SOURCE 1_gemm_xdl/gemm_xdl_int8.cpp)
|
|
set(GEMM_XDL_BF16_SOURCE 1_gemm_xdl/gemm_xdl_bf16.cpp)
|
|
set(GEMM_XDL_BIAS_RELU_SOURCE 2_gemm_xdl_bias_relu/gemm_xdl_bias_relu.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)
|
|
set(GEMM_XDL_ALPHA_BETA_SOURCE 8_gemm_xdl_alpha_beta/gemm_xdl_alpha_beta.cpp)
|
|
set(CONV2D_FWD_XDL_INT8_SOURCE 9_conv2d_fwd_xdl_int8/conv2d_fwd_xdl_int8.cpp)
|
|
set(CONV2D_WRW_XDL_SOURCE 13_conv2d_backward_weight_xdl/main.cpp)
|
|
set(CONV3D_FWD_XDL_SOURCE 10_conv3d_fwd_xdl/conv3d_fwd_xdl.cpp)
|
|
set(CONVND_FWD_XDL_SOURCE 11_convnd_fwd_xdl/convnd_fwd_xdl.cpp)
|
|
set(CONV2D_BWD_DATA_XDL_SOURCE 12_conv2d_bwd_data_xdl/conv2d_bwd_data_xdl.cpp)
|
|
set(POOL2D_FWD_SOURCE 12_pool2d_fwd/pool2d_fwd.cpp)
|
|
set(REDUCE_BLOCKWISE_SOURCE 13_reduce_blockwise/reduce_blockwise.cpp)
|
|
|
|
add_executable(gemm_xdl ${GEMM_XDL_SOURCE})
|
|
add_executable(gemm_xdl_int8 ${GEMM_XDL_INT8_SOURCE})
|
|
add_executable(gemm_xdl_bf16 ${GEMM_XDL_BF16_SOURCE})
|
|
add_executable(gemm_xdl_bias_relu ${GEMM_XDL_BIAS_RELU_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})
|
|
add_executable(gemm_xdl_alpha_beta ${GEMM_XDL_ALPHA_BETA_SOURCE})
|
|
add_executable(conv2d_fwd_xdl_int8 ${CONV2D_FWD_XDL_INT8_SOURCE})
|
|
add_executable(conv2d_wrw_xdl ${CONV2D_WRW_XDL_SOURCE})
|
|
add_executable(conv3d_fwd_xdl ${CONV3D_FWD_XDL_SOURCE})
|
|
add_executable(convnd_fwd_xdl ${CONVND_FWD_XDL_SOURCE})
|
|
add_executable(conv2d_bwd_data_xdl ${CONV2D_BWD_DATA_XDL_SOURCE})
|
|
add_executable(pool2d_fwd ${POOL2D_FWD_SOURCE})
|
|
add_executable(reduce_blockwise ${REDUCE_BLOCKWISE_SOURCE})
|
|
|
|
target_link_libraries(gemm_xdl PRIVATE host_tensor)
|
|
target_link_libraries(gemm_xdl_int8 PRIVATE host_tensor)
|
|
target_link_libraries(gemm_xdl_bf16 PRIVATE host_tensor)
|
|
target_link_libraries(gemm_xdl_bias_relu 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)
|
|
target_link_libraries(gemm_xdl_alpha_beta PRIVATE host_tensor)
|
|
target_link_libraries(conv2d_fwd_xdl_int8 PRIVATE host_tensor)
|
|
target_link_libraries(conv2d_wrw_xdl PRIVATE host_tensor)
|
|
target_link_libraries(conv3d_fwd_xdl PRIVATE host_tensor)
|
|
target_link_libraries(convnd_fwd_xdl PRIVATE host_tensor)
|
|
target_link_libraries(conv2d_bwd_data_xdl PRIVATE host_tensor)
|
|
target_link_libraries(pool2d_fwd PRIVATE host_tensor)
|
|
target_link_libraries(reduce_blockwise PRIVATE host_tensor)
|
|
|