[PATCH] D147040: [AArch64][CodeGen] Use interleave store for streaming compatible functions

[David Sherwood via Phabricator via llvm-commits]

david-arm accepted this revision.
david-arm added a comment.
This revision is now accepted and ready to land.

LGTM! Eccelente! Thanks for making the changes @CarolineConcatto.



================
Comment at: llvm/test/CodeGen/AArch64/sve-streaming-mode-fixed-length-shuffle.ll:35
+
+define void @interleave_store_legalization(ptr %a, <8 x i32> %b) #0 {
+; CHECK-LABEL: interleave_store_legalization:
----------------
CarolineConcatto wrote:
> david-arm wrote:
> > This test has the same problem as `@hang_when_merging_stores_after_legalisation`, because it's using splats. I think you can do this:
> > 
> > ```define void @interleave_store_legalization(ptr %p, <8 x i32> %a, <8 x i32> %b) #0 {
> >   %interleaved = shufflevector <8 x i32> %a, <8 x i32> %b, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
> >   store <16 x i32> %interleaved, ptr %p, align 1
> >   ret void
> > }```
> I don't fully understand why the splat in not a good example, but I did changed. Hope it is better now,
Well, it's for the same reason as `@hang_when_merging_stores_after_legalisation`, because the splat version may get optimised in future to be a pair of `stp` instructions that's all.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D147040/new/

https://reviews.llvm.org/D147040