* update onnx-tensorrt parser to master
* disable unsupported tests
* add cuda sm 75 for T4
* update tensorrt pipeline
* update trt pipelines
* update trt pipelines
* Update linux-gpu-tensorrt-ci-pipeline.yml
* update trt cid pipeline
* Update linux-gpu-tensorrt-ci-pipeline.yml
* Update Tensorrt Windows build pool and TensorRT/CUDA/CuDNN version
* update to cuda11.4 in trt ci pipeline
* update base image to cuda11.4
* update packaging pipeline to cuda11.4
* clean up
* remove cuda11.1 and cuda11.3 docker file
* disable unsupported tensorrt tests at runtime
* Update linux-multi-gpu-tensorrt-ci-pipeline.yml
Pytorch cpuinfo library allows us to query current cpu features, micro-architecture and cache size, etc. These information is needed for targeted performance optimizations.
Unfortunately it does not work under Windows/ARM. We need to develop our own later
Co-authored-by: Chen Fu <fuchen@microsoft.com>
Description:
This change add google benchmark git repo as a submodule in onnxruntime repo.
Motivation and Context
Currently we have benchmarking code that depends on google benchmark. The version we are using has cross compilation issues for ARM CPUs. Recent changes in Google benchmark fixed these issues.
Another problem is that we now rely on ONNX to pull in Google benchmark, an indirect dependency. Updating ONNX involves complex steps and rightly so. However, updating Google benchmark dependency should not be hindered by these processes.
* 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>
Changes include:
* Revert Event Pool changes
* Add copyright and revert unrelated changes
* Add DLPack as submodule and remove to_dlpack and from_dlpack from public API
* Update golden numbers for DHP Parallel tests
* Update ORTTrainer unit test numbers
* Rollback to DLPack v0.3
* Disable flaky test
* Update third party notices and CG manifest file
* Minor refactoring of ORTValue API
* fix hash conflict
* Add verbose for engine deserialization and destroy old engine memory if new engine is generated
* update parser
* Update tensorrt_execution_provider.cc
* use a better hash algorithm
* Update tensorrt_execution_provider.cc
* correct some errors in the flatbuffers schema, move flatbuffers submodule to cmake/external
* update the ort flatbuffers schema to use less namespace
* minor update
Co-authored-by: gwang0000 <62914304+gwang0000@users.noreply.github.com>
* add flatbuffers submodule
* test version of flat buffer schema
* test version of flat buffer schema
* minor updates
* add serialization of the value info, group defs in different namespace
* update comments
* update cgmanifest.json
* update namespace, changed typeinfovalue to use union, added root_type and file_identifier
* add new container type, add max_node_index to graph
* add serializing session state
* addressed review comments
* minor updates
Co-authored-by: gwang0000 <62914304+gwang0000@users.noreply.github.com>
* Add protobuf mutator library as a git submodule
* Added files and instructions to build the protobuf mutator library in CMake
* Added fuzzing flag to build system and added fuzzing dependency library. To run fuzzing test use the flags --fuzz_testing --build_shared_lib --use_full_protobuf --cmake_generator 'Visual Studio 16 2019'
* Added src files and build instructions for the main fuzzing engine
* Removed Random number generation test from inside the engine
* Added license header to files
* Removed all pep8 violations introduced by this change and other E501 violations
The default branch for the spdlog repository on GitHub recently changed from "master"
to "v1.x", which has a different API for `syslog_sink::syslog_sink()`. This breaks
builds of the server for anyone who has checked out the submodules since that change.
Fixes#4077.
