mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-23 22:13:38 +00:00
### Description Enablement of onnxruntime for AIX and fixing issues related to big-endian platform. ### Motivation and Context changes in this PR contains: 1. Enablement code for building onnxruntime on AIX operating system. 2. while testing the build on AIX, we found issues related to big endian platform . More details about few of those issues can be found in [Big endian issue: Graph Transformation Attention Fusion tests are failing #12921](https://github.com/microsoft/onnxruntime/issues/12921) Below are list of files and the description about the change. 1. cmake/CMakeLists.txt [BUILDING on AIX issue] check for "IBMClang" is added for handling -Wno-unused-parameter 2. cmake/external/onnxruntime_external_deps.cmake [BUILDING on AIX issue]Enabling gtest_disable_pthreads for AIX 3. cmake/onnxruntime.cmake [BUILDING on AIX issue] o Blocking codes for AIX which generates generated_source.c and further requires some symbol files. o Putting NO AIX check for non-supported linker flags like --Xlinker o iconv linking 4. cmake/onnxruntime_framework.cmake [BUILDING on AIX issue]Putting NO AIX check for -Wl,-rpath='$ORIGIN' 5. cmake/onnxruntime_mlas.cmake [BUILDING on AIX issue]POWER10 releated macro/function definition . 6. cmake/onnxruntime_providers_cpu.cmake [BUILDING on AIX issue]Putting NO AIX check for non-supported linker flags like --Xlinker 7. cmake/onnxruntime_unittests.cmake [BUILDING on AIX issue] o Putting NO AIX check for non-supported linker flags like --Xlinker o Adding required libraries for AIX linker under applicatiion like onnxruntime_shared_lib_test ,onnxruntime_logging_apis etc 8. cmake/patches/flatbuffers/flatbuffers.patch [BUILDING on AIX issue] Handling of TypeCode in include/flatbuffers/flatbuffers.h under AIX + clang 9. onnxruntime/contrib_ops/cpu/murmur_hash3.cc [Big endian issue] Byte-Conversion handlling in compute() and getblock() routines 10. onnxruntime/contrib_ops/cpu/quantization/matmul_nbits_impl.cc [Big endian issue] Handling of test failures . Byte swapping for quant_value. 11. onnxruntime/core/framework/tensorprotoutils.cc [Big endian issue] Implementation of SetRawDataInTensorProto , ConvertRawDataInTensorProto . o SetRawDataInTensorProto : Wrapper for set_raw_data(). Calling ConvertRawDataInTensorProto() in big-endian system o ConvertRawDataInTensorProto : function used mainly on big-endian system for byte-swapping of tensor raw_data 12. onnxruntime/core/framework/tensorprotoutils.h [Big endian issue] Declaration of SetRawDataInTensorProto, ConvertRawDataInTensorProto 13. onnxruntime/core/graph/graph.cc [Big endian issue] o Call ConvertRawDataInTensorProto for SPARSE_TENSOR type o Call ConvertRawDataInTensorProto for SaveToOrtFormat 14. onnxruntime/core/mlas/lib/platform.cpp [BUILDING on AIX issue] POWER10 released enablement for AIX 15. onnxruntime/core/mlas/lib/power/qgemm_kernel_power10.cpp [BUILDING on AIX issue]Handling of __vector under AIX+clang 16. onnxruntime/core/mlas/lib/qgemm.h [BUILDING on AIX issue] Adding _AIX flag 17. onnxruntime/core/mlas/lib/qlmul.cpp [BUILDING on AIX issue] Handling of __vector under AIX+clang 18. onnxruntime/core/optimizer/attention_fusion.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 19. onnxruntime/core/optimizer/compute_optimizer/shared_utils.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 20. onnxruntime/core/optimizer/constant_folding.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 21. onnxruntime/core/optimizer/embed_layer_norm_fusion.