* update dockerfiles/README (#2336)
* Make elementwise op run 4 items per thread (#2335)
Description: Describe your changes.
Make elementwise op run 4 items per thread
unroll for loop to leverage ILP
remove unnessary N==0 check inside elementwise GPU kernel
Motivation and Context
Why is this change required? What problem does it solve?
It can improve the performance of GPU elementwise ops. ~2% performance gain on popular NLP bert model.
If it fixes an open issue, please link to the issue here.
* Add CUDA GatherElements kernel (#2310)
* Updates
* Update test
* Update
* Updates
* nits
* PR feedback
* Update
* Update
* PR feedback
* PR comments
* Update
* Fix build
* Fix build
* Nits
* Fix
* Layer Normalization Fusion (#2319)
basic layer normalization transform
* Add FastGelu Cuda Op for Gelu and Add bias fusion (#2293)
* Add FastGelu cuda op
* Add AddBiasGelu for experiment
* Revert "Add AddBiasGelu for experiment"
This reverts commit 5c1ee019858c657e6bb75887265cb85675626e5b.
* Add bias
* Add unit tests
* update comment
* update script
* fix build error
* update coding style
* update for CR feedback
Enable half2 optimization only when cuda arch >= 7.0
* move _Tanh to common.cuh
* implement CPU contrib OP Attention (#2333)
* Remove unused initializer from GraphProto as well as name_to_initial_tensor_ in CleanUnusedInitializers. (#2320)
* Remove unused initializer from GraphProto as well as name_to_initial_tensor_ in CleanupUnusedInitializers.
This means initializers that have been replaced during graph optimizations are not left in the GraphProto when we save an optimized model.
* Handle edge case where a model has an unused initializer with matching graph input by also removing the graph input.
* Use non-const iterators in std::find_if calls to make centos build happy.
* Nuget pipeline changes (#2305)
1. refactor the pipeline, remove some duplicated code
2. Move Windows_py_GPU_Wheels job to Win-GPU-CUDA10. We'll deprecated the "Win-GPU" pool
3. Delete cpu-nocontribops-esrp-pipeline.yml and cpu-nocontribops-pipeline.yml
4. In Linux nuget jobs, run "make install" before creating the package. So that extra RPAH info will be removed
* Cuda Reverse Sequence Op, maping types of same size using same template function. (#2281)
* Set ElementType to String type of node metadata, instead of byte[] (#2348)
* Set ElementType to String type of node metadata, instead of byte[]
* Fix spacing
* Introduce PrimitiveType into a Type System along with an integer constant (#2307)
Improve perf by avoiding GetType<T>() calls. Introduce MLTypeCallDispatcher to switch on Input Type. Add Tensor IsType<T>() fast method.
* Fix/test dim value of 0 handling in a couple of places (#2337)
* Update the CUDA Where implementation broadcasting logic to handle a dim with value of 0.
Add unit test
Also add unit test for unary op with dim value of 0
* Exclude ngraph from Where test with 0 dim.
* Openvino EP R3.1 onnxrt server (#2357)
* onnxrt server with OVEP
* onnxrt server with OVEP
* Update Dockerfile.server.openvino
* onnxrt server OVEP fix reviews
* onnxrt server OVEP fix reviews
* Implement cuda nonzero op. (#2056)
Implement cuda nonzero op.
* Direct use python numpy array's memory if already contiguous. (#2355)
* Direct use python numpy array's memory if already contiguous. This
could greatly improve performance for session with large input,
like big image 1920x1080 fastrcnn, 30~40% speed up could be achieved.
* Add test case enforce contiguous/non-contiguos numpy array as inputs.
* Add helper to create output to minimize binary size. (#2365)
Add ConstEigenTensorMap typedef so we don't unnecessarily const_cast the const input Tensor.
