[all-commits] [llvm/llvm-project] ced97f: [mlir][Vector] Don't fully unroll transfer_writes ...

[Benjamin Maxwell via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: ced97ffd0899a3faff796170ed778723efcf8a5b
      https://github.com/llvm/llvm-project/commit/ced97ffd0899a3faff796170ed778723efcf8a5b
  Author: Benjamin Maxwell <benjamin.maxwell at arm.com>
  Date:   2023-11-13 (Mon, 13 Nov 2023)

  Changed paths:
    M mlir/lib/Conversion/VectorToSCF/VectorToSCF.cpp
    M mlir/test/Conversion/VectorToSCF/vector-to-scf.mlir

  Log Message:
  -----------
  [mlir][Vector] Don't fully unroll transfer_writes of n-D scalable vectors (#71924)

It is not possible to unroll a scalable vector at compile time. This
currently prevents transfer_writes from being lowered to
arm_sme.tile_writes (downstream).