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 22. onnxruntime/core/optimizer/nchwc_transformer.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 23. onnxruntime/core/optimizer/qdq_transformer/avx2_weight_s8_to_u8.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 24. onnxruntime/core/optimizer/qdq_transformer/qdq_s8_to_u8.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 25. onnxruntime/core/optimizer/qdq_transformer/s8_to_u8.h [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 26. onnxruntime/core/optimizer/qdq_transformer/selectors_actions/qdq_actions.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 27. onnxruntime/core/optimizer/reshape_fusion.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 28. onnxruntime/core/optimizer/stft_decomposition.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 29. onnxruntime/core/optimizer/transpose_optimization/ort_optimizer_api_impl.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 30. onnxruntime/core/platform/path_lib.h [BUILDING on AIX issue] Moving to normal function call, instead of template 31. onnxruntime/core/platform/posix/env.cc [BUILDING on AIX issue]Blocking syscall.h in AIX 32. onnxruntime/core/session/inference_session.cc [Big endian issue] Removing ORT_RETURN_IF_NOT, FLATBUFFERS_LITTLEENDIAN 33. onnxruntime/test/flatbuffers/flatbuffer_utils_test.cc [Big endian issue] Call ConvertRawDataInTensorProto in CreateInitializer and ExternalWriteReadWithLoadInitializers 34. onnxruntime/test/framework/sparse_kernels_test.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 35. onnxruntime/test/framework/tensorutils_test.cc [Big endian issue] Helper method ConvertEndianessForVector and call this from required place. 36. onnxruntime/test/framework/test_tensor_loader.cc o. [BUILDING on AIX issue] Handling of getcwd for AIX o. [Big endian issue] Bytes Swapping in run_external_data_test 37. onnxruntime/test/onnx/main.cc [Big endian issue] including <thread> for AIX 38. onnxruntime/test/onnx/tensorprotoutils.cc [Big endian issue] Bytes swapping in UnpackTensorWithRawData 39. onnxruntime/test/optimizer/graph_transform_test.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 40. onnxruntime/test/optimizer/graph_transform_test_builder.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 41. onnxruntime/test/optimizer/graph_transform_test_builder.h [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 42. onnxruntime/test/optimizer/initializer_test.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 43. onnxruntime/test/optimizer/nchwc_optimizer_test.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 44. onnxruntime/test/providers/base_tester.cc [Big endian issue] Use util function SetRawDataInTensorProto, instead of set_raw_data 45. onnxruntime/test/providers/cpu/generator/random_test.cc [BUILDING on AIX issue] Adding AIX check in MultinomialGoodCase --------- Co-authored-by: Vamshikrishna Thatikonda <vamshikrishna@in.ibm.com>
273 lines
13 KiB
CMake
273 lines
13 KiB
CMake
# Copyright (c) Microsoft Corporation. All rights reserved.
|
|
# Licensed under the MIT License.
|
|
|
|
file(GLOB_RECURSE onnxruntime_providers_srcs CONFIGURE_DEPENDS
|
|
"${ONNXRUNTIME_ROOT}/core/providers/cpu/*.h"
|
|
"${ONNXRUNTIME_ROOT}/core/providers/cpu/*.cc"
|
|
)
|
|
|
|
if(onnxruntime_DISABLE_ML_OPS)
|
|
list(FILTER onnxruntime_providers_srcs EXCLUDE REGEX ".*/ml/.*")
|
|
endif()
|
|
|
|
file(GLOB_RECURSE onnxruntime_cpu_contrib_ops_srcs CONFIGURE_DEPENDS
