We were missing to check for transpose when folding.
Also add a new file to test folding independently of
canonicalization as canonicalization was hiding the bug.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D140533
This is part of an effort to migrate from llvm::Optional to
std::optional. This patch changes the way mlir-tblgen generates .inc
files, and modifies tests and documentation appropriately. It is a "no
compromises" patch, and doesn't leave the user with an unpleasant mix of
llvm::Optional and std::optional.
A non-trivial change has been made to ControlFlowInterfaces to split one
constructor into two, relating to a build failure on Windows.
See also: https://discourse.llvm.org/t/deprecating-llvm-optional-x-hasvalue-getvalue-getvalueor/63716
Signed-off-by: Ramkumar Ramachandra <r@artagnon.com>
Differential Revision: https://reviews.llvm.org/D138934
This patch introduces the initial bits to support vector masking
using the `vector.mask` operation. Vectorization changes should be
NFC for non-masked cases. We can't test masked cases directly until
we extend the Transform dialect to support masking.
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D137690
This patch mechanically replaces None with std::nullopt where the
compiler would warn if None were deprecated. The intent is to reduce
the amount of manual work required in migrating from Optional to
std::optional.
This is part of an effort to migrate from llvm::Optional to
std::optional:
https://discourse.llvm.org/t/deprecating-llvm-optional-x-hasvalue-getvalue-getvalueor/63716
- Use `zip_equal` where iteratees are supposted to have equal lenght.
- Use `zip_first` where the first iteratee is supposed to be the
shortest.
- Use `llvm::enumerate` instead of calculating index manually.
- Use structured bindings to unpack tuples where appropriate.
- Fix a bug in a comparison in `intersectsWhereNonNegative`.
Both `zip_first` (after D138858) and `zip_equal` (introduced in D138865)
assert interatee lengths, which allows us to more precisely convey
whether we want to iterate over the common prefix (`zip`), or expect all
lengths to be the same (`zip_equal`).
Reviewed By: dcaballe, antiagainst
Differential Revision: https://reviews.llvm.org/D139022
This helper handles non trivial cases of broadcast + optional transpose creation
that should not leak to the outside world.
Differential Revision: https://reviews.llvm.org/D139003
Fold InsertStridedOp(ConstantOp into ConstantOp) -> ConstantOp.
This pattern comes with vector size threshold to make sure we do not
introduce too many large constants.
This help clean up code created by the Wide Integer Emulation pass.
Reviewed By: antiagainst
Differential Revision: https://reviews.llvm.org/D138739
This revision fixes a bug in the vector.extract folding that was missing
handling the "dim-1" broadcasting case in vector.broadcast.
Differential Revision: https://reviews.llvm.org/D138804
This pattern comes with vector size threshold to make sure we do not
introduce too many large constants.
This help clean up code created by the Wide Integer Emulation pass.
Reviewed By: dcaballe
Differential Revision: https://reviews.llvm.org/D138733
This allows us to better canonicalize/clean-up code created by the Wide
Integer Emulation pass.
Reviewed By: antiagainst
Differential Revision: https://reviews.llvm.org/D138606
This generalizes the existing fold for `ExtractOp(non-splat constant)`
to work with vector results. The vector case is handled by extracting
the subrange of attribute array.
My main use it to clean up code generated by the Wide Integer Emulation
pass.
Reviewed By: antiagainst
Differential Revision: https://reviews.llvm.org/D138690
Masking hasn't been widely used in vector transfer ops and the semantics
of the mask operand were a bit loose. This patch states that the mask
operand in a vector transfer op is applied to the read/write part of the
operation and, therefore, its shape should match the shape of the
elements read/written from/into the memref/tensor regardless of any
permutation/broadcasting also applied by the transfer operation.
Reviewers: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D138079
Those methods were added long time ago. Now we get the same methods generated by tablegen, so there is no need for duplicates.
Differential Revision: https://reviews.llvm.org/D137544
This MaskingOpInterface provides masking cababilitites to those
operations that implement it. For only is only implemented by the `vector.mask`
operation and it's used to break the dependency between the Vector
dialect (where the `vector.mask` op lives) and operations implementing
the MaskableOpInterface.
