[PATCH] D109416: getVPMemoryOpCost interface

Roland Froese via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Mon Oct 18 11:23:23 PDT 2021


RolandF added a comment.

In D109416#3070423 <https://reviews.llvm.org/D109416#3070423>, @bmahjour wrote:

> In D109416#3067495 <https://reviews.llvm.org/D109416#3067495>, @RolandF wrote:
>
>> Is this still needed?
>
> Yes, this patch establishes the target interface that is implemented by D109417 <https://reviews.llvm.org/D109417>.

Yes, I realize.  Are you intending to go ahead with that patch?  It has been sitting of a a while.  I would imagine that is useful info for other reviewers.



================
Comment at: llvm/include/llvm/Analysis/TargetTransformInfo.h:1121
+  InstructionCost
+  getVPMemoryOpCost(unsigned Opcode, Type *Src, Align Alignment,
+                    unsigned AddressSpace,
----------------
bmahjour wrote:
> RolandF wrote:
> > I prefer the downstream name getVariableLengthMemoryOpCost.  I'm not sure
> > what VP stands for here and it seems like VP is already used in the context of VPlan.  At least explain in the comment.
> VP stands for Vector Predication and is the name that the community has used for all the predicated intrinsics. See https://llvm.org/docs/LangRef.html#vector-predication-intrinsics
Well, I followed your link.  There are no "vp" memory ops.  The loads and stores are named "masked" operations.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D109416/new/

https://reviews.llvm.org/D109416



More information about the llvm-commits mailing list