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/cpu/*.h"
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/cpu/*.cc"
|
|
)
|
|
|
|
file(GLOB_RECURSE onnxruntime_cuda_contrib_ops_cc_srcs CONFIGURE_DEPENDS
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/cuda/*.h"
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/cuda/*.cc"
|
|
)
|
|
|
|
file(GLOB_RECURSE onnxruntime_cuda_contrib_ops_cu_srcs CONFIGURE_DEPENDS
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/cuda/*.cu"
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/cuda/*.cuh"
|
|
)
|
|
|
|
file(GLOB_RECURSE onnxruntime_rocm_contrib_ops_cc_srcs CONFIGURE_DEPENDS
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/rocm/*.h"
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/rocm/*.cc"
|
|
)
|
|
|
|
file(GLOB_RECURSE onnxruntime_rocm_contrib_ops_cu_srcs CONFIGURE_DEPENDS
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/rocm/*.cu"
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/rocm/*.cuh"
|
|
)
|
|
|
|
file(GLOB_RECURSE onnxruntime_js_contrib_ops_cc_srcs CONFIGURE_DEPENDS
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/js/*.h"
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/js/*.cc"
|
|
)
|
|
|
|
file(GLOB onnxruntime_providers_common_srcs CONFIGURE_DEPENDS
|
|
"${ONNXRUNTIME_ROOT}/core/providers/*.h"
|
|
"${ONNXRUNTIME_ROOT}/core/providers/*.cc"
|
|
"${ONNXRUNTIME_ROOT}/core/providers/op_kernel_type_control_overrides.inc"
|
|
)
|
|
|
|
|
|
source_group(TREE ${ONNXRUNTIME_ROOT}/core FILES ${onnxruntime_providers_common_srcs} ${onnxruntime_providers_srcs})
|
|
|
|
set(onnxruntime_providers_src ${onnxruntime_providers_common_srcs} ${onnxruntime_providers_srcs})
|
|
|
|
# disable contrib ops conditionally
|
|
if(NOT onnxruntime_DISABLE_CONTRIB_OPS)
|
|
if (NOT onnxruntime_ENABLE_ATEN)
|
|
list(REMOVE_ITEM onnxruntime_cpu_contrib_ops_srcs
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/cpu/aten_ops/aten_op.h"
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/cpu/aten_ops/aten_op.cc"
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/cpu/aten_ops/aten_op_executor.cc"
|
|
)
|
|
endif()
|
|
set(onnxruntime_cpu_neural_speed_srcs
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/cpu/quantization/neural_speed_wrapper.h"
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/cpu/quantization/neural_speed_defs.h"
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/cpu/quantization/neural_speed_gemm.cc"
|
|
"${ONNXRUNTIME_ROOT}/contrib_ops/cpu/quantization/neural_speed_gemm.h"
|
|
)
|
|
if(NOT USE_NEURAL_SPEED)
|
|
list(REMOVE_ITEM onnxruntime_cpu_contrib_ops_srcs ${onnxruntime_cpu_neural_speed_srcs})
|
|
endif()
|
|
# add using ONNXRUNTIME_ROOT so they show up under the 'contrib_ops' folder in Visual Studio
|
|
source_group(TREE ${ONNXRUNTIME_ROOT} FILES ${onnxruntime_cpu_contrib_ops_srcs})
|
|
list(APPEND onnxruntime_providers_src ${onnxruntime_cpu_contrib_ops_srcs})
|
|
endif()
|
|
|
|
if (onnxruntime_ENABLE_TRAINING_OPS AND NOT onnxruntime_ENABLE_TRAINING)
|
|
file(GLOB_RECURSE onnxruntime_cpu_training_ops_srcs CONFIGURE_DEPENDS
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/*.h"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/*.cc"
|
|
)
|
|
|
|
source_group(TREE ${ORTTRAINING_ROOT}/ FILES ${onnxruntime_cpu_training_ops_srcs})
|
|
list(APPEND onnxruntime_providers_src ${onnxruntime_cpu_training_ops_srcs})
|
|
|
|
file(GLOB_RECURSE onnxruntime_cpu_full_training_only_srcs
