saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-31 23:27:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/cmake/onnxruntime_session.cmake

76 lines
3.5 KiB
CMake
Raw Normal View History

Initial bootstrap commit.
2018-11-20 00:48:22 +00:00
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License.
make builds more robust (#906) (#932)
2019-04-29 19:58:20 +00:00
file(GLOB onnxruntime_session_srcs CONFIGURE_DEPENDS
Initial bootstrap commit.
2018-11-20 00:48:22 +00:00
"${ONNXRUNTIME_INCLUDE_DIR}/core/session/*.h"
"${ONNXRUNTIME_ROOT}/core/session/*.h"
"${ONNXRUNTIME_ROOT}/core/session/*.cc"
)
Refactor training build options (#13964) ### Description 1. Renames all references of on device training to training apis. This is to keep the naming general. Nothing really prevents us from using the same apis on servers\non-edge devices. 2. Update ENABLE_TRAINING option: With this PR when this option is enabled, training apis and torch interop is also enabled. 3. Refactoring for onnxruntime_ENABLE_TRAINING_TORCH_INTEROP option: - Removed user facing option - Setting onnxruntime_ENABLE_TRAINING_TORCH_INTEROP to ON when onnxruntime_ENABLE_TRAINING is ON as we always build with torch interop. Once this PR is merged when --enable_training is selected we will do a "FULL Build" for training (with all the training entry points and features). Training entry points include: 1. ORTModule 2. Training APIs Features include: 1. ATen Fallback 2. All Training OPs includes communication and collectives 3. Strided Tensor Support 4. Python Op (torch interop) 5. ONNXBlock (Front end tools for training artifacts prep when using trianing apis) ### Motivation and Context Intention is to simply the options for building training enabled builds. This is part of the larger work item to create dedicated build for learning on the edge scenarios with just training apis enabled.
2023-01-03 21:28:16 +00:00
if (onnxruntime_ENABLE_TRAINING_APIS)
file(GLOB_RECURSE training_api_srcs CONFIGURE_DEPENDS
C API version 0.001 (#11758) * C API version 0.001 * fix linker issues * fixes for save checkpoint api * plus fixes based on tests * plus test_runner and other changes * Plus cosmetic updates * remove unnecessary headers * plus some updates * plus more changes Co-authored-by: Ashwini Khade <askhade@microsoft.com@orttrainingdev10.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>
2022-06-15 18:13:35 +00:00
"${ORTTRAINING_SOURCE_DIR}/training_api/*.cc"
fix headers for training apis (#14350) ### Description Minor refactor PR for fixing header placement for training apis
2023-01-19 18:26:53 +00:00
"${ORTTRAINING_SOURCE_DIR}/training_api/*.h"
Create dedicated build for training api (#14136) ### Description Enable creating dedicated build for on device training. With this PR we can build a lean binary for on device training using flag --enable_training_apis. This binary includes only the essentials like training ops, optimizers etc and NOT features like Aten fallback, strided tensors, gradient builders etc . This binary also removes all the deprecated components like training::TrainingSession and OrtTrainer etc ### Motivation and Context This enables our partners to create a lean binary for on device training.
