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.
* 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.
* Added code for Relugrad with GPU support.
Signed-off-by: Chethan Palangotu Keshava <chethan.palangotu.keshava@intel.com>
* Add GPU support for DNNL ConvGrad
Signed-off-by: George Nash <george.nash@intel.com>
* Add GPU support for DNNL MaxPoolGrad
Updates to MaxPool for training with GPU
Update oneDNN to version 1.8.1
Signed-off-by: George Nash <george.nash@intel.com>
* Fixed issues found durring code review
- error in code comment
- using auto when the direct type would have been better
- removed ternary operators that were returning bool values
Signed-off-by: George Nash <george.nash@intel.com>
Co-authored-by: Chethan Palangotu Keshava <chethan.palangotu.keshava@intel.com>
* Added support to interchange Cast and Transpose operations.
* Added ONNX models for the Transpose-Cast-MatMul fusion testcases.
* Added python code to generate the ONNX models required for testing Transpose+Cast+Matmul fusion to Cast+FusedMatMul.
* Added diagram of the Transpose+MatMul fusion documentation
Cleaning up some naming in the op kernel type control infrastructure.
"Supported types" was a bit semantically overloaded. Renamed it to "default types". They are the types that are supported by default.
Implement an alternate workaround for the LLVM x86 problem described in PR #5088. That change made the x86 assembly files build with the GNU assembler by using -fno-integrated-as
* disable materialize grads
* gradient builder bugfix
* fix ut
* fix ut
* resolve comments and bugfix
* add more assert
* disable forward compare for now
* priority-based exec order
* disable 1 failing test
* fix UT
* more comments
Co-authored-by: Ethan Tao <ettao@OrtTrainingDev4.af05slrtruoetgaxwwjv5nsq5e.px.internal.cloudapp.net>
Implemented following change to avoid the error when using both --use_external_data_form and --precision int8 with GPT2LMHeadModel, which results in
line 161, in save_external_data; open(external_data_file_path, 'ab').close()
FileNotFoundError: [Errno 2] No such file or directory:
This may also be related to the identified bug #6047.
* add config allow_spinning
* add config allow_spinning
* set true as default
* split configures for inter and intra ops
Co-authored-by: Randy Shuai <rashuai@microsoft.com>
* Change msbuild condition for UAP
* update .netcore target as well
* create nuget packages with _native path
* validate path under _native directory for windowsai package
* pep8
* add diagnostic error message
* pep8
* use baseame
* lib\uap10.0
* uap10
* build\\uap10.0
* Manually binplace winmds into appx when PackageReference is used.
* always binplace winmd regardless of packagereference since c# should work with packages.config also
* resolve all paths to full paths to avoid some reference warnings
* move winmds out of lib folder to prevent automatic component registration
Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
* Add more asserts on forward outputs
* Found one more failing case
Co-authored-by: Sherlock Huang <bahuang@OrtTrainingDev3.af05slrtruoetgaxwwjv5nsq5e.px.internal.cloudapp.net>
