[PATCH] D62847: [PowerPC] reorder LSR and PPCCTRLoops pass

[Hal Finkel via Phabricator via llvm-commits]

hfinkel added a comment.

I'm really uneasy about this change. PPCCTRLoops inserts special loop intrinsics which the rest of the loop-optimization pipeline doesn't understand, and so logically, it should come last. It's pretty clear that LSR is interfering with PPCCTRLoops, is this because it transforms the loops into some form that SCEV doesn't understand? Could we adjust LSR to make it more friendly to hardware-assisted loops? In theory, if LSR had the right cost model, it could actually make *more* loops that PPCCTRLoops could handle, and not fewer?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D62847/new/

https://reviews.llvm.org/D62847