2023-01-11 04:58:04 +00:00
"${ORTTRAINING_SOURCE_DIR}/core/framework/checkpoint_common.cc"
"${ORTTRAINING_SOURCE_DIR}/core/framework/checkpoint_common.h"
C API version 0.001 (#11758) * C API version 0.001 * fix linker issues * fixes for save checkpoint api * plus fixes based on tests * plus test_runner and other changes * Plus cosmetic updates * remove unnecessary headers * plus some updates * plus more changes Co-authored-by: Ashwini Khade <askhade@microsoft.com@orttrainingdev10.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>
2022-06-15 18:13:35 +00:00
)
Refactor training build options (#13964) ### Description 1. Renames all references of on device training to training apis. This is to keep the naming general. Nothing really prevents us from using the same apis on servers\non-edge devices. 2. Update ENABLE_TRAINING option: With this PR when this option is enabled, training apis and torch interop is also enabled. 3. Refactoring for onnxruntime_ENABLE_TRAINING_TORCH_INTEROP option: - Removed user facing option - Setting onnxruntime_ENABLE_TRAINING_TORCH_INTEROP to ON when onnxruntime_ENABLE_TRAINING is ON as we always build with torch interop. Once this PR is merged when --enable_training is selected we will do a "FULL Build" for training (with all the training entry points and features). Training entry points include: 1. ORTModule 2. Training APIs Features include: 1. ATen Fallback 2. All Training OPs includes communication and collectives 3. Strided Tensor Support 4. Python Op (torch interop) 5. ONNXBlock (Front end tools for training artifacts prep when using trianing apis) ### Motivation and Context Intention is to simply the options for building training enabled builds. This is part of the larger work item to create dedicated build for learning on the edge scenarios with just training apis enabled.
2023-01-03 21:28:16 +00:00
list(APPEND onnxruntime_session_srcs ${training_api_srcs})
C API version 0.001 (#11758) * C API version 0.001 * fix linker issues * fixes for save checkpoint api * plus fixes based on tests * plus test_runner and other changes * Plus cosmetic updates * remove unnecessary headers * plus some updates * plus more changes Co-authored-by: Ashwini Khade <askhade@microsoft.com@orttrainingdev10.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>
2022-06-15 18:13:35 +00:00
endif()
Move shared providers CPU providers into separate file (#8293)
2021-07-19 22:19:32 +00:00
if (onnxruntime_MINIMAL_BUILD)
set(onnxruntime_session_src_exclude
"${ONNXRUNTIME_ROOT}/core/session/provider_bridge_ort.cc"
)
list(REMOVE_ITEM onnxruntime_session_srcs ${onnxruntime_session_src_exclude})
endif()
Initial bootstrap commit.
2018-11-20 00:48:22 +00:00
source_group(TREE ${REPO_ROOT} FILES ${onnxruntime_session_srcs})
Add static code analyzer to Windows CPU/GPU CI builds and fix the warnings (#7489)
2021-04-29 18:54:57 +00:00
onnxruntime_add_static_library(onnxruntime_session ${onnxruntime_session_srcs})
Use target name for flatbuffers (#13991) ### Description Use target name for flatbuffers. Add version range for flatbuffers. It is similar to #13870 ### Motivation and Context To fix a build error: ``` CMake Error at onnxruntime_graph.cmake:88 (add_dependencies): The dependency target "flatbuffers" of target "onnxruntime_graph" does not exist. Call Stack (most recent call first): CMakeLists.txt:1490 (include) ``` It happens when flatbuffers library is already installed. For example, on Ubuntu people may get it from apt-get. But, the one provided by Ubuntu 20.04 is not compatible with our code. The one in Ubuntu 22.04 works fine.
2022-12-20 19:44:02 +00:00
onnxruntime_add_include_to_target(onnxruntime_session onnxruntime_common onnxruntime_framework onnx onnx_proto ${PROTOBUF_LIB} flatbuffers::flatbuffers Boost::mp11 safeint_interface nlohmann_json::nlohmann_json)
Add Tracelogging for profiling (#1639) Enabled only if onnxruntime_ENABLE_INSTRUMENT is ON
2019-11-12 05:34:10 +00:00
if(onnxruntime_ENABLE_INSTRUMENT)
target_compile_definitions(onnxruntime_session PUBLIC ONNXRUNTIME_ENABLE_INSTRUMENT)
endif()
enable torch interop build (#8493) * fix build - python.h not found * disable --build_shared_lib for ortmodule tests * fix * fix the build flag * disable --build_shared_lib for training path (not only for ortmodule) * fix missing test model files * disable test CApiTest.test_custom_op_library when ENABLE_TRAINING_TORCH_INTEROP is ON * enable custom_op_library build * fix build * fix * merge master and fix build failure * build onnx_test_runner when onnxruntime_ENABLE_TRAINING_TORCH_INTEROP is ON * resolve comments * use --enable_training_torch_interop to replace "onnxruntime_ENABLE_TRAINING_TORCH_INTEROP=ON"
2021-08-19 01:16:32 +00:00
Update compliance tasks in python packaging pipeline and fix some compile warnings (#8471) 1. Update SDLNativeRules from v2 to v3. The new one allows us setting excluded paths. 2. Update TSAUpload from v1 to v2. And add a config file ".gdn/.gdntsa" for it. 3. Fix some parentheses warnings 4. Update cmake to the latest. 5. Remove "--x86" build option from pipeline yaml files. Now we can auto-detect cpu architecture from python. So we don't need to ask user to specify it.
