[PATCH] D93030: [AArch64][SVE]Add cost model for masked gather and scatter for scalable vector.

[Caroline via Phabricator via llvm-commits]

CarolineConcatto added a comment.

@tschuett  I agree that we should refine the value if MaxVScale according to the Architecture by using flags. 
 But I believe this should be the scope of another patch. 
 Implementing the use of a flag to compute the value of MaxVScale will increase the complexity of the patch, and  IMHO it is not related to the cost of gather and scatters.
The value of MaxVScale is/will be used to compute the cost of others intrinsic/instructions with vscale data type.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D93030/new/

https://reviews.llvm.org/D93030