Optimize multiply across slices (ROCm#568)

* Add initial optimization when using a mul over a sliced convolution

* Formatting

* Add more tests

* Formatting

* Convert to an assert

* Check if used once

* Formatting

* Add test with horiz fusion

* Formatting

* Optimize nested slice

* Formatting

* Fix test

* Add const refs

* Remove unnecessary assert

Co-authored-by: mvermeulen <[email protected]>

Fix the usage of move_dpp in HIP-Clang. (ROCm#544)

Add same padding mode for onnx (ROCm#456)

* fix pad calc

* add padding calc and test

* formatting

* made asym generic function

* formatting

Co-authored-by: mvermeulen <[email protected]>

Bump version

Fix c++ documentaion

Merge branch 'develop' into so-version

Merge pull request ROCm#273 from ROCmSoftwarePlatform/rnn_optimization

Rnn optimization

Formatting

Fix throw rename