[all-commits] [llvm/llvm-project] e47334: [mlir][Vector] Improve vector.transferx store-to-l...

[Kunwar Grover via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: e4733424bc9f8dd6df2f2f3e35e6c4477b8755d7
      https://github.com/llvm/llvm-project/commit/e4733424bc9f8dd6df2f2f3e35e6c4477b8755d7
  Author: Kunwar Grover <groverkss at gmail.com>
  Date:   2025-12-12 (Fri, 12 Dec 2025)

  Changed paths:
    M mlir/lib/Dialect/Vector/IR/VectorOps.cpp
    M mlir/test/Dialect/Vector/canonicalize.mlir

  Log Message:
  -----------
  [mlir][Vector] Improve vector.transferx store-to-load-forwarding (#171840)

This patch changes the transfer_write -> transfer_read load store
forwarding canonicalization pattern to work based on permutation maps
and less on adhoc logic. The old logic couldn't canonicalize a simple
unit dim broadcast through transfer_write/transfer_read which is added
as a test in this patch.

This patch also details what would be needed to support cases which are
not yet implemented better.



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