after introducing the IndexedGenericOp to GenericOp canonicalization (https://reviews.llvm.org/D101612).

Differential Revision: https://reviews.llvm.org/D102235

These two patterns allow for more efficient codegen in VectorToSCF.

Differential Revision: https://reviews.llvm.org/D102222

Such ops are no-ops and are folded to their respective `source`/`vector` operand.

Differential Revision: https://reviews.llvm.org/D101879

Broadcast dimensions of a vector transfer op have no corresponding dimension in the mask vector. E.g., a 2-D TransferReadOp, where one dimension is a broadcast, can have a 1-D `mask` attribute.

This commit also adds a few additional transfer op integration tests for various combinations of broadcasts, masking, dim transposes, etc.

Differential Revision: https://reviews.llvm.org/D101745

This reverts commit c9087788.

Accidentally pushed old version of the commit.

Broadcast dimensions of a vector transfer op have no corresponding dimension in the mask vector. E.g., a 2-D TransferReadOp, where one dimension is a broadcast, can have a 1-D `mask` attribute.

This commit also adds a few additional transfer op integration tests for various combinations of broadcasts, masking, dim transposes, etc.

Differential Revision: https://reviews.llvm.org/D101745

Rank-0 case causes a graph during linalg reshape operation.

Differential Revision: https://reviews.llvm.org/D102282

The current static checker for linalg does not work on the decreasing
index cases well. So, this is to Update the current static bound checker
for linalg to cover decreasing index cases.

Reviewed By: hanchung

Differential Revision: https://reviews.llvm.org/D102302

Reviewed By: bixia

Differential Revision: https://reviews.llvm.org/D102285

Add a conversion pass to convert higher-level type before translation.
This conversion extract meangingful information and pack it into a struct that
the translation (D101504) will be able to understand.

Reviewed By: ftynse

Differential Revision: https://reviews.llvm.org/D102170

after introducing the IndexedGenericOp to GenericOp canonicalization (https://reviews.llvm.org/D101612).

Differential Revision: https://reviews.llvm.org/D102245

after introducing the IndexedGenericOp to GenericOp canonicalization (https://reviews.llvm.org/D101612).

Differential Revision: https://reviews.llvm.org/D102308

First step in adding alignment as an attribute to MLIR global definitions. Alignment can be specified for global objects in LLVM IR. It can also be specified as a named attribute in the LLVMIR dialect of MLIR. However, this attribute has no standing and is discarded during translation from MLIR to LLVM IR. This patch does two things: First, it adds the attribute to the syntax of the llvm.mlir.global operation, and by doing this it also adds accessors and verifications. The syntax is "align=XX" (with XX being an integer), placed right after the value of the operation. Second, it allows transforming this operation to and from LLVM IR. It is checked whether the value is an integer power of 2.

Reviewed By: ftynse, mehdi_amini

Differential Revision: https://reviews.llvm.org/D101492

This is actually necessary for correctness, as memref.reinterpret_cast
doesn't verify if the output shape doesn't match the static sizes.

Differential Revision: https://reviews.llvm.org/D102232

Switch llvm.noalias attribute from a boolean attribute to a unit
attribute.

Differential Revision: https://reviews.llvm.org/D102225

VectorTransfer split previously only split read xfer ops. This adds
the same logic to write ops. The resulting code involves 2
conditionals for write ops while read ops only needed 1, but the created
ops are built upon the same patterns, so pattern matching/expectations
are all consistent other than in regards to the if/else ops.

Differential Revision: https://reviews.llvm.org/D102157

after introducing the IndexedGenericOp to GenericOp canonicalization (https://reviews.llvm.org/D101612).

Differential Revision: https://reviews.llvm.org/D102187

after introducing the IndexedGenericOp to GenericOp canonicalization (https://reviews.llvm.org/D101612).

Differential Revision: https://reviews.llvm.org/D102174

after introducing the IndexedGenericOp to GenericOp canonicalization (https://reviews.llvm.org/D101612).