2021-07-31 00:16:37 +00:00
if(NOT MSVC)
set_source_files_properties(${ONNXRUNTIME_ROOT}/core/session/environment.cc PROPERTIES COMPILE_FLAGS "-Wno-parentheses")
endif()
Check kernel def hashes (#7120) Add unit test for verifying kernel def hashes. Add way to add new types to kernel definition without changing hash.
2021-04-02 00:42:58 +00:00
target_include_directories(onnxruntime_session PRIVATE ${ONNXRUNTIME_ROOT} ${eigen_INCLUDE_DIRS})
Enable selecting custom ops in onnxruntime-extensions. (#8826) * Enable selecting custom ops in onnxruntime-extensions. * Move cmake_helper.py. * Remove over-indented spaces. * Add doc. * Remove onnxruntime-extensions from git submodules, and user should pass path of onnxruntime-extensions for build. * Modify doc. * Remove argument --enable_onnxruntime_extensions and use --onnxruntime_extensions_path. * Fix build error. * Fix build error. * Use onnxruntime_extensions_path. * support both submodule and external source folders * refinement * Update cgmanifest.json * Support building onnxruntime-extensions from either git submodule or pre-pulled path. * Update doc. * more standard name * update docs * add the copyright header Co-authored-by: Zuwei Zhao <zuzhao@microsoft.com> Co-authored-by: Wenbing Li <wenbingl@outlook.com> Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com>
2021-08-28 04:45:52 +00:00
if (onnxruntime_USE_EXTENSIONS)
target_link_libraries(onnxruntime_session PRIVATE onnxruntime_extensions)
Integrate onnxruntime-extensions into onnxruntime. (#8143) Co-authored-by: Zuwei Zhao <zuzhao@microsoft.com>
2021-07-01 16:34:03 +00:00
endif()
Initial bootstrap commit.
