Implement various improvements related to reordering a tensor for use by NCHWc operations:
Relax the requirement that the input channel count must be a multiple of the NCHWc block size (either 8 or 16 depending on ISA). The requirement now is that the channel count must be a multiple of 4. The implementation of MlasReorderInputNchw would need further work to support relaxing this further, but I don't have any models where I've observed this to be necessary yet.
Support fusing a Transpose(NHWC->NCHW) into a following ReorderInput. ReorderInput now has a channels_last attribute as was done in the past for ReorderOutput. This helps with models converted from TF where the converter is unable to remove all Transpose operations.
Add threading support to ReorderInput to accelerate performance (ReorderOutput will come later).
* wait for dispatch done in RunParallelSection
* pass worker_fn by value
* cancel move
* only move work_fn when it is lastly referred
Co-authored-by: Randy Shuai <rashuai@microsoft.com>
* Implement qlinear concat and unit test.
Add quantization tools for QLinearConcat and it quantization tests.
* Add kernel def hash for QLinearConcat.
* Change according to PR. Add qdq transformer support for QLinearConcat.
* Add QDQ Transformer unittest. Fix typo on domain.
* remove dup logic of no use.
* fix x86 build error.
* Update operator docs.
* Pass cuda stream to thrust function to not use default stream.
In the commit 299ace0, ORT has been changed to not use cuda default stream.
* update amd_hipify.py
* remove un-necessary stream sync
Co-authored-by: Weixing Zhang <wezhan@microsoft.com>
* add async dispatch
* minor renamings
* build py38
* restore yml
* fix sync up issue between dispatch thread and main
* fix comments
* refactor SummonWorker and rename to RunInParallelInternal
Currently in high dimension matmul, we call multiple GEMM sequentially. In this change we execute these GEMMs in parallel, removing barriers between two adjacent GEMM operations.
Performance tested with Bert and T5 model. Bert model shows no noticeable perf differences, as the heavy lifting is done by the attention operator, which is not changed in this PR. In T5 model, we see no regression on low parallel threads (x4), and performance improvement is more pronounced in high number of threads (8-16). T5 shows 10% speedup with 16 threads. With profiling, we can see the most expensive MatMul operators in T5 achieves around 20% speedup with 16 threads.
Co-authored-by: Chen Fu <fuchen@microsoft.com>
* first attempt rocm training wheel
* modifications needed to python packaging pipeline for Rocm 4.1
* changges to not conflict with cuda
missed stage1 changes
remove package push
add option r to getopt
try again without python install
try again without python install
try again without python install
split pipelines and add back push to remote storage
try on cuda gpu pool
try again
try again
try running without az subscription set
try again on original pipeline
change pool
passing AMD Rocm whl on AMD-GPU pool
split rocm pipeline from cuda pipeline
remove comments
* try adding Rocm tests as well
* try with tests in place
* fix trailing ws
* add training data
* try again as root for tests
* use python3
* typo
* try to map video, render group into container
* try again
* try again
* try to avoid yum error code
* make UID 1001
* try without yum downgrade
* define rocm_version=None
* remove CUDA related comments for Rocm Dockerfile
* Dont pin nightly torch torchvision torchtext versions as they expire (for now nightly is required for Rocm 4.1)
* missed requirements-rocm.txt from last commit
* fix whitespace
* Made the python script generating the testcases modular.
* Modified RemoveBackToBackCasts function to remove cast even if the parent node has other consumers.
* Modified InsertCastNodes to update the graph consistently for other functions to work.
* Moved ConcatNames function to the top.
* PropagateBackward/SearchUpstream and PropagateFP16CastsFromOutputsToInputs insert FP32 casts if the level >1 in order to propagate FP16 casts backwards.
* Added new testcases for level two setting.
* initial dynamic load example
* support load EP in the provider options
* support dynamic load EP in orttrainer
* split the provider interface; fix comments in pr
* remove experiment code
* add test
* remove useless file
* add test model file;fix linux brewak
* fix linux build and missing file
* fix python build
* fix python build
* fix python binding
* fix python test
* fix runtime path for posix env
* exclude the shared library from minimal build
* fix comments in pr;
* seperate the provider shared lib loading
* excluded from minimal / macos / ios build
* skip copy the provider shared lib for minimal build and mac os
* fix macos build
* exclude the test for macos build
* exclude from andorid build
* exclude from web assembly build
* enable the invalid ep test
Co-authored-by: Cheng Tang <chenta@microsoft.com>
* beam search refactoring checkin
* add factory class and deduplicate code
* one step beam search works on gpu
Co-authored-by: Xiaoyu Liu <xiaoyu@xiaoyu-VM.z4vh1dzj5eoevgybsksdpz2izh.jx.internal.cloudapp.net>
* Add gradient registration and tests for Min/Max
* Add helper function for min/max grad test
* limit Min/Max Grad to accept at most two inputs; modify test case accordingly
* resolve merge error
* Fixes needed to PropagateCast transformation.
* Added number of passes to the logs.
* Added logging support to OrtModuleGraphBuilder.
* Added new testcases.
* Added NodeArgToConsumerMap
