* special case concat and split when sizes are equal
* add tests for 16 and 32 inputs with same dim
* add tests for 16/64 inputs on concat or 16/64 outputs on split
* try eliminate windows warning
* outter => outer
* test running hf bert-large
* try again
* try again
* include other models
* correct names
* disable deberta-v2-xxlarge
* avoid torch.distributed
* add compare json loss and perf for bert-large to test
* fix sed expression
* remove pytest
* add more models
* move unit tests u
* display samples/sec
* support register external ep lib inforation; make eager mode share the same ep pools with training workloads
* fix inference code
* fix build break
* fix the message
The following ops have been added to the DNNL execution provider
Abs, Elu, Exp, Log, *Relu, Round, Sigmoid, Softplus, Sqrt, and Tanh
*Relu op was moved from its individual file to the elementwise operators
The error tolerance for the LogGrad unit test had to be decreased slightly
when using OneDNN. Still investigating why a differet tolerance value is
needed.
DnnlSubgraph::AddKernels() member function was moved to the top of the file
since this is eddited every time a new operator is added to the the execution
provider this places the code at the top which mean less scrooling when
adding new kernels.
Signed-off-by: George Nash <george.nash@intel.com>
* Expose symbols in onnx and protobuf namespaces in python when building with --enable_external_custom_op_schemas
* Add external onnx and protobuf files to wheel
* Added an example to demonstrate external custom ops use-case
* Added a Linux build pipeline to test external custom ops
* seperate the training python module; share the execution proivder instance
* fix build break
* fix cuda test crash; reorg the python module code base
* se correct env
* use provider customized hash func
* fixbuild break
* fix rocm break
* use const ref in argument
* rename the file
* move hash func to trainiing module
* Ported changes / bug fixes from torch/ort.
* Fixed formatting
* Renamed function
* Renamed module_ to module.
* Revert "Renamed module_ to module."
This reverts commit b17fc114b3db20d174283811d90592b5b8154c19.
* Include pybind common header to fix linker errors on windows debug.
* Fix to generation of > 1 custom op.
Co-authored-by: Ashwin Hari <ashari@microsoft.com>
* Implement Gemm op for DNNL execution provider
Signed-off-by: George Nash <george.nash@intel.com>
* Remove KernelRegistry and Gemm op for dnnl ep
The KernelRegistry for the dnnl execution provider only
registered a Gemm op that as best we can tell was never
actually used and also was not using the dnnl library.
We have implemented a Gemm op in the DNNL execution provider
subgraph code and thus are removing the unused Gemm op that
was in the dnnl KernelRegistry.
Signed-off-by: George Nash <george.nash@intel.com>
* Fix duplicated output and kernelshape inference
fix getcapability to make sure subgraph outputs do not have duplicates
fix kernelshape inference in pool
Signed-off-by: Wang <zhaoyang.wang@intel.com>
* Removed most dnnl specialized ifdefs from gradient_ops_test code
Re-enable GlobalAveragePoolGrad test for dnnl ep
The bugs that were exposed by the GlobalAveragePoolGrad test have
been fixed and this test no longer needs to be disabled for DNNL.
Removed the ReluGradDnnl test. We are getting the testing from the
already existing ReluGrad test.
MaxPoolGrad test no longer has specialized execution provider
enabling for DNNL execution provider. It will now run without
the extra enabling.
ConvGrad is the only test that still has dnnl specialized ifdefs
However, the ConvGrad code was not being executed by the code
unless it was listed first in the list of execution providers.
Signed-off-by: George Nash <george.nash@intel.com>
* Fix transpose issue on Gemm
On transposing square matrices, getmemoryandreshape will fail to reshape
fix by adding a bool
Signed-off-by: Wang <zhaoyang.wang@intel.com>
* Save memory space by reusing internal tensor for output
The intermediat matmul output tensor can be used as the output
tensor for the binary calculation.
Remove the unused IsAttributeSupported from the
DnnlGemmNodeCapability class since we now support all of the
Gemm attributes in our implementation.
Signed-off-by: George Nash <george.nash@intel.com>
Co-authored-by: Wang <zhaoyang.wang@intel.com>
* adding support for tracing to sqldb instead of files
* use compiled statements
* script to pull tensors from db
* link sqlite3
* remove node info redundant with onnx graph
* addressing PR comments
* address PR comments and include program counter
* third party notice
* use find_pacakge
* add to cgmanifests.json
* address thread safety and add pid suffix
* build fi
* python script to select on devicetype
* remove unpopulated and redundant Shape and Type fields
* comment
* comment
* PR comments
* add graph execution counter to session state
* move increment to inference session
* std::endl to \n
* ifdef on graph execution counter
* add ifdef to inference session
* move DEBUG_NODE_INPUTS_OUTPUTS to CMakeLists.txt
* Fetching frontier tensors to frontend
* Move before session initialize call
* Fetch tensor and add to cache
* Rest of the changes for using cache
* Review comments
* Review changes
* Review comments
* switch to shared_ptr
* Fix bug after rebase
* FE docstring change
* dnnl ep rework
rework DnnlTensor,DnnlNode,DnnlSubgraph to support arbitrary graph topology and tensor data types
rework GetCapability to claim nodes in graph greedily from node topological ordering and delay creation of DnnlSubgraph until Compile
rework compile to have DnnlSubgraphPrimitive as the object to handle primitive creation and execution
instead of thread local primitive pool which duplicates intermediate memory allocated by the EP across threads
DnnlSubgraphPrimitive provides helpers to handle many common functions for each dnnl primitive builder and become the centralized place to store input, output, intermediate memories, initializer memories and etc
it provides functions to obtain input memories with automatic reordering/reshaping and moving between engines
it provides interfaces to add primitive, set output memory for single node and etc
add CONCURRENT_EXEC compile flag for dnnl library as without it, convolution primitive cannot be created and executed on different threads
enable unit tests to run on dnnl ep as well if built with dnnl ep
add dnnl ep support for Matmulinteger
* Add Relu to the DNNL refactor
Signed-off-by: George Nash <george.nash@intel.com>
* Add Convolution op to the DNNL rework
Signed-off-by: George Nash <george.nash@intel.com>
* Add Pooling ops to the DNNL rework
This adds the following ops:
- AveragePool
- GlobalAveragePool
- GlobalMaxPool
- MaxPool
Note: Pooling with dilation is not yet supported.
