[PATCH] [AArch64] Override useAA and remove unneeded edges in the scheduling graph

[Chad Rosier]

Hi Sanjin,
I put this in Phabricator to ease review.  I also added reviewers that
might be interested (i.e., James, Jiangning, and Tim) and left a few
comments myself.

http://reviews.llvm.org/D5103

 Chad

> Hi,
>
>
>
> This patch removes edges in the scheduling graph between stores/loads off
> the same base register if memory accesses do not overlap.   We saw an
> improvement on eembc/automark on a cortex-a53 device, as well as a small
> improvement on spec2000/eon.  No significant performance changes were
> observed on cortex-a57, but this may be more relevant on in-order
> architectures.
>
>
>
> Would this be of interest to anyone?  If so, can someone please review?
>
>
>
> Thanks,
>
> Sanjin
>
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits
>