2018-11-20 00:48:22 +00:00
add_dependencies(onnxruntime_session ${onnxruntime_EXTERNAL_DEPENDENCIES})
set_target_properties(onnxruntime_session PROPERTIES FOLDER "ONNXRuntime")
Move CopyTensor out of IExecutionProvider interface. (#1268) * add ortdevice class * add data transfer manager for copying tensors. * update * add data trasnfer for gpu * fix constexpr build break. * update * remove unnecessary header files. * remove unnecessary header files. * add dependency * add dependency * add dependency * add dependency * fix linux build break. * update * fix build break * fix build break * fix build break * update * update * update c api. * update to not use OrtCreateAllocatorInfo * change to all eps . * fix linux build break * remove useless codes. * update * move datatransfermanager in session state * update * fix cuda build break. * fix comments * fix windows GPU build. * fix comments * fix build break * fix comments * fix test failure * update * fix comments * fix onnx runtime server. * update * fix test failure. * fix comments * fix comment
2019-07-11 21:49:20 +00:00
if (onnxruntime_USE_CUDA)
target_include_directories(onnxruntime_session PRIVATE ${onnxruntime_CUDNN_HOME}/include ${CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES})
endif()
[ROCm] static re-hipify of CUDA EP to ROCm EP, now a shared provider (#8877) * re-hipify all rocm EP sources * fix all other files affected by re-hipify * add cuda_provider_factory.h to amd_hipify.py * do not use cudnn_conv_algo_search in ROCm EP, missing reduce min registration * Fix ReduceConsts template specialization introduced in #9101. Fixes the error when building for ROCm 4.3.1: error: too many template headers for onnxruntime::rocm::ReduceConsts<__half>::One (should be 0) * fix flake8 error in amd_hipify.py * speed up hipify with concurrent.futures * flake8 fix in amd_hipify.py
2021-10-14 22:15:51 +00:00
if (onnxruntime_USE_ROCM)
Update CK and fix performance issue on dev machine (#13531) 1. Update CK to its latest develop branch 2. `-mllvm -amdgpu-early-inline-all=true` is critical to CK's performance, ensure it is properly configured. - The flags are propagated from target `hip-lang::device`'s `INTERFACE_COMPILE_OPTIONS`, we must not manually add the flags. - Instead, we must ensure this target is properly configured by checking _CMAKE_HIP_DEVICE_RUNTIME_TARGET is set. TL,DR `hip-lang::device` sometime will be not be properly configured if our `CMAKE_PREFIX_PATH` is not configured carefully. In the CI docker, the configuration is in good state, but on dev machine it is not, which then silently result poor performance for kernels. We fixed it in this PR and add a guard to avoid unsuccessful future editing and to prevent convoluted debugging process. `_CMAKE_HIP_DEVICE_RUNTIME_TARGET ` is shared in `/opt/rocm/lib/cmake/hip-lang/hip-lang-config.cmake` and it is internal to [CMake](https://gitlab.kitware.com/cmake/cmake/-/merge_requests/6121/diffs), the variable name will not be changed in the foreseeable future.
2022-11-03 11:32:30 +00:00
target_compile_options(onnxruntime_session PRIVATE -Wno-sign-compare -D__HIP_PLATFORM_AMD__=1 -D__HIP_PLATFORM_HCC__=1)
[ROCm] static re-hipify of CUDA EP to ROCm EP, now a shared provider (#8877) * re-hipify all rocm EP sources * fix all other files affected by re-hipify * add cuda_provider_factory.h to amd_hipify.py * do not use cudnn_conv_algo_search in ROCm EP, missing reduce min registration * Fix ReduceConsts template specialization introduced in #9101. Fixes the error when building for ROCm 4.3.1: error: too many template headers for onnxruntime::rocm::ReduceConsts<__half>::One (should be 0) * fix flake8 error in amd_hipify.py * speed up hipify with concurrent.futures * flake8 fix in amd_hipify.py
2021-10-14 22:15:51 +00:00
target_include_directories(onnxruntime_session PRIVATE ${onnxruntime_ROCM_HOME}/hipfft/include ${onnxruntime_ROCM_HOME}/include ${onnxruntime_ROCM_HOME}/hipcub/include ${onnxruntime_ROCM_HOME}/hiprand/include ${onnxruntime_ROCM_HOME}/rocrand/include)
# ROCM provider sources are generated, need to add include directory for generated headers
target_include_directories(onnxruntime_session PRIVATE ${CMAKE_CURRENT_BINARY_DIR}/amdgpu/onnxruntime ${CMAKE_CURRENT_BINARY_DIR}/amdgpu/orttraining)
endif()
Fix usage of enable_training_ops and reduce ifdef complexity for training builds (#13888) ### Description Fix usage of enable_training_ops and reduce ifdef complexity for training builds. ### Motivation and Context This is the second refactoring PR towards creating a dedicated build for on device training. This PR aims to reduce some complexity. We can set ENABLE_TRAINING_OPS in cmake when either ENABLE_TRAINING or ENABLE_TRAINING_ON_DEVICE is selected, this way we dont have to use if defined(ENABLE_TRAINING) || defined(ENABLE_TRAINING_ON_DEVICE ) everywhere in the code. - If it fixes an open issue, please link to the issue here. -->
2022-12-14 16:32:46 +00:00
if (onnxruntime_ENABLE_TRAINING_OPS)
Introduce training changes.
