onnxruntime/cmake/onnxruntime_framework.cmake

66 lines
3.3 KiB
CMake
Raw Normal View History

2018-11-20 00:48:22 +00:00
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License.
2019-04-29 19:58:20 +00:00
file(GLOB_RECURSE onnxruntime_framework_srcs CONFIGURE_DEPENDS
2018-11-20 00:48:22 +00:00
"${ONNXRUNTIME_INCLUDE_DIR}/core/framework/*.h"
"${ONNXRUNTIME_ROOT}/core/framework/*.h"
"${ONNXRUNTIME_ROOT}/core/framework/*.cc"
)
if (onnxruntime_MINIMAL_BUILD)
set(onnxruntime_framework_src_exclude
"${ONNXRUNTIME_ROOT}/core/framework/provider_bridge_ort.cc"
"${ONNXRUNTIME_ROOT}/core/framework/fallback_cpu_capability.h"
"${ONNXRUNTIME_ROOT}/core/framework/fallback_cpu_capability.cc"
)
# custom ops support must be explicitly enabled in a minimal build. exclude if not.
if (NOT onnxruntime_MINIMAL_BUILD_CUSTOM_OPS)
list(APPEND onnxruntime_framework_src_exclude
"${ONNXRUNTIME_INCLUDE_DIR}/core/framework/customregistry.h"
"${ONNXRUNTIME_ROOT}/core/framework/customregistry.cc"
)
endif()
list(REMOVE_ITEM onnxruntime_framework_srcs ${onnxruntime_framework_src_exclude})
endif()
2018-11-20 00:48:22 +00:00
source_group(TREE ${REPO_ROOT} FILES ${onnxruntime_framework_srcs})
onnxruntime_add_static_library(onnxruntime_framework ${onnxruntime_framework_srcs})
if(onnxruntime_ENABLE_INSTRUMENT)
target_compile_definitions(onnxruntime_framework PRIVATE ONNXRUNTIME_ENABLE_INSTRUMENT)
endif()
if(onnxruntime_USE_TENSORRT)
# TODO: for now, core framework depends on CUDA. It should be moved to TensorRT EP
Ryanunderhill/cuda shared (#7626) * 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 commit c7ec2cfe98e4dcc30e1a54cad71adb89ab18adde. * Revert "Disable DLL test" This reverts commit e901cb93aafd537af088fa29629029a479926362. * Revert "Test adding unload method for shared providers" This reverts commit c427b7879989be93572b09c4662b1fa8b153eec9. * 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 commit be35fc2a5ab53868568791f1e54320e6c7fc75ce. * 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 commit 648679b37093740bbefc7b41ff53d3239451333f. * 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 commit a73a811516ad2acdbbea890a2ae2143341f915ad. * Revert "Remove cupti library dependency from core library" This reverts commit 6a889ee8bf72f34f44b8a4642728b7bd83f61255. * 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>
2021-05-20 14:53:47 +00:00
target_include_directories(onnxruntime_framework PRIVATE ${ONNXRUNTIME_ROOT} ${eigen_INCLUDE_DIRS} ${onnxruntime_CUDNN_HOME}/include PUBLIC ${CMAKE_CURRENT_BINARY_DIR} ${CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES})
else()
Ryanunderhill/cuda shared (#7626) * 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 commit c7ec2cfe98e4dcc30e1a54cad71adb89ab18adde. * Revert "Disable DLL test" This reverts commit e901cb93aafd537af088fa29629029a479926362. * Revert "Test adding unload method for shared providers" This reverts commit c427b7879989be93572b09c4662b1fa8b153eec9. * 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 commit be35fc2a5ab53868568791f1e54320e6c7fc75ce. * 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 commit 648679b37093740bbefc7b41ff53d3239451333f. * 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 commit a73a811516ad2acdbbea890a2ae2143341f915ad. * Revert "Remove cupti library dependency from core library" This reverts commit 6a889ee8bf72f34f44b8a4642728b7bd83f61255. * 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>
2021-05-20 14:53:47 +00:00
target_include_directories(onnxruntime_framework PRIVATE ${ONNXRUNTIME_ROOT} ${eigen_INCLUDE_DIRS} PUBLIC ${CMAKE_CURRENT_BINARY_DIR})
endif()