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/collective/*.cc"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/collective/*.h"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/communication/*.cc"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/communication/*.h"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/controlflow/record.cc"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/controlflow/record.h"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/controlflow/wait.cc"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/controlflow/wait.h"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/controlflow/yield.cc"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/controlflow/yield.h"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/gist/*.cc"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/gist/*.h"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/tensorboard/*.cc"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/tensorboard/*.h"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/torch/*.cc"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/torch/*.h"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/triton/triton_op.cc"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/triton/triton_op.h"
|
|
)
|
|
|
|
list(REMOVE_ITEM onnxruntime_providers_src ${onnxruntime_cpu_full_training_only_srcs})
|
|
endif()
|
|
|
|
if (onnxruntime_ENABLE_ATEN)
|
|
file(GLOB_RECURSE onnxruntime_providers_dlpack_srcs CONFIGURE_DEPENDS
|
|
"${ONNXRUNTIME_ROOT}/core/dlpack/dlpack_converter.cc"
|
|
"${ONNXRUNTIME_ROOT}/core/dlpack/dlpack_converter.h"
|
|
)
|
|
set(onnxruntime_providers_dlpack_srcs ${onnxruntime_providers_dlpack_srcs})
|
|
source_group(TREE ${ONNXRUNTIME_ROOT}/core FILES ${onnxruntime_providers_dlpack_srcs})
|
|
list(APPEND onnxruntime_providers_src ${onnxruntime_providers_dlpack_srcs})
|
|
endif()
|
|
|
|
if (onnxruntime_ENABLE_TRAINING)
|
|
file(GLOB_RECURSE onnxruntime_cpu_training_ops_srcs CONFIGURE_DEPENDS
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/*.h"
|
|
"${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/*.cc"
|
|
"${ORTTRAINING_SOURCE_DIR}/core/framework/*.h"
|
|
"${ORTTRAINING_SOURCE_DIR}/core/framework/*.cc"
|
|
"${ORTTRAINING_SOURCE_DIR}/core/framework/adasum/*"
|
|
"${ORTTRAINING_SOURCE_DIR}/core/framework/communication/*"
|
|
)
|
|
|
|
# This is already built in framework.cmake
|
|
file(GLOB_RECURSE onnxruntime_training_framework_excude_srcs CONFIGURE_DEPENDS
|
|
"${ORTTRAINING_SOURCE_DIR}/core/framework/torch/*.h"
|
|
"${ORTTRAINING_SOURCE_DIR}/core/framework/torch/*.cc"
|
|
"${ORTTRAINING_SOURCE_DIR}/core/framework/triton/*.h"
|
|
"${ORTTRAINING_SOURCE_DIR}/core/framework/triton/*.cc"
|
|
)
|
|
|
|
list(REMOVE_ITEM onnxruntime_cpu_training_ops_srcs ${onnxruntime_training_framework_excude_srcs})
|
|
|
|
source_group(TREE ${ORTTRAINING_ROOT}/ FILES ${onnxruntime_cpu_training_ops_srcs})
|
|
list(APPEND onnxruntime_providers_src ${onnxruntime_cpu_training_ops_srcs})
|
|
endif()
|
|
|
|
if (onnxruntime_REDUCED_OPS_BUILD)
|
|
substitute_op_reduction_srcs(onnxruntime_providers_src)
|
|
endif()
|
|
onnxruntime_add_static_library(onnxruntime_providers ${onnxruntime_providers_src})
|
|
if (onnxruntime_REDUCED_OPS_BUILD)
|
|
add_op_reduction_include_dirs(onnxruntime_providers)
|
|
endif()
|
|
|
|
if (HAS_BITWISE_INSTEAD_OF_LOGICAL)
|
|
target_compile_options(onnxruntime_providers PRIVATE "-Wno-bitwise-instead-of-logical")
|
|
endif()
|
|
|
|
if(NOT onnxruntime_DISABLE_CONTRIB_OPS)
|
|
if(USE_NEURAL_SPEED)
|
|
onnxruntime_add_include_to_target(onnxruntime_providers neural_speed::bestla)