Co-authored-by: Derek Murray <demurra@microsoft.com>
* Switch to CUDA10.2
* Update win-gpu-tensorrt-ci-pipeline.yml
* Update win-gpu-tensorrt-ci-pipeline.yml
* remove dynamic_shape
* update onnx-tensorrt submodule
* check if input shape is specified for TensorRT subgraph input and enable some TensorRT unit tests
* fix format issue
* add shape inference instruction for TensorRT
* update according to the reviews
* Update win-gpu-tensorrt-ci-pipeline.yml
* update onnx-tensorrt submodule to trt7 branch
* add fp16 option for TRT7
* switch to master branch of onnx tensorrt
* update submodule
* update to TensorRT7.0.0.11
* update to onnx-tensorrt for TensorRT7.0
* switch to private branch due to issues in master branch
* remove trt_onnxify
* disable warnings c4804 for TensorRT parser
* disable warnings c4702 for TensorRT parser
* add back sanity check of shape tensort input in the parser
* disable some warnings for TensorRT7
* change fp16 threshold for TensorRT
* update onn-tensorrt parser
* fix cycle issue in faster-rcnn and add cycle detection in GetCapability
* Update TensorRT container to v20.01
* Update TensorRT image name
* Update linux-multi-gpu-tensorrt-ci-pipeline.yml
* Update linux-gpu-tensorrt-ci-pipeline.yml
* disable rnn tests for TensorRT
* disable rnn tests for TensorRT
* disabled some unit test for TensorRT
* update onnx-tensorrt submodule
* update build scripts for TensorRT
* formating the code
* Update TensorRT-ExecutionProvider.md
* Update BUILD.md
* Update tensorrt_execution_provider.h
* Update tensorrt_execution_provider.cc
* Update win-gpu-tensorrt-ci-pipeline.yml
* use GetEnvironmentVar function to get env virables and switch to Win-GPU-2019 agent pool for win CI build
* change tensorrt path
* change tensorrt path
* fix win ci build issue
* update code based on the reviews
* fix build issue
* roll back to cuda10.0
* add RemoveCycleTest for TensorRT
* fix windows ci build issues
* fix ci build issues
* fix file permission
* fix out of range issue for max_workspace_size_env
This change adds a new execution provider powered by [DirectML](https://aka.ms/DirectML).
DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning on Windows. DirectML provides GPU acceleration for common machine learning tasks across a broad range of supported hardware and drivers.
The DirectML execution provider is capable of greatly improving evaluation time of models using commodity GPU hardware, without sacrificing broad hardware support or requiring vendor-specific extensions to be installed.
**Note** that the DML EP code was moved verbatim from the existing WindowsAI project, which is why it doesn't yet conform to the onnxruntime coding style. This is something that can be fixed later; we would like to keep formatting/whitespace changes to a minimum for the time being to make it easier to port fixes from WindowsAI to ORT during this transition.
Summary of changes:
* Initial commit of DML EP files under onnxruntime/core/providers/dml
* Add cmake entries for building the DML EP and for pulling down the DirectML redist using nuget
* Add a submodule dependency on the Windows Implementation Library (WIL)
* Add docs under docs/execution_providers/DirectML-ExecutionProvider.md
* Add support for DML EP to provider tests and perf tests
* Add support for DML EP to fns_candy_style_transfer sample
* Add entries to the C ABI for instantiating the DML EP
Remove gsl subodule and replace with a local copy of gsl-lite
Refactor for onnxruntime::make_unique
gsl::span size and index are now size_t
Remove lambda auto argument type detection.
Remove constexpr from fail_fast in gsl due to Linux not being happy.
Comment out std::stream support due to MacOS std lib broken.
Move make_unique into include/core/common so it is accessible for server builds.
Relax requirements for onnxruntime/test/providers/cpu/ml/write_scores_test.cc
due to x86 build.
Add ONNXRUNTIME_ROOT to Server Lib includes so gsl is recognized
* add mimalloc submodule
* basic hooks into execution provider header and build script option
* pull mimalloc into build
* windows has to use the override vcxproj already set up, and disable bfcarena when using mimalloc
* fix import_location
* generalize build msbuild command
* add mimalloc dependency to python package as well as various commenting cleanups
* update mimalloc commit as stop gap
* include mimalloc changes from master
* create capi directory if doesn't exist for mimalloc copying over
* disable runtime hooks and remove old comment
* temporary change to test CI
* fetch the mimalloc output name property
* uniformly call target_link_libraries
* query cmake to get the correct windows sdk to target
* revert change to trailing directory slash
* pickup windows sdk off msbuild path if possible
* copy the produced dll/so at install time, not configure time
* deal with mimalloc unimplemented atomic
* move to dev branch of mimalloc to avoid atomic issues on gcc
* for windows specify solution settings (x86) rather than individual project settings
* pin mimalloc submodule to updated commit
* typo
* Revert "temporary change to test CI"
This reverts commit 764867376936a5d307dded3cc37f00a34e3b0c96.
