[PATCH] D20695: Floating Point SCEV Analysis

Sanjay Patel via llvm-commits llvm-commits at lists.llvm.org
Thu Jun 2 07:52:31 PDT 2016

spatel added a reviewer: scanon.
spatel added a subscriber: scanon.
spatel added a comment.

In http://reviews.llvm.org/D20695#446877, @sbaranga wrote:

> Replacing x with fp_inc*N should require fast-math - and it's not clear to me what fast-math allows.
>  If this is correct with fast-math, we should be able to use this to get the backedge taken count - which would be a good reason for doing this in SCEV.
> I don't know if this has been established before, but the vectorization tests use FP re-association, so fast-math is also required there.

These are the same questions raised in PR27894:

An even simpler test case still raises questions if we support changes to the FP env:

[cc'ing @scanon for FP semantics questions]



More information about the llvm-commits mailing list