5 Commits

Author SHA1 Message Date
Lei Zhang
3049ac44e6
[mlir][vector] Enable transfer op hoisting with dynamic indices (#68500)
Recent changes (https://github.com/llvm/llvm-project/pull/66930)
disabled vector transfer ops hoisting with view-like intermediate ops.
The recommended way is to fold subview ops into transfer op indices
before invoking hoisting. That would mean now we see transfer op indices
involving dynamic values, instead of static constant values before with
subview ops. Therefore hoisting won't kick in anymore. This breaks
downstream users.

To fix it, this commit enables hoisting transfer ops with dynamic
indices by using `ValueBoundsConstraintSet` to prove ranges are disjoint
in `isDisjointTransferIndices`. Given that utility is used in many
places including op folders, right now we introduce a flag to it and
only set as true for "heavy" transforms in hoisting and load-store
forwarding.
2023-10-15 16:37:54 -07:00
Matthias Springer
ebaf8d4949
[mlir][affine] ValueBoundsConstraintSet: Fully compose affine.apply (#68899)
Fully compose `affine.apply` ops before adding them to the underlying
`FlatLinearConstraints`. This works around a limitation of
`FlatLinearConstraints`, which cannot deduce a constant bound if it
involves two identical local variables.

Details for future improvements of `FlatLinearConstraints`: The
constraint set infrastructure fails to compute a constant bound of -8
for the first variable.
```
Domain: 0, Range: 1, Symbols: 4, Locals: 2
8 constraints
(None    None    None    None    None    Local    Local    const)
 1    -1    0    0    0    0    0    0    = 0
 0    1    -1    1    0    0    0    0    = 0
 0    0    1    0    0    0    -16    0    = 0
 0    0    0    1    0    -16    0    -8    = 0
 0    0    0    0    -1    0    32    31    >= 0
 0    0    0    0    1    0    -32    0    >= 0
 0    0    0    0    -1    32    0    31    >= 0
 0    0    0    0    1    -32    0    0    >= 0
```
2023-10-12 18:17:37 -07:00
Matthias Springer
4c48f016ef [mlir][Affine][NFC] Wrap dialect in "affine" namespace
This cleanup aligns the affine dialect with all the other dialects.

Differential Revision: https://reviews.llvm.org/D148687
2023-04-20 11:19:21 +09:00
Matthias Springer
041bc485bf [mlir][Interfaces] ValueBoundsOpInterface: Support LB and UB bounds
This change also adds support for `affine.min` and `affine.max` ops.

Differential Revision: https://reviews.llvm.org/D145787
2023-04-07 10:48:19 +09:00
Matthias Springer
4f8f01b76c [mlir][linalg] ValueBoundsOpInterface: Add affine.apply op
Differential Revision: https://reviews.llvm.org/D145694
2023-04-06 10:23:06 +09:00