* fix builds enabling onnxruntime_DEBUG_NODE_INPUTS_OUTPUTS (#2369)
* fix builds enabling onnxruntime_DEBUG_NODE_INPUTS_OUTPUTS
* update
* Add Tracelogging for profiling (#1639)
Enabled only if onnxruntime_ENABLE_INSTRUMENT is ON
* test bidaf with nuphar for avx target (#2370)
increase nuphar test coverage a bit
* Fix a bug in TLS refcount that may destabilized CUDA CI (#2374)
* update output size calculation for resize (#2366)
* change how output size is calculated for resize op
* add tests for ver 10 resize
* Extend OneHot CPU kernel to support more types (#2311)
* Extend OneHot CPU kernel to support input int64_t, depth int32_t, output float
* Skip BERT before the test data fix is picked up
* Fix bug with Slice. Need to pass in flattened input dimensions so the initial offset into the input is calculated correctly. (#2372)
* Add opset 11 version of Split to CUDA ops (#2376)
Organize the CUDA ops definitions so all the opset 10 and 11 parts are together (same setup used for CPU ops)
* Layer Norm Fusion Fix (#2379)
* layer norm fusion fix
* Add input shape check in code and unit tests
* Fuse Add + Gelu (#2360)
Implement the transformer to fuse add + gelu
Implement the accurate kernel
* Skip layer norm transform (#2350)
* skip layer normalization transformer
* Another try to stabilize CUDA CI (#2383)
The root cause seems to be failure in CUDA dealloc when tear down. cudaFree return code was ignored before, so should the debug check.
* fix BUILD.md typo (#2375)
build.py: error: argument --config: invalid choice: 'RelWithDebugInfo' (choose from 'Debug', 'MinSizeRel', 'Release', 'RelWithDebInfo')
* Fixed compilation with ngraph (#2388)
* Fix reuse logic in allocation planner. (#2393)
* Fix reuse logic in allocation planner.
* PR comments
* Add helpful comments
* Don't allow reuse across string tensors.
* [NupharEP] Multiple optimizations (#2380)
Fuse transpose into MatMul
Implement Pow and constant scalar simplification
Vectorize ReduceMean
Improve symbolic shape inference
Minor updates for better debugging in fused function name
* Avoid using the default logger in the graph lib and optimizers (#2361)
1. Use the session logger if it is available.
2. Don't disable warning 4100 globally. We should fix the warnings instead of disabling it.
* Change CUDA implementation of Transpose to support all fixed size tensor types (#2387)
* Change CUDA implementation of Transpose to not use a typed kernel so we can support more types with minimum binary size.
Add support for 8, 16, 32 and 64 bit types.
Add unit tests.
Add method so the implementation can be called directly (will be used by CUDA Scan very soon).
* Disable TensorRT for MLFloat16 and int8 unit tests.
* Address PR comment and add support for calling cublas implementation if type is mlfloat16.
* Add opset 11 versions of the existing CUDA operators that had negative axis support explicitly added. (#2398)
* Add opset 11 versions of the existing CUDA operators that had negative axis support explicitly added.
* [NupharEP] force some low/zero cost ops to be inlined (#2409)
* fix cross compile bug (#2415)
* Minor optimization: if a node has already been placed, there's no need to find a kernel for it. (#2417)
* Add Reshape Fusion (#2395)
* Add reshape fusion
* Add some comments
* update comments
* update comment format
* update according to feedback
* update for recent logger change
* fix build error
* (1) Support both input and output edges in find path in graphutils
(2) Add a test case of only one constant initializer of Concat input.
(3) Refactor ReshapeFusion class to allow add more subgraph fusion in the future.
* fix error
* (1) loose constraint on initializer: non constant is allowed for reshape fusion.
(2) Change versions type to vector.
(3) Add logging.
(4) Return false when multiple output edges matched in FindPath. Add comments.
