[PATCH] D40021: [X86][Haswell]: Updating the scheduling information for the Haswell subtarget.

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added a comment.

What are your thoughts on the retl/retq latencies? Some models are using the default (which includes load latency) but others have overriden it. It doesn't make much difference to codegen but I'm wondering if we need to be consistent.


Repository:
  rL LLVM

https://reviews.llvm.org/D40021