Do not generate CollapseShapeOps/ExpandShapeOps that have the same source and result shape. Generate casts instead. Such reshapes became invalid with D138498.
Differential Revision: https://reviews.llvm.org/D138557
Avoid duplicate code by using an existing helper function to interchange
a vector based on a permutation. Address comments emerged after landing
D138119.
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D138480
Pack and Unpack return new tensors within which the individual elements
are reshuffled according to the packing specification. This has the
consequence of modifying the canonical order in which a given operator
(i.e., Matmul) accesses the individual elements. After bufferization,
this typically translates to increased access locality and cache
behavior improvement, e.g., eliminating cache line splitting.
Co-authored-by: Mahesh Ravishankar <ravishankarm@google.com>
Co-authored-by: Han-Chung Wang <hanchung@google.com>
RFC: https://discourse.llvm.org/t/rfc-tensor-pack-and-tensor-unpack/66408/1
Reviewed By: nicolasvasilache, rengolin, hanchung
Differential Revision: https://reviews.llvm.org/D138119
The `RankedTensorType` can have an optional encoding
attribute. Allowing the builders of `tensor.empty` to accept the
encoding attribute (optionally), allows building empty tensors with
the type having the encoding attribute.
Reviewed By: nicolasvasilache, hanchung, springerm
Differential Revision: https://reviews.llvm.org/D137297
When writing a tensor.extract/tensor.insert, the rank of the tensor is implied by the number of specified indices. When extracting from/inserting into an unranked tensor, it should first be casted to a ranked version.
Differential Revision: https://reviews.llvm.org/D136756
Drop the `createPadScalarOp` from Utils.h since it is a duplicate of
the `build` method added here.
Differential Revision: https://reviews.llvm.org/D136493
`getDestinationOperands` was almost a duplicate of `DestinationStyleOpInterface::getOutputOperands`. Now that the interface has been moved to mlir/Interfaces, it is no longer needed.
Differential Revision: https://reviews.llvm.org/D136240
The assert is misplaced as the result type is allowed to be null. A few
lines below the result type is inferred if it is passed a nullptr.
Besides, this behavior is described in the documentation of the builder.
Reviewed By: ftynse
Differential Revision: https://reviews.llvm.org/D136262
These operations have undefined behavior if the index is not less than the rank of the source tensor / memref, so they cannot be freely speculated like they were before this patch. After this patch we speculate them only if we can prove that they don't have UB.
Depends on D135505.
Reviewed By: mravishankar
Differential Revision: https://reviews.llvm.org/D135748
tensor.empty/linalg.init_tensor produces an uninititalized tensor that can be used as a destination operand for destination-style ops (ops that implement `DestinationStyleOpInterface`).
This change makes it possible to implement `TilingInterface` for non-destination-style ops without depending on the Linalg dialect.
RFC: https://discourse.llvm.org/t/rfc-add-tensor-from-shape-operation/65101
Differential Revision: https://reviews.llvm.org/D135129
This change adds a set of utilities to replace the result of a
`tensor.collapse_shape -> tensor.extract_slice` chain with the
equivalent result formed by aggregating slices of the
`tensor.collapse_shape` source. In general, it is not possible to
commute `extract_slice` and `collapse_shape` if linearized dimensions
are sliced. The i-th dimension of the `tensor.collapse_shape`
result is a "linearized sliced dimension" if:
1) Reassociation indices of tensor.collapse_shape in the i'th position
is greater than size 1 (multiple dimensions of the input are collapsed)
2) The i-th dimension is sliced by `tensor.extract_slice`.
We can work around this by stitching together the result of
`tensor.extract_slice` by iterating over any linearized sliced dimensions.
This is equivalent to "tiling" the linearized-and-sliced dimensions of
the `tensor.collapse_shape` operation in order to manifest the result
tile (the result of the `tensor.extract_slice`). The user of the
utilities must provide the mechanism to create the tiling (e.g. a loop).
In the tests, it is demonstrated how to apply the utilities using either
`scf.for` or `scf.foreach_thread`.