* only allow one direction (input or output) in FindPath
* [NupharEP] Update notebook and docker image (#2416)
Add BERT squad in Nuphar tutorial
Enhance speed comparsion readability
* Fix the issue in matmul_add_fusion (#2407)
Fix the issue in matmul_add_fusion
If Muatmul + Add has shape [K] * [K, N], reset it to [1, K] * [K, N] will make the output shape to [1, N] will also requires a reshape on the output.
Fix: just remove the shape reset to not fuse it.
Add a negative test case for matmul+add fusion
* feat(treeregressor): Update TreeEnsembleRegressor for type support (#2389)
Updates the `TreeEnsembleRegressor` to allow for `double`, `float`,
`int64`, and `int32` inputs to match the upstream specification.
Signed-off-by: Nick Groszewski <nicholas.groszewski@capitalone.com>
* onnxrt server documentation update (#2396)
* Added support for Pad-2 operator in OpenVINO-EP (#2405)
* Add CUDA If operator. (#2377)
* Add CUDA If operator.
Uses CPU operator for implementation.
By adding a CUDA version the inputs/outputs (with the exception of the 'cond' input) stay on GPU, and no other logic is required to avoid a copy to CPU across the control flow node.
* Improved documentation for onnxruntime::utils::SwapByteOrderCopy(), added precondition check.
* Fix the type constraints on CUDA If operator to exclude strings. (#2431)
* add Im2col<uint8_t> (#2438)
* Adjust codegen vectorization width from target (#2439)
* Adjust codegen vectorization width from target
* Add CUDA Scan operator. (#2403)
* Add Scan CUDA op.
Uses CPU implementation for logic.
Added some device specific functors for handling when data needs to be manipulated on a different device.
Added ability to override the materialization logic in the OrtValue slicer so DML can plugin their handling.
* Fix Windows GPU C API packaging pipeline failure (#2440)
Fix Windows GPU C API packaging pipeline failure (#2440)
* Correctly handle implicit inputs for fused nodes (#2390)
* Correctly handle implicit inputs for fused nodes
Previously, nuphar's partitioning function didn't include
node's implicit inputs into the inputs list of MetaDef, and hence
a crash was triggered in the onnx graph checker.
This commit fixed the issue. Furthermore, it also fixed a related
issue where we didn't add implicit inputs into
graph_inputs_excluding_initializers_ in Graph::SetGraphInputsOutputs.
the issue was that graph_inputs_including_initializers_ populated by
SetInputs (e.g. called by FunctionImpl::FunctionImpl) may contain
implicit inputs which were not of any node's initializers in the graph.
Because they were not part of any initializers, these implicit inputs
couldn't be visited by going through all nodes' inputs.
Consequently, they would *not* be added into graph_inputs_excluding_initializers_.
We fixed the issue by first copying the populated graph_inputs_including_initializers_
into graph_inputs_excluding_initalizers_, which then had both initializers and
non-initializers as its initial content. Later, we erase initializers from the
list. In this way, we can ensure all implicit inputs to remain in
graph_inputs_excluding_initializers_.
* refined comments and fixed duplicates
Address CR by revisiting comments in terms of implicit inputs
Also fixed an issue by skipping duplicates while copying inputs
from graph_inputs_including_initializers_.
* address CR
explain why we need to collect nodes' implicit inputs
* don't rely on pointer values for iterating std::set
Previously, openvino relied on iterating a set of NodeArg pointers
to construct inputs and outputs for a fused graph. It could cause
non-determinism. The reason was that although iterating std::set by
itself is stable, pointer values of NodeArgs may vary. Consequently,
we could end up visiting the set's elements in different orders for
different runs for the same test, which resulted in constructing
inputs (and outputs) with different orders to the fused graph.
For example, for the same test, we may have inputs [A, B] in some
runs but inputs[B, A] in others.
Let's use std::string as the key type to avoid such nondeterminism.
This commit also added implicit inputs into meta->inputs while returning
the capability from the openvino provider.
