[PATCH] D14909: [X86][FMA] Optimize FNEG(FMUL) Patterns

Simon Pilgrim via llvm-commits llvm-commits at lists.llvm.org
Mon Nov 30 11:39:17 PST 2015


RKSimon added a comment.

In http://reviews.llvm.org/D14909#298759, @spatel wrote:

> Simon - is there a reason to prefer waiting for type legalization before doing the transform? I know that's how it's done in PerformFMACombine(), but it seems that the more common pattern is to check for known legal types for a particular opcode. This allows the transform to fire earlier?


No reason other than matching the behaviour in PerformFMACombine() - I tend to prefer not creating X86ISD nodes until we really need to - it gives the DAGCombiner as much chance to constant fold etc. as possible.


Repository:
  rL LLVM

http://reviews.llvm.org/D14909





More information about the llvm-commits mailing list