[all-commits] [llvm/llvm-project] 0473e3: [mlir][ArmSME] Add rewrite to lift illegal vector....

[Benjamin Maxwell via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 0473e322f67228a9c2dbf462357e5b4a2b3799be
      https://github.com/llvm/llvm-project/commit/0473e322f67228a9c2dbf462357e5b4a2b3799be
  Author: Benjamin Maxwell <benjamin.maxwell at arm.com>
  Date:   2024-02-06 (Tue, 06 Feb 2024)

  Changed paths:
    M mlir/lib/Dialect/ArmSME/Transforms/VectorLegalization.cpp
    M mlir/test/Dialect/ArmSME/vector-legalization.mlir

  Log Message:
  -----------
  [mlir][ArmSME] Add rewrite to lift illegal vector.transposes to memory (#80170)

When unrolling the reduction dimension of something like a matmul for
SME, you can end up with transposed reads of illegal types, like so:

```mlir
%illegalRead = vector.transfer_read %memref[%a, %b]
                : memref<?x?xf32>, vector<[8]x4xf32>
%legalType = vector.transpose %illegalRead, [1, 0]
                : vector<[8]x4xf32> to vector<4x[8]xf32>
```

Here the `vector<[8]x4xf32>` is an illegal type, there's no way to lower
a scalable vector of fixed vectors. However, as the final type
`vector<4x[8]xf32>` is legal, we can instead lift the transpose to
memory (producing a strided memref), and eliminate all the illegal
types. This is shown below.

```mlir
%readSubview = memref.subview %memref[%a, %b] [%c8_vscale, %c4] [%c1, %c1]
                : memref<?x?xf32> to memref<?x?xf32>
%transpose = memref.transpose %readSubview (d0, d1) -> (d1, d0)
                : memref<?x?xf32> to memref<?x?xf32>
%legalType = vector.transfer_read %transpose[%c0, %c0]
                : memref<?x?xf32>, vector<4x[8]xf32>
```