[all-commits] [llvm/llvm-project] fb54fe: [mlir][ArmSME] Implement tile allocation

[Cullen Rhodes via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: fb54fec7263ab420e9e02e1ea2b66403cf655a33
      https://github.com/llvm/llvm-project/commit/fb54fec7263ab420e9e02e1ea2b66403cf655a33
  Author: Cullen Rhodes <cullen.rhodes at arm.com>
  Date:   2023-07-18 (Tue, 18 Jul 2023)

  Changed paths:
    M mlir/include/mlir/Dialect/ArmSME/Transforms/Passes.h
    M mlir/include/mlir/Dialect/ArmSME/Transforms/Passes.td
    M mlir/lib/Dialect/ArmSME/Transforms/CMakeLists.txt
    M mlir/lib/Dialect/ArmSME/Transforms/LegalizeForLLVMExport.cpp
    A mlir/lib/Dialect/ArmSME/Transforms/TileAllocation.cpp
    A mlir/test/Dialect/ArmSME/tile-allocation.mlir
    M mlir/test/Integration/Dialect/Vector/CPU/ArmSME/vector-ops.mlir

  Log Message:
  -----------
  [mlir][ArmSME] Implement tile allocation

This patch adds a pass '-allocate-sme-tiles' to the ArmSME dialect that
implements allocation of SME ZA tiles.

It does this at the 'func.func' op level by replacing
'arm_sme.get_tile_id' ops with 'arith.constant' ops that represent the
tile number. The tiles in use in a given function are tracked by an
integer function attribute 'arm_sme.tiles_in_use' that is a 16-bit tile
mask with a bit for each 128-bit element tile (ZA0.Q-ZA15.Q), the
smallest ZA tile granule. This is initialized on the first
'arm_sme.get_tile_id' rewrite and updated on each subsequent rewrite.
Mixing of different element tile types is supported.

Section B2.3.2 of the SME spec [1] describes how the 128-bit element
tiles overlap with other element tiles.

Depends on D154941

[1] https://developer.arm.com/documentation/ddi0616/aa

Reviewed By: awarzynski

Differential Revision: https://reviews.llvm.org/D154955