2020-03-11 21:25:37 +00:00
target_include_directories(onnxruntime_session PRIVATE ${ORTTRAINING_ROOT})
endif()
Extend node debugging utilities to push tensors and node placement to SQL database (#8672) * adding support for tracing to sqldb instead of files * use compiled statements * script to pull tensors from db * link sqlite3 * remove node info redundant with onnx graph * addressing PR comments * address PR comments and include program counter * third party notice * use find_pacakge * add to cgmanifests.json * address thread safety and add pid suffix * build fi * python script to select on devicetype * remove unpopulated and redundant Shape and Type fields * comment * comment * PR comments * add graph execution counter to session state * move increment to inference session * std::endl to \n * ifdef on graph execution counter * add ifdef to inference session * move DEBUG_NODE_INPUTS_OUTPUTS to CMakeLists.txt
2021-08-21 07:40:12 +00:00
Packaging pipeline now builds with PythonOp (aka running autograd.Function) (#8652) This PR disable UTs in training's package pipelines for building packages with PythonOp (torch.autograd.Function).
2021-08-17 17:55:13 +00:00
if (onnxruntime_ENABLE_TRAINING_TORCH_INTEROP)
C API version 0.001 (#11758) * C API version 0.001 * fix linker issues * fixes for save checkpoint api * plus fixes based on tests * plus test_runner and other changes * Plus cosmetic updates * remove unnecessary headers * plus some updates * plus more changes Co-authored-by: Ashwini Khade <askhade@microsoft.com@orttrainingdev10.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>
2022-06-15 18:13:35 +00:00
onnxruntime_add_include_to_target(onnxruntime_session Python::Module)
Packaging pipeline now builds with PythonOp (aka running autograd.Function) (#8652) This PR disable UTs in training's package pipelines for building packages with PythonOp (torch.autograd.Function).
2021-08-17 17:55:13 +00:00
endif()
[cmake] Export multi targets in static build (#11063) * [cmake] Export multi targets in static build * Install more components in static build, format some code * Fix code pos
2022-04-04 05:37:18 +00:00
if (NOT onnxruntime_BUILD_SHARED_LIB)
added support for cmake "find_package" (#8919) **Description**: Adds support for cmake find_package. **Motivation and Context** As mentioned in issue #7150 onnxruntime doesn't have support for CMake find_package, this PR adds that and also adds the CMake package version file. Now anyone can link onnxruntime like this: ```cmake find_package(onnxruntime) add_executable(test Source.cpp) target_link_libraries(test PRIVATE onnxruntime::onnxruntime) ``` this also simplifies #3124
2023-06-20 05:20:31 +00:00
install(DIRECTORY ${PROJECT_SOURCE_DIR}/../include/onnxruntime/core/session DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/onnxruntime/core)
[cmake] Export multi targets in static build (#11063) * [cmake] Export multi targets in static build * Install more components in static build, format some code * Fix code pos
2022-04-04 05:37:18 +00:00
install(TARGETS onnxruntime_session
ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR}
FRAMEWORK DESTINATION ${CMAKE_INSTALL_BINDIR})
endif()
Fix hipify to avoid nccl_service.h: No such file or directory (#13852) Fix various flaky build error due to onnxruntime_session missing dependencies on hipify generated files.
2022-12-07 01:10:37 +00:00
if (onnxruntime_USE_NCCL AND onnxruntime_USE_ROCM)
add_dependencies(onnxruntime_session generate_hipified_files)
endif()
Reference in a new issue Copy permalink