[all-commits] [llvm/llvm-project] dfa10e: [mlir][ArmSME] Extend arm_sme.zero for all types

[Cullen Rhodes via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: dfa10ec2e6006ce5366a1e9013f0dbf4344f3e60
      https://github.com/llvm/llvm-project/commit/dfa10ec2e6006ce5366a1e9013f0dbf4344f3e60
  Author: Cullen Rhodes <cullen.rhodes at arm.com>
  Date:   2023-08-11 (Fri, 11 Aug 2023)

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

  Log Message:
  -----------
  [mlir][ArmSME] Extend arm_sme.zero for all types

The arm_sme.zero op currently only supports 8-bit element tiles. This
extends the op and lowering from 'arith.constant dense<0>' ->
'arm_sme.zero' to support all tile types.

The lowering from arm_sme.zero to intrinsics is not updated as part of
this patch and will be done separately.

Reviewed By: dcaballe

Differential Revision: https://reviews.llvm.org/D156980