[all-commits] [llvm/llvm-project] 22f115: [mlir][ArmSME] Propagate pad and mask in vector.tr...

[Cullen Rhodes via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 22f11592232839f8e7b2228169012beab24fa56a
      https://github.com/llvm/llvm-project/commit/22f11592232839f8e7b2228169012beab24fa56a
  Author: Cullen Rhodes <cullen.rhodes at arm.com>
  Date:   2023-11-02 (Thu, 02 Nov 2023)

  Changed paths:
    M mlir/lib/Conversion/VectorToArmSME/VectorToArmSME.cpp
    M mlir/test/Dialect/ArmSME/vector-ops-to-sme.mlir

  Log Message:
  -----------
  [mlir][ArmSME] Propagate pad and mask in vector.transfer_read lowering (#70814)

This extends the lowering of vector.transfer_read -> arm_sme.tile_load
lowering to propagate pad and mask.

The restriction on the transfer_read being a transposition is also
removed, identity maps are lowered to normal horizontal loads.