[all-commits] [llvm/llvm-project] 77db8b: [mlir][vector] Restrict DropInnerMostUnitDimsTrans...

[Andrzej Warzyński via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 77db8b08c8b186c2625f8dfb26bb976561b43c4c
      https://github.com/llvm/llvm-project/commit/77db8b08c8b186c2625f8dfb26bb976561b43c4c
  Author: Andrzej Warzyński <andrzej.warzynski at arm.com>
  Date:   2024-06-12 (Wed, 12 Jun 2024)

  Changed paths:
    M mlir/lib/Dialect/Vector/Transforms/VectorTransforms.cpp
    M mlir/test/Dialect/Vector/vector-transfer-collapse-inner-most-dims.mlir

  Log Message:
  -----------
  [mlir][vector] Restrict DropInnerMostUnitDimsTransferRead (#94904)

Restrict `DropInnerMostUnitDimsTransferRead` so that it fails when one
of the indices to be dropped could be != 0, e.g.

```mlir
func.func @negative_example(%A: memref<16x1xf32>, %i:index, %j:index) -> (vector<8x1xf32>) {
  %f0 = arith.constant 0.0 : f32
  %1 = vector.transfer_read %A[%i, %j], %f0 : memref<16x1xf32>, vector<8x1xf32>
  return %1 : vector<8x1xf32>
}
```

This is an edge case that could represent an out-of-bounds access,
though that will depend on the actual value of `%j`. Importantly,
_without this change_ it would be transformed as follows:
```mlir
  func.func @negative_example(%arg0: memref<16x1xf32>, %arg1: index, %arg2: index) -> vector<8x1xf32> {
    %cst = arith.constant 0.000000e+00 : f32
    %subview = memref.subview %arg0[0, 0] [16, 1] [1, 1] : memref<16x1xf32> to memref<16xf32, strided<[1]>>
    %0 = vector.transfer_read %subview[%arg1], %cst : memref<16xf32, strided<[1]>>, vector<8xf32>
    %1 = vector.shape_cast %0 : vector<8xf32> to vector<8x1xf32>
    return %1 : vector<8x1xf32>
  }
```

This is incorrect - `%arg2` is ignored. Hence the extra restriction to
avoid such cases.

NOTE: This PR is limited to tests for `vector.transfer_read`.



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