|
|
endif()
|
|
endif()
|
|
|
|
if (MSVC)
|
|
target_compile_options(onnxruntime_providers PRIVATE "/bigobj")
|
|
# if(NOT CMAKE_SIZEOF_VOID_P EQUAL 8)
|
|
# target_compile_options(onnxruntime_providers PRIVATE "/wd4244")
|
|
# endif()
|
|
endif()
|
|
onnxruntime_add_include_to_target(onnxruntime_providers onnxruntime_common onnxruntime_framework onnx onnx_proto ${PROTOBUF_LIB} flatbuffers::flatbuffers Boost::mp11 safeint_interface)
|
|
|
|
if (onnxruntime_BUILD_MS_EXPERIMENTAL_OPS)
|
|
target_compile_definitions(onnxruntime_providers PRIVATE BUILD_MS_EXPERIMENTAL_OPS=1)
|
|
endif()
|
|
|
|
if(HAS_DEPRECATED_COPY)
|
|
#temporarily ignore this warning
|
|
#see: https://en.wikipedia.org/wiki/Rule_of_three_(C%2B%2B_programming)
|
|
set_source_files_properties("${ONNXRUNTIME_ROOT}/core/providers/cpu/math/matmul_integer.cc" PROPERTIES COMPILE_FLAGS -Wno-deprecated-copy)
|
|
set_source_files_properties("${ONNXRUNTIME_ROOT}/core/providers/cpu/math/quantize_linear_matmul.cc" PROPERTIES COMPILE_FLAGS -Wno-deprecated-copy)
|
|
set_source_files_properties("${ONNXRUNTIME_ROOT}/core/providers/cpu/nn/qlinearconv.cc" PROPERTIES COMPILE_FLAGS -Wno-deprecated-copy)
|
|
set_source_files_properties("${ONNXRUNTIME_ROOT}/core/providers/cpu/nn/conv_integer.cc" PROPERTIES COMPILE_FLAGS -Wno-deprecated-copy)
|
|
set_source_files_properties("${ONNXRUNTIME_ROOT}/core/providers/cpu/generator/random.cc" PROPERTIES COMPILE_FLAGS -Wno-deprecated-copy)
|
|
set_source_files_properties("${ONNXRUNTIME_ROOT}/core/providers/cpu/tensor/onehot.cc" PROPERTIES COMPILE_FLAGS -Wno-deprecated-copy)
|
|
set_source_files_properties("${ONNXRUNTIME_ROOT}/core/providers/cpu/tensor/where_op.cc" PROPERTIES COMPILE_FLAGS -Wno-deprecated-copy)
|
|
endif()
|
|
|
|
# This is enabled only for Adasum files in training mode.
|
|
# The flags won't be applied globally since some high-precision training and inferencing ops will incur precision loss.
|
|
if (onnxruntime_ENABLE_CPU_FP16_OPS)
|
|
set_source_files_properties(${ORTTRAINING_SOURCE_DIR}/core/framework/adasum/adasum_mpi.cc PROPERTIES COMPILE_FLAGS " -fassociative-math -ffast-math -ftree-vectorize -funsafe-math-optimizations -mf16c -mavx -mfma ")
|
|
set_source_files_properties(${ORTTRAINING_SOURCE_DIR}/training_ops/cpu/collective/adasum_kernels.cc PROPERTIES COMPILE_FLAGS " -fassociative-math -ffast-math -ftree-vectorize -funsafe-math-optimizations -mf16c -mavx -mfma ")
|
|
set_source_files_properties(${ORTTRAINING_SOURCE_DIR}/training_ops/cuda/collective/adasum_kernels.cc PROPERTIES COMPILE_FLAGS " -fassociative-math -ffast-math -ftree-vectorize -funsafe-math-optimizations -mf16c -mavx -mfma ")
|
|
endif()
|
|
|
|
target_include_directories(onnxruntime_providers PRIVATE ${ONNXRUNTIME_ROOT} ${eigen_INCLUDE_DIRS})
|
|
onnxruntime_add_include_to_target(onnxruntime_providers re2::re2)
|
|
add_dependencies(onnxruntime_providers onnx ${onnxruntime_EXTERNAL_DEPENDENCIES})
|
|
|
|
if (onnxruntime_ENABLE_TRAINING_OPS)
|
|
target_include_directories(onnxruntime_providers PRIVATE ${ORTTRAINING_ROOT})
|
|
endif()
|
|
|
|
if (onnxruntime_ENABLE_ATEN)
|
|
target_compile_definitions(onnxruntime_providers PRIVATE ENABLE_ATEN)
|
|
# DLPack is a header-only dependency
|
|
set(DLPACK_INCLUDE_DIR ${dlpack_SOURCE_DIR}/include)
|
|
target_include_directories(onnxruntime_providers PRIVATE ${DLPACK_INCLUDE_DIR})
|
|
endif()
|
|
|
|
if (onnxruntime_ENABLE_TRAINING)
|
|
add_dependencies(onnxruntime_providers tensorboard)
|
|
onnxruntime_add_include_to_target(onnxruntime_providers tensorboard)