# Needed for the provider interface, as it includes training headers when training is enabled
if (onnxruntime_ENABLE_TRAINING OR onnxruntime_ENABLE_TRAINING_OPS)
target_include_directories(onnxruntime_framework PRIVATE ${ORTTRAINING_ROOT})
if (onnxruntime_USE_NCCL OR onnxruntime_USE_MPI)
target_include_directories(onnxruntime_framework PUBLIC ${MPI_CXX_INCLUDE_DIRS})
endif()
endif()
onnxruntime_add_include_to_target(onnxruntime_framework onnxruntime_common onnx onnx_proto protobuf::libprotobuf flatbuffers)
2018-11-20 00:48:22 +00:00
set_target_properties(onnxruntime_framework PROPERTIES FOLDER "ONNXRuntime")
# need onnx to build to create headers that this project includes
add_dependencies(onnxruntime_framework ${onnxruntime_EXTERNAL_DEPENDENCIES})
# In order to find the shared provider libraries we need to add the origin to the rpath for all executables we build
# For the shared onnxruntime library, this is set in onnxruntime.cmake through CMAKE_SHARED_LINKER_FLAGS
# But our test files don't use the shared library so this must be set for them.
# For Win32 it generates an absolute path for shared providers based on the location of the executable/onnxruntime.dll
build ONNXRuntime into WebAssembly (#6478) * Simplified version of WebAssembly support to keep most of existing data structures and add cmake using Ninja and emcmake * Clean up CMakeLists.txt and add an example to create and compute a kernel * Load a model from bytes and remove graph building steps * Add all cpu and contrib ops with mlas library * WebAssembly build with Onnxruntime C/CXX API * Use protobuf cmakefile directory instead of adding every necessary source file * Fix invalid output at example * add missing files * Change an example to use Teams model and support ort mobile format * add API for javascript * fix input releasing in _ort_run() * update API * Let onnxruntime cmake build WebAssembly with option '--wasm' * allow one-step building for wasm * Make build script working on Linux and MacOS * Fix broken build from Windows command * Enable unit test on building WebAssembly * Resolve comments * update build flags * wasm conv improvement from: 1) GemmV; 2) Depthwise direct convolution 3x3; 3) Direct convolution 3x3 * Cleaned mlas unittest. * use glob * update comments * Update baseline due to loss scale fix (#6948) * fix stream sync issue (#6954) * Enable type reduction in EyeLike, Mod, random.cc CPU kernels. (#6960) * Update EyeLike CPU kernel. * Update Mod CPU kernel. * Update Multinomial CPU kernel. * Slight improvement to Pad CPU kernel binary size. * Update RandomNormal[Like], RandomUniform[Like] CPU kernels. * Fix warning from setting multiple MSVC warning level options. (#6917) Fix warning from setting multiple MSVC warning level options. Replace an existing /Wn flag instead of always appending a new one. * MLAS: quantized GEMM update (#6916) Various updates to the int8_t GEMMs: 1) Add ARM64 udot kernel to take advantage of dot product instructions available in newer cores. Some models run 4x faster than the stock implementation we used before. 2) Refactor the x64 kernels to share common code for AVX2(u8u8/u8s8/avxvnni) vs AVX512(u8u8/u8s8/avx512vnni) to reduce binary size. 3) Extend kernels to support per-column zero points for matrix B. This is not currently wired to an operator. * Implement QLinearAveragePool with unit tests. (#6896) Implement QLinearAveragePool with unit tests. * Attention fusion detect num_heads and hidden_size automatically (#6920) * fixed type to experimental session constructor (#6950) * fixed type to experimental session constructor Co-authored-by: David Medine <david.medine@brainproducts.com> * Update onnxruntime_perf_test.exe to accept free dimension overrides (#6962) Co-authored-by: Ori Levari <orlevari@microsoft.com> * Fix possible fd leak in NNAPI (#6966) * Release buffers for prepacked tensors (#6820) Unsolved problems: 1. One test failure was caused by a bug in Cudnn rnn kernels, when they can allocate a buffer and partially initialize it, the garbage data near tail of the buffer caused problem in some of the hardware. To attack this problem in a broader sense, should we add code in our allocators, and during a memory fuzzing test, fill an allocated buffer with garbage before returning to the caller? 