The below example illustrates the pattern using `scf.for`:
```
%0 = linalg.generic ... -> tensor<3x7x11x10xf32>
%1 = tensor.collapse_shape %0 [[0, 1, 2], [3]] : ... to tensor<341x10xf32>
%2 = tensor.extract_slice %1 [13, 0] [10, 10] [2, 1] : .... tensor<10x10xf32>
```
We can construct %2 by generating the following IR:
```
%dest = linalg.init_tensor() : tensor<10x10xf32>
%2 = scf.for %iv = %c0 to %c10 step %c1 iter_args(%arg0) -> tensor<10x10xf32> {
// Step 1: Map this output idx (%iv) to a multi-index for the input (%3):
%linear_index = affine.apply affine_map<(d0)[]->(d0*2 + 11)>(%iv)
%3:3 = arith.delinearize_index %iv into (3, 7, 11)
// Step 2: Extract the slice from the input
%4 = tensor.extract_slice %0 [%3#0, %3#1, %3#2, 0] [1, 1, 1, 10] [1, 1, 1, 1] :
tensor<3x7x11x10xf32> to tensor<1x1x1x10xf32>
%5 = tensor.collapse_shape %4 [[0, 1, 2], [3]] :
tensor<1x1x1x10xf32> into tensor<1x10xf32>
// Step 3: Insert the slice into the destination
%6 = tensor.insert_slice %5 into %arg0 [%iv, 0] [1, 10] [1, 1] :
tensor<1x10xf32> into tensor<10x10xf32>
scf.yield %6 : tensor<10x10xf32>
}
```
The pattern was discussed in the RFC here: https://discourse.llvm.org/t/rfc-tensor-extracting-slices-from-tensor-collapse-shape/64034
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D129699
This reverts commit 5711957875738c1318f89afd7bf4be388f85a087.
A circular dependency is introduced here from Dialect/Utils/ to the
ViewLikeInterface, but it already depends on Dialect/Utils.
Also this introduces a dependency from lib/Dialect/Tensor to Linalg,
which isn't obviously correct from a layering point of view.
This change adds a set of utilities to replace the result of a
`tensor.collapse_shape -> tensor.extract_slice` chain with the
equivalent result formed by aggregating slices of the
`tensor.collapse_shape` source. In general, it is not possible to
commute `extract_slice` and `collapse_shape` if linearized dimensions
are sliced. The i-th dimension of the `tensor.collapse_shape`
result is a "linearized sliced dimension" if:
1) Reassociation indices of tensor.collapse_shape in the i'th position
is greater than size 1 (multiple dimensions of the input are collapsed)
2) The i-th dimension is sliced by `tensor.extract_slice`.
We can work around this by stitching together the result of
`tensor.extract_slice` by iterating over any linearized sliced dimensions.
This is equivalent to "tiling" the linearized-and-sliced dimensions of
the `tensor.collapse_shape` operation in order to manifest the result
tile (the result of the `tensor.extract_slice`). The user of the
utilities must provide the mechanism to create the tiling (e.g. a loop).
In the tests, it is demonstrated how to apply the utilities using either
`scf.for` or `scf.foreach_thread`.
The below example illustrates the pattern using `scf.for`:
```
%0 = linalg.generic ... -> tensor<3x7x11x10xf32>
%1 = tensor.collapse_shape %0 [[0, 1, 2], [3]] : ... to tensor<341x10xf32>
%2 = tensor.extract_slice %1 [13, 0] [10, 10] [2, 1] : .... tensor<10x10xf32>
```
We can construct %2 by generating the following IR:
```
%dest = linalg.init_tensor() : tensor<10x10xf32>
%2 = scf.for %iv = %c0 to %c10 step %c1 iter_args(%arg0) -> tensor<10x10xf32> {
// Step 1: Map this output idx (%iv) to a multi-index for the input (%3):
%linear_index = affine.apply affine_map<(d0)[]->(d0*2 + 11)>(%iv)
%3:3 = arith.delinearize_index %iv into (3, 7, 11)
// Step 2: Extract the slice from the input
%4 = tensor.extract_slice %0 [%3#0, %3#1, %3#2, 0] [1, 1, 1, 10] [1, 1, 1, 1] :
tensor<3x7x11x10xf32> to tensor<1x1x1x10xf32>
%5 = tensor.collapse_shape %4 [[0, 1, 2], [3]] :
tensor<1x1x1x10xf32> into tensor<1x10xf32>
// Step 3: Insert the slice into the destination
%6 = tensor.insert_slice %5 into %arg0 [%iv, 0] [1, 10] [1, 1] :
tensor<1x10xf32> into tensor<10x10xf32>
scf.yield %6 : tensor<10x10xf32>
}
```
The pattern was discussed in the RFC here: https://discourse.llvm.org/t/rfc-tensor-extracting-slices-from-tensor-collapse-shape/64034
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D129699
parallel_insert_slice doesn't return a value therefore we shouldn't try
to fold the result. The insert folding don't apply to this op.