* Fixed another latent issue in openvino's GetCapability function
The issue was that we couldn't simply erase fused_inputs and fused_outputs
while iterating the nodes. For example, an output NodeArg may have multiple
uses, and it's wrong if we erase it from fused_outputs when we encounter only
one of its uses as input.
* Remove DeviceAllocatorRegistry class (#2451)
Remove DeviceAllocatorRegistry class
* CSharp api and test for loading custom op shared library (#2420)
- Added C-API test for loading custom op shared lib.
- Made some changes in C++ api header and C-api implementation to get it working.
- Added C# API and corresponding test for loading custom op shared library.
* Parallel Gelu with ParallelFor (#2399)
Parallel Gelu to get better performance for Gelu
* Clean up build.py (#2446)
* Pull the latest image before running docker build
* Fuse SkipLayerNorm with Bias (#2453)
Fuse SkipLayerNorm with Bias
* Allow more than one invocation of CreateEnv in the same process. (#2467)
* Allow more than one invocation of CreateEnv in the same process.
* Fix centos build
* Symbolic shape inference improvements: (#2460)
* Symbolic shape inference improvements:
- add a mode to guess unknown ops' output rank
- add support for GatherND
- add support for If
- fix a bug in get_int_values when then tensor rank > 1D, by treating it as no sympy data
- add symbol to literal merge when ONNX silently merges dims
- fix a bug in Concat when input dim is 0
- fix a bug in ConstantOfShape that computed dim is not updated
- add support for dynamic shape in ConstantOfShape
- fix a bug in Loop output shape that loop iterator dim is not inserted at dim 0
- add support for dynamic padding in Pad
- add support for dynamic shape in Reshape
- add support for Resize with opset > 10, by treating output dims as dynamic
- fix a bug in Slice when starts/ends are dynamic
- restrict input model to opset 7 and above
- make output model optional to avoid disk write when testing
Run model tests for symbolic shape inference
Reduce 2GB docker image size of nuphar
* add additional test data set for nuget pipeline (#2448)
* add SAS token to download internal test data for nuget pipeline
* update azure endpoint
* fix keyvault download step
* fix variable declaration for secret group
* fix indentation
* fix yaml syntax for variables
* fix setting secrets for script
* fix env synctax
* Fix macos pipeline
* attempt to add secrets to windows download data
* fix mac and win data download
* fix windows data download
* update test data set url and location
1. Add openvino GPU nightly build pipeline, this test is running on Intel Up square Edge device. The device are host locally not from Azure VM. We persist a smaller model test data on Edge device.
2. Update the build condition for openvino GPU so it works for GPU_FP32, GPU_FP16
3. add option to install_ubuntu.sh to exclude the package used for nuphar, so that we can save some disk space as the Edge device usually have limited disk space.
* Update cuda for python wheels
* Update cuda for python wheels
* Update cuda for python wheels
* Update azure-pipelines-py-packaging.yml
* Update to cuda 10
* Only test win gpu
* Update cuda for python wheels
* Use manylinux2010 image to build linux python wheels
Allow wheels built to truly be compliant with a manylinux policy
* Initial commit for OpenVINO Execution Provider
OpenVINO Execution Provider provides the interface for ONNX Runtime
applications to access Intel's hardware accelerators using Intel's
OpenVINO Toolkit.
* Fixed bug in GetCapability to disable custom ops
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Added OPENVINO ci pipeline
Added new pipeline for openvino provider,
made changes to support the docker build and
onnxruntime build with openvino.
