[all-commits] [llvm/llvm-project] c7a334: [mlir][linalg] Fix scalable vectorisation of tenso...

[Andrzej Warzyński via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c7a3346ab6a8fbd551a80bd4028ec8624daa35e4
      https://github.com/llvm/llvm-project/commit/c7a3346ab6a8fbd551a80bd4028ec8624daa35e4
  Author: Andrzej Warzyński <andrzej.warzynski at arm.com>
  Date:   2024-07-25 (Thu, 25 Jul 2024)

  Changed paths:
    M mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp
    M mlir/test/Dialect/Linalg/vectorize-tensor-extract-masked.mlir

  Log Message:
  -----------
  [mlir][linalg] Fix scalable vectorisation of tensor.extract (#100325)

This PR fixes one very specific aspect of vectorising `tensor.extract`
Ops when targeting scalable vectors. Namely, it makes sure that the
scalable flag is correctly propagated when creating
`vector::ShapeCastOp`.

BEFORE:
```mlir
vector.shape_cast %idx_vec : vector<1x1x[4]xindex> to vector<4xindex>
```

AFTER:
```mlir
vector.shape_cast %idx_vec : vector<1x1x[4]xindex> to vector<[4]xindex>
```

This particular ShapeCastOp is created when generating an index for
`vector.transfer_read` operations. Strictly speaking, casting is not
really required. However, it makes the subsequent address calculation
much simpler (*).

The following test is updated to demonstrate the use of
`vector.shape_cast` by the vectoriser:
*
@masked_static_vectorize_nd_tensor_extract_with_affine_apply_contiguous

Similar test with scalable vectors is also added.

(*) At this point in the vectoriser it is known
that all leading dims in the index vector are "1").



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