mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-06-06 00:03:22 +00:00
* First iteration of making cuda a shared provider. Separated out shared OpKernel change, so doing this to merge with that change. * More cuda shared library refactoring * More cuda shared library refactoring * More build options tested, converted the training ops over. * Fix merge breaks * Fix submodules * Fix submodules * Fix submodules * Fix python * Fix compile errors * Duplicate symbol fix * Test fix for ROCM provider * Another ROCM test workaround * ROCM Build Test * ROCM build fix * ROCM * ROCM * ROCM * ROCM * ROCM * ROCM test * Reduce header dependencies * Remove redundant namespace * Test fix for linux * Fix linux build * Fix Eigen build error * Fix unused parameter warning * Test link error * Another linker test * Linker test * Linker test * Another test * Another build test * Fix linux link error * Build test * Fix control flow ops to use common base class with core code * Remove extra qualifiers * Fix template syntax for linux * Fix cuda memory leak * Fix pybind * Test disabling cast * Cleanup * Restore cuda in test * Remove more header dependencies * Test not adding cuda provider to session * Make GetProviderInfo_CUDA throw * No-op cuda provider creation * Fix some setup issues * Fix memory cleanup on unload * Diagnostics * Don't unload library * Add diagnostics * Fix deleting registry at right time. * Test disabling profiler * Fix merge break * Revert profiler change * Move unloading of shared providers into Environment * Free more global allocations before library unloads * Add more diagnostics * Move unloading back to the OrtEnv as there are multiple Environments created during a session. Remove some library dependencies for tests. * Fix more cmake files * ERROR -> WARNING * Fix python shutdown * Test not using dml in pipeline * Change python version and disable dml * Update python version * Test adding unload method for shared providers * Disable DLL test * Python test * Revert "Python test" This reverts commitc7ec2cfe98. * Revert "Disable DLL test" This reverts commite901cb93aa. * Revert "Test adding unload method for shared providers" This reverts commitc427b78799. * Point to RyanWinGPU * Revert python version * Fix id_to_allocator_map * Another python exit test * Remove extra debug messages Try a more clean python shutdown through DllMain * Revert DllMain idea, it didn't work * Merge conflicts * Fix merge with master issues. * Comments * Undo edit to file * Cleanup + new training ops * Revert yml changes * Fix another merge error * ROCM fix * ROCM fix v2 * Put back Linux hack, it is necessary * Stupid fixes * Fix submodule out of sync * ROCM fix 3 * ROCM 4 * Test java fix * Fix typos * Java test on my VM * Fix build error * Spotless fix * Leave temp file around to load properly * Fix cleanup on exit * Fix break * Java comments * Remove LongformerAttentionBase workaround * Spotless fix * Switch yml back to regular build pool * Revert "Switch yml back to regular build pool" This reverts commitbe35fc2a5a. * Code review feedback * Fix errors due to merge * Spotless fix * Fix minimal build * Java fix for non cuda case * Java fix for CPU build * Fix Nuphar? * Fix nuphar 2 * Fix formatting * Revert "Remove LongformerAttentionBase workaround" This reverts commit648679b370. * Training fix * Another java fix * Formatting * Formatting * For orttraining * Last orttraining build fix... * training fixes * Fix test provider error * Missing pass command * Removed in wrong spot * Python typo * Python typos * Python crash on exit, possibly due to unloading of libraries. * Remove test_execution_provider from training build Only enable python atexit on windows Remove assert on provider library exit * Still can't unload providers in python, alas. * Disable Nvtx temporarily * MPI Kernels for Training * MPI Kernels part 2 * Patch through INcclService * Oops, wrong CMakeLists * Missing namespace * Fix missing () * Move INcclService::GetInstance around to link nicer * Missing } * Missing MPI libraries for Cuda * Add extra GetType functions used by MPI * Missing Nccl library * Remove LOGS statements as a test * Add in a couple more missing GetType methods * Update comments * Missed a logging reference in mpi_context.h * Convert aten_op to shared (due to marge with master) * Test moving DistributedRunContext instance into shared provider layer (with purpose error to verify it's being built properly) * Test passed, now with fix * Missing static * Oops, scope DistributedRunContext to just NCCL * Merge related issues and code review feedback. * Merge error * Bump to rel-1.9.1 (#7684) * Formatting * Code review feedback for Java build on non Windows * Remove cupti library dependency from core library * Test Java pipeline fix * Linux build fix * Revert "Linux build fix" This reverts commita73a811516. * Revert "Remove cupti library dependency from core library" This reverts commit6a889ee8bf. * Packaging pipeline fixes to copy cuda shared provider for tensorrt & standard packages * Add cuda to Tensorrt nuget package * onnxruntime_common still has a cuda header dependency Co-authored-by: ashbhandare <ash.bhandare@gmail.com>
