[PATCH] D25881: [EarlyCSE] Optimize MemoryPhis and reduce memory clobber queries w/ MemorySSA
Geoff Berry via llvm-commits
llvm-commits at lists.llvm.org
Fri Oct 21 13:18:27 PDT 2016
Would you be opposed to me making this change in a follow-on change
since I've already done all of my testing on this version?
On 10/21/2016 4:15 PM, Daniel Berlin wrote:
> (IE you can use getClobberingAccess always, and not worry about it)
>
> On Fri, Oct 21, 2016 at 1:14 PM, Daniel Berlin <dberlin at dberlin.org
> <mailto:dberlin at dberlin.org>> wrote:
>
> "Also, when using MemorySSA to check if two MemoryUses are reading
> from
> the same version of the heap, use the defining access instead of
> calling
> getClobberingAccess, since the latter can currently result in many
> more
> AA calls."
>
> This should be fixed as of yesterday.
>
>
> On Fri, Oct 21, 2016 at 1:12 PM, Geoff Berry
> <gberry at codeaurora.org <mailto:gberry at codeaurora.org>> wrote:
>
> gberry created this revision.
> gberry added a reviewer: dberlin.
> gberry added subscribers: llvm-commits, mcrosier.
>
> When using MemorySSA, re-optimize MemoryPhis when removing a
> store since
> this may create MemoryPhis with all identical arguments.
>
> Also, when using MemorySSA to check if two MemoryUses are
> reading from
> the same version of the heap, use the defining access instead
> of calling
> getClobberingAccess, since the latter can currently result in
> many more
> AA calls. Once the MemorySSA use optimization tracking
> changes are
> done, we can remove this limitation, which should result in
> more loads
> being CSE'd.
>
>
> https://reviews.llvm.org/D25881 <https://reviews.llvm.org/D25881>
>
> Files:
> lib/Transforms/Scalar/EarlyCSE.cpp
> test/Transforms/EarlyCSE/memoryssa.ll
>
>
>
--
Geoff Berry
Employee of Qualcomm Datacenter Technologies, Inc.
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc. Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20161021/bf3c6e93/attachment.html>
More information about the llvm-commits
mailing list