* Refine optimizers
* Address PR comments
* Changes from PR comments and discussion.
* Fixed signed/unsigned mismatch
* Address PR comments
* Address PR comments
* Fix linux build
* Fix issue with mkldnn logic.
* Turn off optimizers by default for operator unit tests.
* Handle edge case of graph with no nodes in partitioner so all execution providers don't need to.
* Comment out change to turn off optimizers for unit tests. Add details on what needs to be done to re-enable.
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
In ORT, there is only 3 cuda stream: default, HtoD, DtoH. And both HtoD and DtoH are non-blocking stream. Thus, per-thread stream mode doesn't have any benefit.
I also tried in multiple thread env and the legacy mode is also better than per-thread model.
Below is the perf of a 3 layer bert on v100. Unit is ms:
batch size 1:
concurrency | c=1 | c=2 | c=4
legacy | 0.54 | 1.17 | 2.68
per-thread | 0.66 | 1.37 | 2.86
batch size 4:
concurrency | c=1 | c=2 | c=4
legacy | 1.1 | 2.22 | 4.6
per-thread | 1.21 | 2.44 | 4.98
batch size 64:
concurrency | c=1 | c=2 | c=4
legacy | 8.09 | 16.13 | 32.37
per-thread | 8.18 | 16.26 | 32.45
* Adjust ngraph cmake files to onnx 1.5.0
* Enable LSTM reverse direction mode in nGraph EP
* Enable full support for the Split op in nGraph EP
* Revert "Disable the unsigned input Shrink op tests for nGraph until the next update"
This reverts commit 257b42a55bdd98f804d4846868542b8e3aeb4b4e.
* Enable Gather and remove unused subgraph attribute
* Remove the unused param from AppendClusterToSubGraph
* Fix for the incorrect onnx opset version
* Use the r0.26 release branch before the tag is created
* Enable the quantizelinear and dequantizelinear for NGEP
* Use the v0.26.0-rc.2 tag in ngraph.cmake
* Add skip for modes others than default in Pad operator
* Reenable negative axis tests for ngraph
* Use temporary ngraph version
* Use branch name instead of SHA for temporary ngraph branch
* Use ngraph v0.26.0-rc.4
* Remove patch for missing symbol in MKLDNN
* Use MKLDNN 1.0 in ngraph
* Exclude the Pad op for opsets greater than 10
* Disable quantizelinear and dequantizelinear tests for ONNX 1.5.0
* Fix the onnx-headers related compilation errors
* ONNX libs linking fix
* Use a tag for ngraph and support more Pad modes
* Use the v0.26.0 release tag for nGraph
* Update ngraph to RC8 - bigobj flag for Windows builds
* Fix the MKLDNN constexpr error on Windows
* save status: add tiling layout; add avx512 skylake cpuid info
* unit tests and matmul integer model passed on skylake, need to verify model
* save commit before update master
* fix check
* address comments
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
* Fixed a bug of missing tvm in python wheel
* Put Nuphar Python scripts into wheel
* Add note book tutorial
* Some improvements in symbolic shape inference for quantized models
* Added support for Hetero plugin
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Fixed spelling error in cmake for hetero plugin
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Added listener to print messages from the plugin
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Updated Documentation for VAD-F enablement
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Added VAD-F option for FPGA
*Disabled unit tests and backed tests because FPGA only accepts NCHW models
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Added comment for why tests need to be disabled on VAD-F
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Avoid variable length stack array variables for VC++ compatibility
Use dynamically allocated arrays or vectors instead.
* windows enabling
* openvino windows build
* Update build instructions
* resolve conflicts for PR
* remove debug messages from cmake
* PR fix for window support
* Fix symbolic shape inference for faster_rcnn, mask_rcnn, yolov3
Force merge when --auto_merge, on symbolic dims which sympy cannot simplify
Add symbolic inference for Resize opset 10
Add support for step != 1 in Slice
Add support for computed dim in TopK
Bug fixes in passing symbolic dims from subgraph
Fix an outdate comment in Nuphar provider header
* 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.
* Bump onnx to latest
Update onnx.in.proto with changes for SparseTensor.
* add temp skip tests
* remove passed tests from skip list
* skip more tests for new ops in opset 11
* skip crashing tests
* update handling of new attribute types sparse tensor and sparse tensors
* advance onnx commit and remove skip cpu_flaky_tests
* temporarily skip yolo3 model test due to resize opset10 shape inference regression
* update proto for onnxruntime server
* advance onnx commit further
C/C++ Opage APIs
Add new virtual interfaces for NonTensorType
Implement entry points.
Add shared header for the data container.
Add export symbols.
Add serialization/deserialization.
Implement model with Opaque types.
Rework opqaue_api_test as a standalone executable.
Refactor the SGEMM kernels to resynchronize the code between Windows/Linux and remove unneeded binary bloat from a different zero/add mode kernel. Another goal is to get to a cleaner state for then doing a DGEMM kernel.
Enable Nuphar EP docker build
Revert back to LLVM 6.0.1
Reinstate disabled Softmax tests caused by LLVM 8.0.1
Reinstate Nuphar Python test due to stale sympy version
Increase build timeout of Linux CI
* Implement Nuphar execution provider
Nuphar execution provider is a TVM-based compilation provider. It has shown great speedups for RNN models using Scan.
This PR is mainly for a preview of the shared codegen library for other TVM-based providers.
* Fix submodules
* Fix TVM submodule
* Update Nuphar to latest and resolve confliction
* Remove stale files caused by merge -X theirs
* Revert heap buffer change to not introduce onnxruntime_framework into onnxruntime_perf_test
* Fix bad merge
* Merge from Nuphar
* Fix warning treated as error, revert some unnecessary changes
* Revert some more test changes
* Some more test revert or comments to make review easier
New tests could be added later
* One more revert of unnecessary changes
* More change revert. Test could be added back later.
