`vector.contract` is being lowered to the default mul/add contraction
regardless if of the kind indicated. Stop the lowering completely in
this case until the correct one can be implemented.
Reviewed By: springerm, ThomasRaoux
Differential Revision: https://reviews.llvm.org/D136079
This patch takes the first step towards a more principled modeling of undefined behavior in MLIR as discussed in the following discourse threads:
1. https://discourse.llvm.org/t/semantics-modeling-undefined-behavior-and-side-effects/4812
2. https://discourse.llvm.org/t/rfc-mark-tensor-dim-and-memref-dim-as-side-effecting/65729
This patch in particular does the following:
1. Introduces a ConditionallySpeculatable OpInterface that dynamically determines whether an Operation can be speculated.
2. Re-defines `NoSideEffect` to allow undefined behavior, making it necessary but not sufficient for speculation. Also renames it to `NoMemoryEffect`.
3. Makes LICM respect the above semantics.
4. Changes all ops tagged with `NoSideEffect` today to additionally implement ConditionallySpeculatable and mark themselves as always speculatable. This combined trait is named `Pure`. This makes this change NFC.
For out of tree dialects:
1. Replace `NoSideEffect` with `Pure` if the operation does not have any memory effects, undefined behavior or infinite loops.
2. Replace `NoSideEffect` with `NoSideEffect` otherwise.
The next steps in this process are (I'm proposing to do these in upcoming patches):
1. Update operations like `tensor.dim`, `memref.dim`, `scf.for`, `affine.for` to implement a correct hook for `ConditionallySpeculatable`. I'm also happy to update ops in other dialects if the respective dialect owners would like to and can give me some pointers.
2. Update other passes that speculate operations to consult `ConditionallySpeculatable` in addition to `NoMemoryEffect`. I could not find any other than LICM on a quick skim, but I could have missed some.
3. Add some documentation / FAQs detailing the differences between side effects, undefined behavior, speculatabilty.
Reviewed By: rriddle, mehdi_amini
Differential Revision: https://reviews.llvm.org/D135505
This commit adds a pattern to merge accumulator and result
`vector.transpose` ops into `vector.contract`. This kind of
pattern can be generated for NCHW convolution vectorization,
where we use transposes to convert the 1-D NCW convolution
into NWC during vectorization. Merging the transpose would
mean we can avoid materialize vector extract/insert for
transposes and it makes further vector level transformations
easier.
Reviewed By: ThomasRaoux
Differential Revision: https://reviews.llvm.org/D135496
Make sure we consider other subviews of the same buffer when doing store
to load forwarding or dead store elimination.
Differential Revision: https://reviews.llvm.org/D134576
One of the vector transformation patterns has been indiscriminately
converting layouts to affine maps. Leverage the strided form when
possible.
Reviewed By: nicolasvasilache, dcaballe
Differential Revision: https://reviews.llvm.org/D134047
Bufferization already makes the assumption that buffers pass function
boundaries in the strided form and uses the corresponding affine map layouts.
Switch it to use the recently introduced strided layout instead to avoid
unnecessary casts when bufferizing further operations to the memref dialect
counterparts that now largely rely on the strided layout attribute.
Depends On D133947
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D133951
Simplify the lowering of warp_execute_on_lane0 of scf.if by making the
logic more generic. Also remove the assumption that the most inner
dimension is the dimension distributed.
Differential Revision: https://reviews.llvm.org/D133826
This revision significantly improves and tests the broadcast behavior of vector.warp_execute_on_lane_0.
Previously, the implementation of the broadcast behavior of vector.warp_execute_on_lane_0
assumed that the broadcasted value was always of scalar type.
This is not necessarily the case.
Differential Revision: https://reviews.llvm.org/D133767
This is the first step in replacing interator_type from strings with enums in Vector and Linalg dialect. This change adds IteratorTypeAttr and uses it in ContractionOp.
To avoid breaking all the tests, print/parse code has conversion between string and enum for now.
There is a shared code in StructuredOpsUtils.h that expects iterator types to be strings. To break this dependancy, this change forks helper function `isParallelIterator` and `isReductionIterator` to utils in both dialects and adds `getIteratorTypeNames()` to support backward compatibility with StructuredGenerator.
In the later changes, I plan to add a similar enum attribute to Linalg.
Differential Revision: https://reviews.llvm.org/D133696
The logic to figure out if a transfer op can be flattened wasn't
considering the shape being loaded therefore it was incorrectly assuming
some transfer ops were reading contigous data.
Differential Revision: https://reviews.llvm.org/D133544
Running: `mlir-opt -test-vector-warp-distribute=rewrite-warp-ops-to-scf-if -canonicalize -verify-each=0`.
Prior to this revision, IR resembling the following would be produced:
```
%4 = "vector.load"(%3, %arg0) : (memref<1x32xf32, 3>, index) -> vector<1x1xf32>
```
This fails verification since it needs 2 indices to load but only 1 is provided.
Differential Revision: https://reviews.llvm.org/D133106
The patch introduces the required changes to update the pass declarations and definitions to use the new autogenerated files and allow dropping the old infrastructure.
Reviewed By: mehdi_amini, rriddle
Differential Review: https://reviews.llvm.org/D132838
The patch introduces the required changes to update the pass declarations and definitions to use the new autogenerated files and allow dropping the old infrastructure.
Reviewed By: mehdi_amini, rriddle
Differential Review: https://reviews.llvm.org/D132838
In addition to memref, accept ranked tensor as the base operand of vector.gather, similar to vector.trasnfer_read.
This will allow us to vectorize noncontiguous tensor.extract into vector.gather. Full discussion can be found here: https://github.com/iree-org/iree/issues/9198
Reviewed By: hanchung, dcaballe
Differential Revision: https://reviews.llvm.org/D130097
This one required more changes than ideal due to overlapping generated name
with different return types. Changed getIndexingMaps to getIndexingMapsArray to
move it out of the way/highlight that it returns (more expensively) a
SmallVector and uses the prefixed name for the Attribute.
Differential Revision: https://reviews.llvm.org/D129919
This allows vectorizing linalg reductions without changing the operation
order. Therefore this produce a valid vectorization even if operations
are not associative.
Differential Revision: https://reviews.llvm.org/D129535
Prevent creating multiple output for the same Value when distributing
operations out of WarpExecuteOnLane0Op. This avoid creating combinatory
explosion of outputs.
Differential Revision: https://reviews.llvm.org/D129465
The result shape of a rank-reducing subview cannot be inferred in the general case. Just the result rank is not enough. The only thing that we can infer is the layout map.
This change also improves the bufferization patterns of tensor.extract_slice and tensor.insert_slice to fully support rank-reducing operations.
Differential Revision: https://reviews.llvm.org/D129144
This revision avoids a crash in the 0-D case of distributing vector.transfer ops out of
vector.warp_execute_on_lane_0.
Due to the code complexity and lack of documentation, it took untangling the implementation
before realizing that the simple fix was to fail in the 0-D case.
The rewrite is still very useful to understand this code better.
Differential Revision: https://reviews.llvm.org/D128793
Adding the accumulator value after the `vector.contract` changes the
precision of the operation. This makes sure the accumulator is carried
through to `vector.reduce` (and down to LLVM).
Differential Revision: https://reviews.llvm.org/D128674
When creating a scf.for without argument a scf.yield is automatically
created. Make sure we don't create a second one.
Differential Revision: https://reviews.llvm.org/D128405