2. Prepacking is used more widely than we know. For instance, Cudnn rnn kernels also cache their weights. They mix several weight tensors together into a single buffer, and never touch the original weight tensor anymore. This is the same idea with pre-pack, but they didn't override the virtual function, and they never tried to release those weight tensors, leading to memory waste. It also seems to me that there are some other kernels have similar behavior. Wonder how much memory we can save if we try to cleanup those too. 3. Turning off memory pattern planning does increase memory fragmentation, leading to out of memory error in some training test cases. Perhaps we can revisit the idea of pushing kernels-creation stage earlier, and then during initializer deserialization, we only avoid tracing those that will be prepacked. * Enable type reduction for Range, ReverseSequence, ScatterND, Split, and Unique CPU kernels. (#6963) * add CI * fix test in ci * fix flags for nsync in wasm build * add copyright banner * fix wasm source glob * add missing exports * resolve comments * Perf gain by make packb wide to 4 from 16 on GEMM for WASM. Remove no need direct conv in previous perf tuning. * fix buildbreak introduced from latest master merge * fix buildbreak in mlasi.h * resolve all comments except MLAS * rewrite packb related 3 functions for WASM_SCALAR seperately rather than using #ifdef in each. and other changes according to PR feedback in mlas. * More complete scalar path in sgemm from Tracy. * Fix edge case handling in depthwise conv2d kernel 3x3. where: *) support input W==1 and H==1 *) recalc in accurate pad_right and pad_bottom *) support hidden pad_right == 2 or pad_bottom == 2 when W == 1 or H==1 and no pad left/top * Add more test coverage for conv depthwise from Tracy. Fix one typo according to PR. * resolve comments * replace typedef by using * do not use throw in OrtRun() * output error message Co-authored-by: Sunghoon <35605090+hanbitmyths@users.noreply.github.com> Co-authored-by: Lei Zhang <zhang.huanning@hotmail.com> Co-authored-by: Wei-Sheng Chin <wschin@outlook.com> Co-authored-by: Tianlei Wu <tlwu@microsoft.com> Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com> Co-authored-by: Tracy Sharpe <42477615+tracysh@users.noreply.github.com> Co-authored-by: David Medine <david.eric.medine@gmail.com> Co-authored-by: David Medine <david.medine@brainproducts.com> Co-authored-by: Ori Levari <ori.levari@microsoft.com> Co-authored-by: Ori Levari <orlevari@microsoft.com> Co-authored-by: Guoyu Wang <62914304+gwang-msft@users.noreply.github.com> Co-authored-by: Chen Fu <chenfucs@gmail.com>
2021-04-06 23:18:10 +00:00
if (UNIX AND NOT APPLE AND NOT onnxruntime_MINIMAL_BUILD AND NOT onnxruntime_BUILD_WEBASSEMBLY)
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,-rpath='$ORIGIN'")
endif()
if (onnxruntime_DEBUG_NODE_INPUTS_OUTPUTS)
target_compile_definitions(onnxruntime_framework PRIVATE DEBUG_NODE_INPUTS_OUTPUTS)
endif()
2018-11-23 04:56:43 +00:00
install(DIRECTORY ${PROJECT_SOURCE_DIR}/../include/onnxruntime/core/framework DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/onnxruntime/core)