Note: GlobalLpPool, LpPool, MaxRoiPool, and MaxUnpool are not supported yet.
Signed-off-by: George Nash <george.nash@intel.com>
* Add Sum op to the DNNL rework
Signed-off-by: George Nash <george.nash@intel.com>
* Add ConvGrad op to the DNNL rework
Signed-off-by: George Nash <george.nash@intel.com>
* Add MaxPoolGrad and AveragePoolGrad ops to DNNL rework
Signed-off-by: George Nash <george.nash@intel.com>
* Added lrn operator to the refactored code
Signed-off by chethan.palangoutu.keshava@intel.com
* Added ReduceMean DNNL op to the refactor code
Signed-off-by: Chethan Palangotu Keshava <chethan.palangotu.keshava@intel.com>
* Added Softmax DNNL op for the refactored code
Signed-off-by: Chethan Palangotu Keshava <chethan.palangotu.keshava@intel.com>
* Added BatchNorm DNNL op inference-only for refactored code
Signed-off-by: Chethan Palangotu Keshava <chethan.palangotu.keshava@intel.com>
* Added Binary Ops to DNNL rework
Signed-off-by: Wang <zhaoyang.wang@intel.com>
* Added ReluGrad to DNNL Rework
Signed-off-by: Wang <zhaoyang.wang@intel.com>
* Update OneDNN tag to v2.3
Signed-off-by: Wang <zhaoyang.wang@intel.com>
* Added support for memory upto dim size 12
this is to fix the CI test cases that contain binary ops of input dim
size > 5
Signed-off-by: Wang <zhaoyang.wang@intel.com>
* Prevent claiming support for float16 and bfloat16 when only float is suppoted
By using The string.find used was causing the code to claiming support
for float16 and bfloat16 when we only supported float. We now explicitly
check the code for the data type or the data type with a 7 letter prefix
basically prefixed with "tensor("
Signed-off-by: George Nash <george.nash@intel.com>
* Disable uint8 mul and div, improve type conversion
Disable mul_uint8 and div_uint8 test cases as they use modulo for
overflow handling while onednn uses saturation
improve ype conversion using enum instead of string comparsion as well
as adding more types
Signed-off-by: Wang <zhaoyang.wang@intel.com>
Co-authored-by: Wang <zhaoyang.wang@intel.com>
Co-authored-by: Chethan Palangotu Keshava <chethan.palangotu.keshava@intel.com>
* changes
* tile grad unsqueeze fix for opset 13
* clean up
* remove bool support for opset 2 to 12 for Pad as it is not supported.
* Copy OperatorKernels.md from artifacts of Windows CI build.
* integrate eager mode source codde; build with cmake and integrate the python test
* Adding the python path for importing libraries in the Eager mode
* fix clang break;check if training and python enabled
* handling the linking of torch libraries across multiple platforms
* merge and fix the naming
* add build instruction
Co-authored-by: Abhishek Jindal <abjindal@OrtTrainingDev0.af05slrtruoetgaxwwjv5nsq5e.px.internal.cloudapp.net>
Co-authored-by: ajindal1 <abjindal@microsoft.com>
* updates for picking pnnx commit
* add tests filter to c# tests
* plus test fixes
* fix versioning for contrib ops
* fix tests
* test filter for optional ops
* more versioning related updates
* fix test
* fix layernorm spec
* more updates
* update docs
* add more test filters
* more filters
* update binary size threshold
* update docs
* plus more fixes
* updates per review
* update to release commit
* add filters for optional type tests
* plus updates
1. Update SDLNativeRules from v2 to v3. The new one allows us setting excluded paths.
2. Update TSAUpload from v1 to v2. And add a config file ".gdn/.gdntsa" for it.
3. Fix some parentheses warnings
4. Update cmake to the latest.
5. Remove "--x86" build option from pipeline yaml files. Now we can auto-detect cpu architecture from python. So we don't need to ask user to specify it.
* correct batchnorm replacement output order;
remove bn replacement in grad graph builder
* update op defs and kernel class
* implement batch norm internal and grad.
* change saved_var into saved_inv_std
* cuda test case: bn internal
* remove redundant include
* fix comment; add support and UT for 1d input.
* exclude batch_norm_internal in amd_hipify
* run BNInternal UT for CUDA only
* fix CI error
* fix comment errors
* fix error
* add comment for inconsistency with cudnnBN doc
* additional comments for cudnnBN inconsistency
Adds a StridedCopy function that implements a copy from strided tensor to another.
This parallelizes the Concat operator, and can also be used in the future to parallelize many other data movement operators (e.g. Transpose, Split, etc.).
This operation is also required for the proposed data layout extensions to ORT.
* freeze/fastpath support
* more comments on _fast_path
* per comments
* minor fix
* IntFlag improve
* address comments
Co-authored-by: Ethan Tao <ettao@OrtTrainingDev4.af05slrtruoetgaxwwjv5nsq5e.px.internal.cloudapp.net>