* remove memory copy between CUDA and TRT
* add info to RegisterExecutionProvider input
* use new IDeviceAllocator for trt allocator
* remove SetDefaultInputsMemoryType from TRT EP
* remove onnx-tensorrt 5.0
* add submodule onnx-tensorrt branch 5.1
* remove redundancy
* Update transformer_memcpy.cc
* Update tensorrt_execution_provider.cc
* switch to TensorRT 5.1.5.0
* update python binding
* disable failed test case on TensorRT
* Update activation_op_test.cc
* upgrade to TensorRT container 19.06
* update according to feedback
* add comments
* remove tensorrt allocator and use cuda(gpu) allocator
* update onnx-tensorrt submodule
* change ci build cuda directory name
* replace log sinks
* limit headers to include dir
* first changes to do dynamic linking
* wip for using cxx api
* remove weird dangling dependency
* building with tests failing
* finish updating converters
* fix const
* intital introduction of typedef
* change logging to use spdlog
* get tests passing
* clang format
* map logging levels better
* clean up unused imports
* trent cr comments
* clang-format
* code review comments
* changing buffer use to reserve
* Dynamically link
* revert tvm
* update binary uploading
* catch exceptions by const-ref
* Revert "revert tvm"
This reverts commit 387676dd1018134d15eb71fa126f7caf94380800.
* fix typo
* update versioning of lib
Description:
This change adds the common part of TVM based codegen library. It includes following parts:
* Microsoft TVM Inventory (MTI): a set of TVM ops for neural networks, similar to TOPI
* Compiler pass for traversing ONNX graph and generate TVM ops
* Compiler pass for traversing generated graph and specify TVM schedule
* Compiler pass for handling weight layout
* Utils for debugging
Motivation and Context:
TVM is an open deep learning compiler stack for cpu, gpu and specialized accelerators. To leverage it in ONNX, we built an execution provider named Nuphar. Currently, Nuphar gets good performance on CPUs with AVX2 on quantized LSTM models.
This codegen library was part of Nuphar execution provider. It is split out for sharing with other execution providers, as we'd like to reuse TVM in more devices.
* init
* Update DNNLibrary
* Update DNNLibrary, set compiler flags, it compiles now
* Add more missing flags, add test
* Update DNNLibrary
* Update Compile method, fix allocator and some other bugs
* Update DNNLibrary
* Implement CopyTensor
* Not delete state explicitly since it is managed by unique_ptr
* Add the missing files when SingleUnitTestProjct is ON
* misc changes
* Fix wrong name in provider factory
* Add my own test
* Update the code of add node into graph, and add the missing initializer into graph
* Fix the bug that re-build the graph produces extra output
* Update DNNLibrary
* Transpose nchw (ONNX) -> nhwc (NNAPI)
* Add license
* Add GetSupportedNodes method (implement it later)
* Rename onnxruntime_nnapi_test->onnxruntime_nnapi_squeezenet_test
* Update squeezenet_test.cpp after rebase master
* Remove squeezenet_test.cpp since it is almost same with the c++ sample
* Update DNNLibrary for GetSupportedNodes
* Update GetSupportedNodes
* Revert "Remove squeezenet_test.cpp since it is almost same with the c++ sample"
This reverts commit a97575fd9ff49e50ba1dc8d8154790d8cd86c48d.
* Update DNNLibrary
* Fix multiple outputs bug
* Remove GetKernelRegistry
* Revert "Revert "Remove squeezenet_test.cpp since it is almost same with the c++ sample""
This reverts commit 2a0670e9cbf10ea654111ce39e198a4be0ddd838.
* Set default memory type of NNAPI EP
* Add CPUOutput allocator
* Update DNNLibrary for multiple outputs
* Fix bug of nhwc->nchw
* Remove GetExecutionHandle()
* Improve TensorRT GetCapability Accuracy
* Update onnxruntime_providers.cmake
* made changes based on feedback
* update unit tests for TensorRT
* update onnx-tensorrt submodule to v5.0 branch
* remove uncessary comments
* convert int32 to int64 at inferencing output
* add more data types in compute
* change returns in compute
* use StatusCode as return in compute
