[PATCH] D18949: [AArch64] Cannonicalize commutative operands based on LSLFast

[Renato Golin via llvm-commits]

rengolin added a comment.

In http://reviews.llvm.org/D18949#396702, @flyingforyou wrote:

> I think this optimization will affect all ARM Architectures. Is this optimization also good for cortex-a57?


Or A53, or A72, or A35...

Without further performance numbers, it's hard to say. If they don't have a positive effect on vanilla AArch64 design, it should be behind a Feature flag.


Repository:
  rL LLVM

http://reviews.llvm.org/D18949