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D136734
The foldMemRefCast method is defined in memref namespace; the
foldTensorCast method is defined in tensor namespace. This revision
deletes the dup code and use the unified methods.
Reviewed By: dcaballe
Differential Revision: https://reviews.llvm.org/D136379
This patch introduces the `vector.mask` operation and the MaskableOpInterface
as described in https://discourse.llvm.org/t/rfc-vector-masking-representation-in-mlir/64964.
The `vector.mask` operation is used to predicate the execution of operations
implementing the MaskableOpInterface. This interface will be implemented by maskable
operations and provides information about its masking constraints and semantics.
For now, only vector transfer and reduction ops implement the MaskableOpInterface
for illustration and testing purposes.
Reviewed By: nicolasvasilache, rriddle
Differential Revision: https://reviews.llvm.org/D134939
In https://reviews.llvm.org/D133883, we changed the
`FoldExtractSliceIntoTransferRead` pattern from requiring
full identity map to minor identity map. This effectively
allows rank reducing `vector.transfer_read` ops. However,
the logic for checking `tensor.extract_slice` rank reducing
still looks at the vector rank, which now could be smaller
than the `tensor.extract_slice`'s output tensor rank.
It ends up we can have incorrect index cacluation after
folding due to this double rank reducing behavior.
Reviewed By: ThomasRaoux
Differential Revision: https://reviews.llvm.org/D134984
vecotr.transfer_read ops with minor identity indexing map is rank
reducing, with implicit leading unit dimensions. This should be
a natural extension to support in addition to full identity indexing
maps.
Reviewed By: ThomasRaoux
Differential Revision: https://reviews.llvm.org/D133883
Add a new pattern to fold `vector.extract` over n-D constants that extract scalars.
The previous code handled ND splat constants only. The new pattern is conservative and does handle sub-vector constants.
This is to aid the `arith::EmulateWideInt` pass which emits a lot of 2-element vector constants.
Reviewed By: Mogball, dcaballe
Differential Revision: https://reviews.llvm.org/D133742
This patch fixes a couple of warnings by switching to has_value/value:
mlir/lib/Dialect/Vector/IR/VectorOps.cpp:529:28: error: 'hasValue'
is deprecated: Use has_value
instead. [-Werror,-Wdeprecated-declarations]
mlir/lib/Dialect/Vector/IR/VectorOps.cpp:533:48: error: 'getValue'
is deprecated: Use value
instead. [-Werror,-Wdeprecated-declarations]
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
CombiningKind was implemented before EnumAttr, so it reimplements the same behaviour with the custom code. Except for a few places, EnumAttr is a drop-in replacement.
Reviewed By: nicolasvasilache, pifon2a
Differential Revision: https://reviews.llvm.org/D133343
Currently vector.gather only supports reading memory into a 1-D result vector.
This patch extends it to support an n-D result vector with the indices, masks,
and passthroughs in n-D vectors.
As we are trying to vectorize tensor.extract with vector.gather
(https://github.com/iree-org/iree/issues/9198), it will need to gather the
elements into an n-D vector. Having vector.gather with n-D results allows us
to avoid flatten and reshape at the vectorization stage. The backends can then
decide the optimal ways to lower the vector.gather op.
Note that this is different from n-D gathering, which is about reading n-D
memory with the n-D indices. The indices here are still only 1-D offsets on
the base.
Reviewed By: dcaballe
Differential Revision: https://reviews.llvm.org/D131905
This commit adds support for 0-D vectors in ReductionOp.
Reviewed By: nicolasvasilache, dcaballe
Differential Revision: https://reviews.llvm.org/D131896
Confined -> ConfinedAttr
AllAttrConstraintsOf -> AllOfAttr
To be in line with ConfinedType and AllOfType.
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D131822
This reland includes changes to the Python bindings.
Switch variadic operand and result segment size attributes to use the
dense i32 array. Dense integer arrays were introduced primarily to
represent index lists. They are a better fit for segment sizes than
dense elements attrs.
Depends on D131801
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D131803
