[LLVMdev] [llvm] r184698 - Add a flag to defer vectorization into a phase after the inliner and its

[Andrew Trick]

On Jun 24, 2013, at 7:24 PM, Chandler Carruth <chandlerc at gmail.com> wrote:

> 
> On Mon, Jun 24, 2013 at 7:16 PM, Andrew Trick <atrick at apple.com> wrote:
> I don't want to start a centi-thread yet, but here's a very rough idea (leaving many things out):
> 
> I actually like the look of this. I'll hack things around so we have a flag (or set) we can use to experiment. It would be great to get the bits factored out of IndvarSimplify so that we can run the experiments more easily.
> 
> I'm particularly interested in this if it addresses the regressions I hit with loop vectorize on by default.

Another thing to look at is whether we need a GVN utility to run after LICM/Unswitch, or just run a fast non-iterative version of the pass a second time. Likewise, the vectorizer may rely on GVN now, but it should probably call a utility instead.

-Andy
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20130624/3c126ccc/attachment.html>