GitLab

Fixes #1595

Enable python 3.10 bindings

* deprecate HCC

* Add driver flag "--exhaustive-tune" to enable tuning, add support for the same in C/C++ and python API

Use requirements-dev.txt instead of the other instances

* add dynamic shape support to concat operator.  Includes new op_shape_test and ref_ops_test cases

Change download location for onnx model from AWS ONNX to download.onnxruntime.ai

[Experimental] Update accuracy checker for tf support and map input dims (custom input shape) (#1514)

* update file reading function to fix external data loading

* Update MIGraphx Docker to point to latest working onnxrt branch.
* Add output for ONNXRUNTIME_COMMIT in CI and add env var in brackets

Change to python ONNX package 1.10.0 to handle new ONNX test generation.

Allows for a model to be converted to the same opset but turn on infer_shapes through
onnx. This allows us to get an idea of what should be valid for the output of nodes
in a network.

Usecase:

python3 tools/convert_onnx_version.py --model <model_name> --opset=<same_as_model> --infer_shapes --output <new_model_name>

Refactor dynamic compute
- add a compute_output_shape object that implicitly converts to a new dyn_output or shape object
- dyn_output object can handle computing the static output shape of an operator given the input arguments shapes
  change an operator's compute function to argument compute(const dyn_output& dyn_out, std::vector<argument> args) to 
  use dyn_output object

Dynamic ref unary functions
-  Included these changes to have an example of the refactored dynamic compute being used
-  Changes to unary base class to handle dynamic shapes
-  Changed elu and leaky_relu to use unary base class and pointwise JIT

Stream sync changes and associated API level changes

Adds two methods for the custom_ops virtual class.

bool runs_on_offload_target(), if the custom op runs directly on the gpu then it should be set to true. in this case, custom op expects its parameters to reside in GPU memory and writes output to the GPU memory. If it is set to false then, custom op expects it's parameter to reside on the host and puts back the result into the host memory.

output_alias, if output of the custom op is aliasing the input buffer. i.e. interpreting the same input buffer with differnet shape and strides.

Update as_vector() in C++ API to handle non-standard shapes. It required exposing element_index to space_index conversion method for the shape class.

Using not and or improves readability. The cppcheck rule will help ensure we are doing it consistently.