178 lines
6.5 KiB
CMake
178 lines
6.5 KiB
CMake
# Copyright (c) Microsoft Corporation. All rights reserved.
|
|
# Licensed under the MIT License.
|
|
|
|
if(UNIX)
|
|
set(SYMBOL_FILE ${CMAKE_CURRENT_BINARY_DIR}/onnxruntime.lds)
|
|
set(OUTPUT_STYLE gcc)
|
|
else()
|
|
set(SYMBOL_FILE ${CMAKE_CURRENT_BINARY_DIR}/onnxruntime_dll.def)
|
|
set(OUTPUT_STYLE vc)
|
|
endif()
|
|
|
|
if (${CMAKE_SYSTEM_NAME} STREQUAL "iOS")
|
|
set(CMAKE_SHARED_LIBRARY_RUNTIME_C_FLAG "-Wl,-rpath,")
|
|
set(OUTPUT_STYLE xcode)
|
|
endif()
|
|
|
|
#If you want to verify if there is any extra line in symbols.txt, run
|
|
# nm -C -g --defined libonnxruntime.so |grep -v '\sA\s' | cut -f 3 -d ' ' | sort
|
|
# after build
|
|
|
|
list(APPEND SYMBOL_FILES "${REPO_ROOT}/tools/ci_build/gen_def.py")
|
|
foreach(f ${ONNXRUNTIME_PROVIDER_NAMES})
|
|
list(APPEND SYMBOL_FILES "${ONNXRUNTIME_ROOT}/core/providers/${f}/symbols.txt")
|
|
endforeach()
|
|
|
|
add_custom_command(OUTPUT ${SYMBOL_FILE} ${CMAKE_CURRENT_BINARY_DIR}/generated_source.c
|
|
COMMAND ${PYTHON_EXECUTABLE} "${REPO_ROOT}/tools/ci_build/gen_def.py"
|
|
--version_file "${ONNXRUNTIME_ROOT}/../VERSION_NUMBER" --src_root "${ONNXRUNTIME_ROOT}"
|
|
--config ${ONNXRUNTIME_PROVIDER_NAMES} --style=${OUTPUT_STYLE} --output ${SYMBOL_FILE}
|
|
--output_source ${CMAKE_CURRENT_BINARY_DIR}/generated_source.c
|
|
DEPENDS ${SYMBOL_FILES}
|
|
WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR})
|
|
|
|
add_custom_target(onnxruntime_generate_def ALL DEPENDS ${SYMBOL_FILE} ${CMAKE_CURRENT_BINARY_DIR}/generated_source.c)
|
|
if(WIN32)
|
|
onnxruntime_add_shared_library(onnxruntime
|
|
${SYMBOL_FILE}
|
|
"${ONNXRUNTIME_ROOT}/core/dll/dllmain.cc"
|
|
"${ONNXRUNTIME_ROOT}/core/dll/onnxruntime.rc"
|
|
)
|
|
elseif(onnxruntime_BUILD_APPLE_FRAMEWORK)
|
|
# include both c and cxx api
|
|
set(APPLE_FRAMEWORK_HEADERS
|
|
"${REPO_ROOT}/include/onnxruntime/core/session/onnxruntime_c_api.h"
|
|
"${REPO_ROOT}/include/onnxruntime/core/session/onnxruntime_cxx_api.h"
|
|
"${REPO_ROOT}/include/onnxruntime/core/session/onnxruntime_cxx_inline.h"
|
|
)
|
|
|
|
# need to add header files for enabled EPs
|
|
foreach(f ${ONNXRUNTIME_PROVIDER_NAMES})
|
|
file(GLOB _provider_headers CONFIGURE_DEPENDS
|
|
"${REPO_ROOT}/include/onnxruntime/core/providers/${f}/*.h"
|
|
)
|
|
list(APPEND APPLE_FRAMEWORK_HEADERS "${_provider_headers}")
