[PATCH] D97758: [CostModel][SVE] Add cost model for shuffle reverse with i1 and scalable vector

[Caroline via Phabricator via llvm-commits]

CarolineConcatto marked an inline comment as done.
CarolineConcatto added a comment.

Thank you Sander!
My mistake not update main. Thank you for pointing it out.
Now the test is based on the latest main repo.



================
Comment at: llvm/test/Analysis/CostModel/AArch64/getIntrinsicInstrCost-vector-reverse.ll:50
   call <16 x bfloat> @llvm.experimental.vector.reverse.v16bf16(<16 x bfloat> undef)
+  call <16 x i1> @llvm.experimental.vector.reverse.nxv16i1(<16 x i1> undef)
+  call <8 x i1> @llvm.experimental.vector.reverse.nxv8i1(<8 x i1> undef)
----------------
sdesmalen wrote:
> The operand is not scalable, so this mangling of the intrinsic is not correct.
Thank you Sander.
It was a C&P mistake.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D97758/new/

https://reviews.llvm.org/D97758