GitLab

* changed split_single_dyn_dim to add a get_tuple_element instruction
needed to access tuple type created by select_module
* dyn_test_runner changed to have offload_copy to false
* split_single_dyn_dim is not going to work with offload_copy unless we
make `load`, `copy_to_gpu` and `copy_from_gpu` handle dynamic shapes

Enable python 3.10 bindings

Avoids double global loads.  Strided loops are unrolled which lets store results in array which compiler will use registers for since the index access is constant.   Updated to handle large reductions so which results with a better stable diffusion result

* deprecate HCC

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

Add dynamic shape support to slice operator.

First draft of this feature doesn't support ops slicing non-fixed, dynamic axes. Resulting shape in such cases is not guaranteed.* Also, onnx parsing doesn't support any arguments other than "axes".

removed the new rank<1> function as it messed up batch_quant_dot_5
verify test

Use requirements-dev.txt instead of the other instances

* Changed the allocates to occur in the submodules
  * Incomplete, as the use_local_alloc variable in module does not work
  properly
* added a hip::sync_stream before the return
* not sure why the hip::sync_stream gets rid of the dangling reference
error (code-wise it's because hip::sync_stream's output alias is -1)

Currently, we default to device 0 when loading programs. Updating this to use hipGetDevice to set the device for the loaded program.

Expands on the documentation and corrects default option documentation error.

* Add serialization of tuples and optional types

Using add_instruction for the neg op was causing issues on replace_instruction. Changed to use insert_instruction.  Tests and added a new one that is failing without the change.

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

dyn shape support for Where operator.  Includes shape test, ref_ops test, onx_test. 

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

* Fuse layernorm with different patterns
* Only match when using the last axis
Co-authored-by: kahmed10 <15948690+kahmed10@users.noreply.github.com>
Co-authored-by: kahmed10 <15948690+kahmed10@users.noreply.github.com>

Switch default ROCm version to 5.4.2 and default calculation algorithm to defined threshold

Refactors memory coloring to only handle allocation instructions. It also handles allocations for tuple shapes.