|
|
unset(_provider_headers)
|
|
endforeach()
|
|
|
|
# apple framework requires the header file be part of the library
|
|
onnxruntime_add_shared_library(onnxruntime
|
|
${APPLE_FRAMEWORK_HEADERS}
|
|
"${CMAKE_CURRENT_BINARY_DIR}/generated_source.c"
|
|
)
|
|
|
|
set(MACOSX_FRAMEWORK_NAME "onnxruntime")
|
|
set(MACOSX_FRAMEWORK_IDENTIFIER "com.microsoft.onnxruntime")
|
|
configure_file(${REPO_ROOT}/cmake/Info.plist.in ${CMAKE_CURRENT_BINARY_DIR}/Info.plist)
|
|
|
|
set_target_properties(onnxruntime PROPERTIES
|
|
FRAMEWORK TRUE
|
|
FRAMEWORK_VERSION A
|
|
PUBLIC_HEADER "${APPLE_FRAMEWORK_HEADERS}"
|
|
MACOSX_FRAMEWORK_INFO_PLIST ${CMAKE_CURRENT_BINARY_DIR}/Info.plist
|
|
VERSION ${ORT_VERSION}
|
|
SOVERSION ${ORT_VERSION}
|
|
)
|
|
else()
|
|
onnxruntime_add_shared_library(onnxruntime ${CMAKE_CURRENT_BINARY_DIR}/generated_source.c)
|
|
endif()
|
|
|
|
add_dependencies(onnxruntime onnxruntime_generate_def ${onnxruntime_EXTERNAL_DEPENDENCIES})
|
|
target_include_directories(onnxruntime PRIVATE ${ONNXRUNTIME_ROOT})
|
|
|
|
target_compile_definitions(onnxruntime PRIVATE VER_MAJOR=${VERSION_MAJOR_PART})
|
|
target_compile_definitions(onnxruntime PRIVATE VER_MINOR=${VERSION_MINOR_PART})
|
|
target_compile_definitions(onnxruntime PRIVATE VER_BUILD=${VERSION_BUILD_PART})
|
|
target_compile_definitions(onnxruntime PRIVATE VER_PRIVATE=${VERSION_PRIVATE_PART})
|
|
target_compile_definitions(onnxruntime PRIVATE VER_STRING=\"${VERSION_STRING}\")
|
|
|
|
if (onnxruntime_USE_CUDA)
|
|
target_include_directories(onnxruntime PRIVATE ${onnxruntime_CUDNN_HOME}/include ${CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES})
|
|
endif()
|
|
|
|
if(UNIX)
|
|
if (APPLE)
|
|
set(ONNXRUNTIME_SO_LINK_FLAG " -Xlinker -dead_strip")
|
|
else()
|
|
set(ONNXRUNTIME_SO_LINK_FLAG " -Xlinker --version-script=${SYMBOL_FILE} -Xlinker --no-undefined -Xlinker --gc-sections -z noexecstack")
|
|
endif()
|
|
else()
|
|
set(ONNXRUNTIME_SO_LINK_FLAG " -DEF:${SYMBOL_FILE}")
|
|
endif()
|
|
|
|
if (NOT WIN32)
|
|
if (APPLE OR ${CMAKE_SYSTEM_NAME} MATCHES "^iOS")
|
|
if (${CMAKE_SYSTEM_NAME} STREQUAL "iOS")
|
|
set_target_properties(onnxruntime PROPERTIES
|
|
SOVERSION ${ORT_VERSION}
|
|
MACOSX_RPATH TRUE
|
|
INSTALL_RPATH_USE_LINK_PATH FALSE
|
|
BUILD_WITH_INSTALL_NAME_DIR TRUE
|
|
INSTALL_NAME_DIR @rpath)
|
|
