1. Add support for vstest.
2. Add support for vcpkg. To use it:
```bat
vcpkg install zlib:x64-windows benchmark:x64-windows gtest:x64-windows protobuf:x64-windows pybind11:x64-windows re2:x64-windows
mkdir build
cmake ..\cmake -DCMAKE_BUILD_TYPE=Debug -A x64 -T host=x64 -DCMAKE_TOOLCHAIN_FILE=C:\vcpkg\scripts\buildsystems\vcpkg.cmake -DVCPKG_TARGET_TRIPLET=x64-windows -Donnxruntime_PREFER_SYSTEM_LIB=ON
```
3. New cmake option: onnxruntime_PREFER_SYSTEM_LIB, which allows user using the preinstall libs instead of the things in onnxruntime submodule.
4. New cmake option: onnxruntime_ENABLE_MEMLEAK_CHECKER, which allows user turn on/off the memory leak checker by @RyanUnderhill in Windows Debug Build. The checker doesn't work with vstest.
4. Fix the post merge pipeline(Mainly for test coverage report).
5. Ignore the compile warning from the Featurizer library code
6. Apply "/utf-8" VC compile flag to our code. Without this, you can't build onnxruntime on Chinese Windows.
7. Remove the SingleUnitTestProject cmake option because it's deprecated more than one year and nobody is using it.
8. Move opaque api tests to onnxruntime_test_all
9. Enable "/W4" on CUDA ep's C++ code(Not the *.cu files), and fix some warnings, add some extra checks.
10. Delete the onnxruntime::test::TestEnvironment class.
11. Add a DLLmain for onnxruntime.dll.
12. Allow dynamic link to libprotobuf
- Linking onnxruntime with JNI_LIBRARIES includes some unnecessary links to native libraries (e.g. libawt) which are not actually used or required by the output onnx library. This causes unsatisfied link exceptions when trying to load the onnx library without including these libraries.
* Documentation for API Breaking Changes
* Add version 2 of the API, plus update documentation
* Add a static assert to ensure version 1 of API we shipped does not change in size.
1. Enable warning "4503" # Decorated name length exceeded.
2. Enable warning "4146" # unary minus operator applied to unsigned type.
3. Enable float64 support for the Softmax operator
4. Enable compliance checks for Windows x86 32bits build
5. Use TryBatchParallelFor to replace some fallback code in mlas pooling.cc
6. Fix Android CI pipeline.
Clear error when throwing an exception for a failed CUDA call so that there is only one error mechanism being used at a time.
Minor improvements to logging to aid debugging of BFCArena behaviour.
Also update onnxruntime_perf_test to catch the exception from the call to Run and return a Status. Otherwise it exits with an 'unknown exception' error.
* Implement Bitonic and Radix TopK
* remove needless print out
* fix com err
* add negative support
* fix comments
Co-authored-by: Randy <45701928+RandyShuai@users.noreply.github.com>
* add calibration tool
* add model for e2e example
* format readme
* some more formatting updates
* plus a few more updates
* plus review comments
* plus updates
* more updates
Disable DML in Windows GPU CI build for now, because there are some wired model test failure and I don't know how to fix it. Will seek help from WinML team.
* Add bert related transformers to doc
* Add execution provider and comment for bert optimizations
* Add comment about accuracy impact of approximation
* use correct type for for loop
* explicitly specify void for parameters of OrtGetApiBase because the function is defined in c, so when the function is just (), it is interpreted as having an unknown number of parameters. This was causing compiler warning C4276.