Signed-off-by: Luis Daniel Castellanos <luis.daniel.castellanos@intel.com>
* Enabled all unit tests for OpenVINO EP
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Fixed syntax issue in run_docker_build.sh file
* Added missing default OPENVINO_VERSION
Default value for OPENVINO_VERSION env was
missing causing the build to fail
* Added install Model Optimizer deps step
* Fixed python unit tests and some tests from onnx_backend_test_series
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Fixed indentation bug
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Disabled some of the python backend tests for OpenVINO
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Disabled some model tests
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Remove Duplicate checks for openvino in build.py
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Modified GetCapability for FP16
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Disabled GPU FP32 tests that are not supported
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Convert modelProto to string and use it in compile
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Pass byte-array input args to MO
* Serialized ModelProto passed in-memory to MO
ModelOptimizer python module receives the serialized ModelProto
in-memory.
Uses appropriate ONNX function to load the serialized bytes.
* Make Py_Finalize compatible with older python versions
Also, remove pFunc unassigned variable possibility.
* Fallback if input dims of Matmul is greater than 2
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* fixup: Device #define syntax
* Updated the documentation
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Enable dynamic dim value
* removed commented out code
* Added Dockerfile for openvino EP
Updated instructions on dockerfiles/README.md file
Signed-off-by: Luis Daniel Castellanos <luis.daniel.castellanos@intel.com>
* Disabled fp16_inception_v1 test
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Code formatting with clang-format
Uses style from the .clang-format file in root directory.
* fixup: docker tag and build error fixes
* Heuristics to automatically detect batching
Distributes slices from batch into parallel infer-request objects.
* Handle disabled tests in GetCapability
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Disabled average pool and max pool if ceil_mode is 1
Also dilations are not supported if they are greater than 1
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Disabled Unsqueeze int32 test
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* changes to fix output results bug
* Disabled a few C++ unit tests for MYRIAD FP16
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Manually revert '9fe162bb Enable dynamic dim value'
Reverts compile time setting of dynamic shape
Reverting manually due to significantly huge auto-revert conflicts.
* Fixed unused variable warning
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Disabled Mul test for GPU_FP16 due to accuracy issue
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* VPU documentation update
* Disabled inception_v1 for MYRIAD and HDDL
*Also disabled few C++ accuracy tests for HDDL
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* updates from upstream
* use the new CustomOpApis for I/O interfacing
* Pass initializers as subgraph meta-def inputs in GetCapability()
Requirement due to API changes introduced with PR# 1019.
* Remove obsolete functions
* Save indexes of graph inputs from fused_node info
Both inputs and initializers are passed as data inputs to the
infer function. To identify only inputs among them, save thier
index info from fused_node in Compile function.
* Documentation changes to enable VPU
* Fix VPU related changes in documentation
* Fix minor changes in documentation
* Fix VPU related changes in documentation
* Use Node.In/OutputDefs() to track graph inputs and outputs.
Don't use graph_viewer's GetInputs() or
GetInputsIncludingInitializers().
* Permit "SAME_UPPER" auto_pad attribute from MaxPool
* Disabled fp16_tiny_yolov2 in onnx model tests
* Updated documentation to include configuration guides for myriad and hddl
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Use 8 Infer requests only for VAD-R
* disable debug prints
* Clang-format source files
* Updated BUILD.md with OpenVINO R5 links
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Disabled same upper python tests
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Update test exclusion syntax
* Change path of install_onnx.sh
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Disable tiny_yolov2 in broken tests
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Revert "Change path of install_onnx.sh"
This reverts commit ba9db165f3be430f2aff1ef413299ed04637196a.
This change is only required for Intel internal CI pipeline until
the settings are matched with the upstream's CI pipeline.
* Added debug statements for debugging CI error
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Add --build_wheel to linux openvino pipeline
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Added -v option to onnx_test_runner for debugging
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Removed path change patch
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Added -c 1 to onnx_test_runner
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Refactor MO python invocation in separate function
Cleans up Model Optimizer python invocation check and conversion
logic. Invokes MO only once in GetCapability() and passes the
IR strings (xml and bin) to the Compiler as meta-def attributes.
* Add comments
* code cleanup and comments
* Code cleanup for GetCapability
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Removed unnecessary files
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Revert "Added -v option to onnx_test_runner for debugging"
This reverts commit d1dd70938a94d648df1a1dbbc2e48d0b97e49ec8.