The current folding would cause pattern rewrite to not be able to
converge.
Differential Revision: https://reviews.llvm.org/D132668
This commit folds a `tensor.cast` op into a `tensor.collapse_shape` op
when following two conditions meet:
1. the `tensor.collapse_shape` op consumes result of the `tensor.cast` op.
2. `tensor.cast` op casts to a more dynamic version of the source tensor.
This is added as a canonicalization pattern in `tensor.collapse_shape` op.
Signed-Off-By: Gaurav Shukla <gaurav@nod-labs.com>
Reviewed By: mravishankar
Differential Revision: https://reviews.llvm.org/D130650
This revision updates the op semantics to also allow rank-reducing behavior as well
as updates the implementation to reuse code between the sequential and the parallel
version of the op.
Depends on D128920
Differential Revision: https://reviews.llvm.org/D128985
This is moslty NFC and will allow tensor.parallel_insert_slice to gain
rank-reducing semantics by reusing the vast majority of the tensor.insert_slice impl.
Depends on D128857
Differential Revision: https://reviews.llvm.org/D128920
This revision makes sure we accept sparse tensors as arguments
of the expand/collapse reshaping operations in the tensor dialect.
Note that the actual lowering to runnable IR is still TBD.
Reviewed By: springerm
Differential Revision: https://reviews.llvm.org/D128311
Marked all dialects that could be (reasonably) easily flipped to _Both
prefix. Updating the accessors to prefixed form will happen in follow
up, this was to flush out conflicts and to mark all dialects explicitly
as I plan to flip OpBase default to _Prefixed to avoid needing to
migrate new dialects.
Except for Standalone example which got flipped to _Prefixed.
Differential Revision: https://reviews.llvm.org/D128027
Instead of requiring the client to compute the "isSplat" bit,
compute it internally. This makes the logic more consistent
and defines away a lot of "elements.size()==1" in the clients.
This addresses Issue #55185
Differential Revision: https://reviews.llvm.org/D125447
Now that dialect constructors are generated in the .cpp file, we can
drop all of the dependent dialect includes from the .h file.
Differential Revision: https://reviews.llvm.org/D124298
I am not sure about the meaning of Type in the name (was it meant be interpreted as Kind?), and given the importance and meaning of Type in the context of MLIR, its probably better to rename it. Given the comment in the source code, the suggestion in the GitHub issue and the final discussions in the review, this patch renames the OperandType to UnresolvedOperand.
Fixes https://github.com/llvm/llvm-project/issues/54446
Differential Revision: https://reviews.llvm.org/D122142
ExpandShapeOp builder cannot infer the result type since it doesn't know
how the dimension needs to be split. Remove this builder so that it
doesn't get used accidently. Also remove one potential path using it in
generic fusion.
Differential Revision: https://reviews.llvm.org/D122019
In this CL, update the function name of verifier according to the
behavior. If a verifier needs to access the region then it'll be updated
to `verifyRegions`.
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D120373
A `tensor.cast` consumer can be folded with its producer. This is
beneficial only if the result of the tensor cast is more static than
the source. This patch adds a utility function to check that this is
the case, and adds a couple of canonicalizations patterns that fold an
operation with `tensor.cast` conusmers.
Reviewed By: gysit
Differential Revision: https://reviews.llvm.org/D120950
Add a pattern matcher for ExtractSliceOp when its source is a constant.
The matching heuristics can be governed by the control function since
generating a new constant is not always beneficial.
Differential Revision: https://reviews.llvm.org/D119605
