[PATCH] D8817: Estimate DCE effect in heuristic for estimating complete-unroll optimization effects.

Michael Zolotukhin mzolotukhin at apple.com
Wed Jul 15 16:52:58 PDT 2015


> On Jul 15, 2015, at 4:25 PM, Chandler Carruth <chandlerc at google.com> wrote:
> 
> I thought this was no longer going forward in favor of the other patches I've been reviewing...
> 
> Michael, leme know if I should still look at this.
Yes, please! This patch is also still relevant.

Thanks,
Michael
> 
> On Wed, Jul 15, 2015 at 4:21 PM Gerolf Hoflehner <ghoflehner at apple.com <mailto:ghoflehner at apple.com>> wrote:
> Was there an update?
> 
> Thanks
> Gerolf
> > On Jul 7, 2015, at 10:28 PM, Michael Zolotukhin <mzolotukhin at apple.com <mailto:mzolotukhin at apple.com>> wrote:
> >
> > mzolotukhin marked an inline comment as done.
> >
> > Thanks, Gerolf,
> > I'll update the comments.
> >
> >
> > ================
> > Comment at: lib/Transforms/Scalar/LoopUnrollPass.cpp:635
> > @@ -620,3 +634,3 @@
> >     // won't find them on later ones too.
> >     if (UnrolledCost == RolledDynamicCost)
> >       return None;
> > ----------------
> > Gerolf wrote:
> >> I'm missing context. Where do the costs get computed?
> > On lines 594, 598.
> >
> >
> > http://reviews.llvm.org/D8817 <https://urldefense.proofpoint.com/v2/url?u=http-3A__reviews.llvm.org_D8817&d=AwMFaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=x9eOzpiYMOnZB_Jbgre_rv1dKbPP9kHD4Ev4Q2aRdbk&s=D6IlRds4PpH8nPUKYAPJg7mE7boYVAJx27Jj3LSW658&e=>
> >
> >
> >
> 
> 
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at cs.uiuc.edu <mailto:llvm-commits at cs.uiuc.edu>
> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits <http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits>
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20150715/67ce24f5/attachment.html>


More information about the llvm-commits mailing list