* Revert "Added debug statements for debugging CI error"
This reverts commit b86d41afed2aa29c3508155d6f9c8d3a7263cc60.
* incorporate Status Code changes
* ComputeFunc returns Status::OK() on success
* Use test names to disable tests for MYRIAD and VAD-R
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Rename local identifiers from CNNNetwork to OpenVINO network
CNNNetwork is an OpenVINO's API class that represents more than
just convolutional neural networks (CNNs). Renaming helps to avoid
confusion that the API's only support CNN type models.
* Added error message if building on windows
* Removed duplicate option in Cmake
* Removed unnecessary parameters in activation_opt_test
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Refactor Map search and access logic for efficiently and cleanliness.
* use C++ style casts
* Use os.path.join for python directory path operations
* use C++ style casts
* EP classes should use onnxruntime namespace
* Clean up fixes from PR comments
* Don't explicitly shutdown Py interpreter
* Remove debug print statements
Prints will be re-enabled later with a logging mechanism with
debug/verbose printing options.
* Decrement ref counts for used pyObjects
* Restore build instructions for other compilers
Content under the "Using other compilers" section has been
accidentally deleted by a previous commit. Restoring back that
content from the latest upstream repo.
* CMake code cleanup
Code clean up, commenting and formatting of CMake code.
* Don't pass the unused device_info parameter to OpenVINOGraph ctor.
* Add support for multiple I/O data types
Adds support for the following tensor data types for graph inputs
and outputs:
1) float
2) float16
3) int32
4) int16
5) int8
6) uint16
7) uint8
* cleanup setup.py module list definition
* Deduce index of input using tracked input index map
Ignores initializers in case they are ordered before inputs.
* Removed debug statement in MO code
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* PR feedback
* Removed per_sample_tolerance for openvino
* Removed unnecessary disabled tests
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Removed debug function
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Disabled tiny_yolo_v2 due to accuracy issues
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Changed the disabled reason for broken tests
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Disabled Reshape with no input
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Python formatting with Autopep8
* Minor fix for MYRIAD devices
* Added zero dimension check
*Removed setting batch size for the network
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Set the threshold to larger value for MNIST
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Removed setting higher threshold in provider_test_utils
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Check for --use_openvino in python wheel setup.py
Add openvino modules to the setup script for building the wheel
package only for --use_openvino a build option.
* Removed nullptr checks for GetNode()
Signed-off-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* Refactor C# to handle x86
* update run script
* Add Native win x86 tests
* Add native x86 tests for Linux
* Update linux tests scripts to control which tests are run
* update linux image name for x86 to prevent using cached image
* update to not run unit python unit tests unless pybind is specified
* remove --build_wheel as a core common arg. Python cannot run on x86 build
* update OrtGetNumOfDimensions to OrtGetDimensionsCount in rest of C#
* enable android build
* Add 'log' to onnxruntime_EXTERNAL_LIBRARIES
* Remove cmake about header_files_test.cc
* Add Android CI pipeline
* Remove some ms-specific(?) ci
* Fix bash error
* Add execute flag for install_deps_android.sh
* Add install_ubuntu_for_android.sh
* Remove python in deps for android
* Add comment for BUILD_ARCH
* Set BUILD_SERVICE to cpu
* Set BUILD_OS in run_build.sh
* Fix -o bug in run_build.sh
* Android -> android
* Correct the android ndk location
* Checkout submodules in my own azure pipelines
* Revert "Remove some ms-specific(?) ci"
This reverts commit 302463213480487d8944c3127a3b311c591d55c0.
* Revert "Checkout submodules in my own azure pipelines"
This reverts commit 1acfb6755f933e532b8312ca35bb4900a833903f.