|
|
if (onnxruntime_ENABLE_TRAINING_TORCH_INTEROP OR onnxruntime_ENABLE_TRITON)
|
|
onnxruntime_add_include_to_target(onnxruntime_providers Python::Module)
|
|
endif()
|
|
|
|
if (onnxruntime_USE_NCCL OR onnxruntime_USE_MPI)
|
|
target_include_directories(onnxruntime_providers PUBLIC ${MPI_CXX_INCLUDE_DIRS})
|
|
endif()
|
|
endif()
|
|
|
|
install(FILES ${PROJECT_SOURCE_DIR}/../include/onnxruntime/core/providers/cpu/cpu_provider_factory.h DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/onnxruntime/)
|
|
set_target_properties(onnxruntime_providers PROPERTIES LINKER_LANGUAGE CXX)
|
|
set_target_properties(onnxruntime_providers PROPERTIES FOLDER "ONNXRuntime")
|
|
|
|
if (NOT onnxruntime_MINIMAL_BUILD AND NOT onnxruntime_EXTENDED_MINIMAL_BUILD
|
|
AND NOT ${CMAKE_SYSTEM_NAME} MATCHES "Darwin|iOS|visionOS"
|
|
AND NOT CMAKE_SYSTEM_NAME STREQUAL "Android"
|
|
AND NOT CMAKE_SYSTEM_NAME STREQUAL "Emscripten")
|
|
file(GLOB onnxruntime_providers_shared_cc_srcs CONFIGURE_DEPENDS
|
|
"${ONNXRUNTIME_ROOT}/core/providers/shared/*.h"
|
|
"${ONNXRUNTIME_ROOT}/core/providers/shared/*.cc"
|
|
)
|
|
|
|
source_group(TREE ${ONNXRUNTIME_ROOT}/core FILES ${onnxruntime_providers_shared_cc_srcs})
|
|
onnxruntime_add_shared_library(onnxruntime_providers_shared ${onnxruntime_providers_shared_cc_srcs} "${ONNXRUNTIME_ROOT}/core/dll/onnxruntime.rc")
|
|
set_target_properties(onnxruntime_providers_shared PROPERTIES FOLDER "ONNXRuntime")
|
|
set_target_properties(onnxruntime_providers_shared PROPERTIES LINKER_LANGUAGE CXX)
|
|
|
|
target_compile_definitions(onnxruntime_providers_shared PRIVATE FILE_NAME=\"onnxruntime_providers_shared.dll\")
|
|
|
|
|
|
# On Apple/Unix we don't directly link with this library as we load it with RTLD_GLOBAL, so this is only set to the actual library on WIN32
|
|
# But, in exchange we need to manually add Boost::mp11 to include dirs for every EP.
|
|
# It is because "provider_api.h" includes core/framework/op_kernel.h which includes op_kernel.h which includes "boost/mp11.hpp"
|
|
set(ONNXRUNTIME_PROVIDERS_SHARED)
|
|
|
|
if(APPLE)
|
|
set_property(TARGET onnxruntime_providers_shared APPEND_STRING PROPERTY LINK_FLAGS "-Xlinker -exported_symbols_list ${ONNXRUNTIME_ROOT}/core/providers/shared/exported_symbols.lst")
|
|
elseif(UNIX)
|
|
if(NOT ${CMAKE_SYSTEM_NAME} MATCHES "AIX")
|
|
set_property(TARGET onnxruntime_providers_shared APPEND_STRING PROPERTY LINK_FLAGS "-Xlinker --version-script=${ONNXRUNTIME_ROOT}/core/providers/shared/version_script.lds -Xlinker --gc-sections")
|
|
endif()
|
|
elseif(WIN32)
|
|
set_property(TARGET onnxruntime_providers_shared APPEND_STRING PROPERTY LINK_FLAGS "-DEF:${ONNXRUNTIME_ROOT}/core/providers/shared/symbols.def")
|
|
set(ONNXRUNTIME_PROVIDERS_SHARED onnxruntime_providers_shared)
|
|
else()
|
|
message(FATAL_ERROR "onnxruntime_providers_shared unknown platform, need to specify shared library exports for it")
|
|
endif()
|
|
|
|
install(TARGETS onnxruntime_providers_shared
|
|
ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
|
|
LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
|
|
RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR}
|
|
)
|
|
endif()
|
|
|
|
if (NOT onnxruntime_BUILD_SHARED_LIB)
|
|
install(TARGETS onnxruntime_providers
|
|
ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
|
|
LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
|
|
RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR}
|
|
FRAMEWORK DESTINATION ${CMAKE_INSTALL_BINDIR})
|
|
endif()
|