set(ONNXRUNTIME_SO_LINK_FLAG " -Wl,-exported_symbols_list,${SYMBOL_FILE}")
|
|
else()
|
|
set_target_properties(onnxruntime PROPERTIES INSTALL_RPATH "@loader_path")
|
|
endif()
|
|
elseif (NOT onnxruntime_BUILD_WEBASSEMBLY)
|
|
set(CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} -Wl,-rpath='$ORIGIN'")
|
|
endif()
|
|
endif()
|
|
|
|
|
|
# strip binary on Android, or for a minimal build on Unix
|
|
if(CMAKE_SYSTEM_NAME STREQUAL "Android" OR (onnxruntime_MINIMAL_BUILD AND UNIX))
|
|
if (onnxruntime_MINIMAL_BUILD AND ADD_DEBUG_INFO_TO_MINIMAL_BUILD)
|
|
# don't strip
|
|
else()
|
|
set_target_properties(onnxruntime PROPERTIES LINK_FLAGS_RELEASE -s)
|
|
set_target_properties(onnxruntime PROPERTIES LINK_FLAGS_MINSIZEREL -s)
|
|
endif()
|
|
endif()
|
|
|
|
target_link_libraries(onnxruntime PRIVATE
|
|
onnxruntime_session
|
|
${onnxruntime_libs}
|
|
${PROVIDERS_ACL}
|
|
${PROVIDERS_ARMNN}
|
|
${PROVIDERS_COREML}
|
|
${PROVIDERS_DML}
|
|
${PROVIDERS_MIGRAPHX}
|
|
${PROVIDERS_NNAPI}
|
|
${PROVIDERS_NUPHAR}
|
|
${PROVIDERS_RKNPU}
|
|
${PROVIDERS_ROCM}
|
|
${PROVIDERS_VITISAI}
|
|
${PROVIDERS_INTERNAL_TESTING}
|
|
${onnxruntime_winml}
|
|
onnxruntime_optimizer
|
|
onnxruntime_providers
|
|
onnxruntime_util
|
|
${onnxruntime_tvm_libs}
|
|
onnxruntime_framework
|
|
onnxruntime_graph
|
|
onnxruntime_common
|
|
onnxruntime_mlas
|
|
onnxruntime_flatbuffers
|
|
${onnxruntime_EXTERNAL_LIBRARIES})
|
|
|
|
if (onnxruntime_ENABLE_LANGUAGE_INTEROP_OPS)
|
|
target_link_libraries(onnxruntime PRIVATE onnxruntime_language_interop onnxruntime_pyop)
|
|
endif()
|
|
|
|
set_property(TARGET onnxruntime APPEND_STRING PROPERTY LINK_FLAGS ${ONNXRUNTIME_SO_LINK_FLAG} ${onnxruntime_DELAYLOAD_FLAGS})
|
|
set_target_properties(onnxruntime PROPERTIES LINK_DEPENDS ${SYMBOL_FILE})
|
|
|
|
|
|
set_target_properties(onnxruntime PROPERTIES VERSION ${ORT_VERSION})
|
|
|
|
install(TARGETS onnxruntime
|
|
ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
|
|
LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
|
|
RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR}
|
|
FRAMEWORK DESTINATION ${CMAKE_INSTALL_BINDIR})
|
|
|
|
set_target_properties(onnxruntime PROPERTIES FOLDER "ONNXRuntime")
|
|
|
|
if (WINDOWS_STORE)
|
|
target_link_options(onnxruntime PRIVATE /DELAYLOAD:api-ms-win-core-libraryloader-l1-2-1.dll)
|
|
endif()
|