GitLab

* Enable scheduler for 1 stream

* Formatting

* Improve performance of sorting

* Formatting

* Adjust the weight calculation

* Formatting

* Simplify formula

* Formatting

* Avoid division by zero

* Fix scheduler test

* Check for either 1 or 2

* Check for waits when order may change

* Formatting

add a pass to resolve the problem that hip_allocation shape is different from instruction output shape.

changed the eliminate_contiguous pass to skip the reshape operator, so onnx file exported from lstm operator can work correctly in the bidirectional case.