[all-commits] [llvm/llvm-project] ca02f3: [mlir][vector] Teach `TransferOptimization` to for...

[Benjamin Maxwell via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: ca02f36bacaec58071a26ff65329fbab5526d1d7
      https://github.com/llvm/llvm-project/commit/ca02f36bacaec58071a26ff65329fbab5526d1d7
  Author: Benjamin Maxwell <benjamin.maxwell at arm.com>
  Date:   2024-05-16 (Thu, 16 May 2024)

  Changed paths:
    M mlir/lib/Dialect/Vector/IR/VectorOps.cpp
    M mlir/test/Dialect/Vector/vector-transferop-opt.mlir

  Log Message:
  -----------
  [mlir][vector] Teach `TransferOptimization` to forward masked stores (#87794)

This only handles one case (that's fairly common in practice*), storing
a masked constant splat, then reloading again with the same mask and a
padding value that matches the splat.

* For SVE/SME (without peeling) this occurs when you have a
`linalg.fill` preceding a `linalg.matmul`.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications