Use optimized library if op available (#324)

Summary:
Pull Request resolved: https://github.com/pytorch/executorch/pull/324

Some models (transformer models) has ops like bmm and optimized library providers a better performance than portable.

With optimized: https://www.internalfb.com/intern/aibench/details/125435623160736 (750 ms per iteration)
With portable: https://www.internalfb.com/intern/aibench/details/521699054450309 (1200 ms per iteration)

Reviewed By: mergennachin

Differential Revision: D49240517

fbshipit-source-id: 7cbc9dfe9ddf7eeff28daa41a0965a74f913497d