* updated cmake files for trt
* added trt execution provider
* added trt basic test
* removed trt_path action attribute
* Add files via upload
* Update build.py
* Update trt_allocator.h
* fixed issues found by reviewers
* changed cast operator
* added comment for custom kernel implementation
* changed auto to auto&
* changed to function compile APIs for TRT execution provider
* changed to function compile APIs for TRT execution provider
* added new DType DInt64
* adapted to the changes of onnxruntime_c_api
* removed trt kernel (use function compile instead)
* updated onnx-tensorrt submodule
* set default memory type to TRT fused kernel
* resolve merge conflict
* fixed the issue that USE_CUDA conflicts with USE_TRT
* construct graph by adding nodes in topological order
* made changes for Windows
* change buffers type
* bypass HasImplementationOf check for TRT XP because TRT kernel is not registered
* added domain to version info in rebuilt model proto
* added trt to test option list
* added DomainToVersionMap() to GraphViewer
* removed Copy()
* fixed broken code
* format the code to clang format
* used local reference to the frequently used values
* fixed a couple of issues according to reviewers feedback
* fixed a couple of issues according to reviewers feedback
* added python binding for TRT and enable use_cuda when use_trt is on
* fixed a redefinition issue
* changed shared_ptr to unique_ptr on trt engines, and made a few changes required by reviewers
* enabled trtexecution provider for unit tests
* renamed trt to tensorrt
* added tesorrt to python binding
* update submodule onnx and onnx-tensorrt
* made a couple of minor changes based on reviewer's feedback
* added CUDA_CHECK
* removed test code
* fixed broken code after merge
* updated onnx-tensorrt submodule
* added post processing to align trt inputs/outputs with graph inputs/outputs
* updated onnx submodule
* added CUDA fallback for TensorRT and fixed TensorRT cmake issue
* added ci pipeline for tensorrt and removed some redundent code from trt xp
* fixed syntax issue
* updated onnx-tensorrt submodule
* fix trt build problem by: (#602)
1. Add additional /wd for debug build
2. Add io.h for additional targets
3. Bring back mb version of getopt
* Update install_ubuntu.sh
* Update linux-gpu-tensorrt-ci-pipeline.yml
* Update linux-gpu-tensorrt-ci-pipeline.yml
* Update run_build.sh
* Update run_build.sh
* Update run_build.sh
* Update run_build.sh
* fixed the issue that GetKernelRegistry returns nullptr
* merged master to this branch
* moved some data types to private
* fixed tensorrt CI pipeline issue
* customized test data for TensorRT pipeline
* added onnx-tensorrt in json file and fixed an issue in ci script
* added comments
* cross compile x86 linux
* fix comments
* install multilib for ubuntu cross compile
* remove tailing slash
* fix -fPIC relocations for x86 target too
* add asm make flag
* fix x86 compile err
* test x86 with zlib and png
* Disable zlib from x86
* install x86 python header
* remove cross-compiling changes
* test 32bit ubuntu
* add x86 ubuntu docker file
* add x86 as arch parametr for docker build
* config pipeline
* avoid dotnet install
* install cmake
* skip dep install
* use latest ubuntu
* install latest cmake
* install x86 deps
* configure cmake
* install ninja
* correct ninja dir
* apt get re2c
* install onnx
* set processor x86
* disable warning
* skip test
* disable test
* disable test
* find lib
* fix typo
* restore test
* disable backend model test
* disable test
* fix test err
* stop installing onnx
* disable onnx test on x86
* restore yml
* mergef with master yml
* cancel needless config setting
* enable x86 flag
* restore all onnx tests
* fix yml typo
* install onnx
* add back x86 flag
* disable cases
* disable case
* disable cases
* add macro to disable cases
* fix typo
* print platform
* remove condition
* Upgrade gpu build to CUDA 10 + cudnn 7.3
* update the yaml file for python package building
* switch to the cuda9.1 docker file if the CUDA_VER is cuda9.1-cudnn7.1