Differential Revision: https://reviews.llvm.org/D102176

All glue and clutter in the linalg ops has been replaced by proper
sparse tensor type encoding. This code is no longer needed. Thanks
to ntv@ for giving us a temporary home in linalg.

So long, and thanks for all the fish.

Reviewed By: bixia

Differential Revision: https://reviews.llvm.org/D102098

This trivially folds into a constant when all operands are constant.

Differential Revision: https://reviews.llvm.org/D102199

A very elaborate, but also very fun revision because all
puzzle pieces are finally "falling in place".

1. replaces lingalg annotations + flags with proper sparse tensor types
2. add rigorous verification on sparse tensor type and sparse primitives
3. removes glue and clutter on opaque pointers in favor of sparse tensor types
4. migrates all tests to use sparse tensor types

NOTE: next CL will remove *all* obsoleted sparse code in Linalg

Reviewed By: bixia

Differential Revision: https://reviews.llvm.org/D102095

According to the API contract, LinalgLoopDistributionOptions
expects to work on parallel iterators. When getting processor
information, only loop ranges for parallel dimensions should
be fed in. But right now after generating scf.for loop nests,
we feed in *all* loops, including the ones materialized for
reduction iterators. This can cause unexpected distribution
of reduction dimensions. This commit fixes it.

Reviewed By: mravishankar

Differential Revision: https://reviews.llvm.org/D102079

In the buffer deallocation pass, unranked memref types are not properly supported.
After investigating this issue, it turns out that the Clone and Dealloc operation
does not support unranked memref types in the current implementation.
This patch adds the missing feature and enables the transformation of any memref
type.

This patch solves this bug: https://bugs.llvm.org/show_bug.cgi?id=48385

Differential Revision: https://reviews.llvm.org/D101760

As a canonicalization, infer the resulting shape rank if possible.

Differential Revision: https://reviews.llvm.org/D102068

The current design uses a unique entry for each argument/result attribute, with the name of the entry being something like "arg0". This provides for a somewhat sparse design, but ends up being much more expensive (from a runtime perspective) in-practice. The design requires building a string every time we lookup the dictionary for a specific arg/result, and also requires N attribute lookups when collecting all of the arg/result attribute dictionaries.

This revision restructures the design to instead have an ArrayAttr that contains all of the attribute dictionaries for arguments and another for results. This design reduces the number of attribute name lookups to 1, and allows for O(1) lookup for individual element dictionaries. The major downside is that we can end up with larger memory usage, as the ArrayAttr contains an entry for each element even if that element has no attributes. If the memory usage becomes too problematic, we can experiment with a more sparse structure that still provides a lot of the wins in this revision.

This dropped the compilation time of a somewhat large TensorFlow model from ~650 seconds to ~400 seconds.

Differential Revision: https://reviews.llvm.org/D102035

Previous change caused another warning in some build configuration:
"default label in switch which covers all enumeration values"

Differential Revision: https://reviews.llvm.org/D102091

Differential Revision: https://reviews.llvm.org/D102088

Differential Revision: https://reviews.llvm.org/D102089

Differential Revision: https://reviews.llvm.org/D102034

Remove the builder signature taking a signed dimension identifier.

Reviewed By: ergawy

Differential Revision: https://reviews.llvm.org/D102055

Replace all `linalg.indexed_generic` ops by `linalg.generic` ops that access the iteration indices using the `linalg.index` op.

Differential Revision: https://reviews.llvm.org/D101612

The pattern to convert subtensor ops to their rank-reduced versions
(by dropping unit-dims in the result) can also convert to a zero-rank
tensor. Handle that case.
This also fixes a OOB access bug in the existing pattern for such
cases.

Differential Revision: https://reviews.llvm.org/D101949

Reviewed By: rriddle

Differential Revision: https://reviews.llvm.org/D102009

This expose a lambda control instead of just a boolean to control unit
dimension folding.
This however gives more control to user to pick a good heuristic.
Folding reshapes helps fusion opportunities but may generate sub-optimal
generic ops.

Differential Revision: https://reviews.llvm.org/D101917

Differential Revision: https://reviews.llvm.org/D101955