[mlir][tensor] Fix bug in insert_slice canonical. with tensor encoding

[last5bits]

Previously, InsertSliceOpSourceCastInserter was incorrectly applied to a case when tensor types have an encoding attribute attached to them. The type newSrcType was missing that attribute from the old srcType, which made the expression srcType == newSrcType false, since tensor<2x2xf32, "foo"> is not equal to tensor<2x2xf32>. That lead to an endless back and forth between InsertSliceOpSourceCastInserter that would introduce a cast and InsertSliceOpCastFolder that would remove it right after.

[github-actions]

Thank you for submitting a Pull Request (PR) to the LLVM Project!

This PR will be automatically labeled and the relevant teams will be
notified.

If you wish to, you can add reviewers by using the "Reviewers" section on this page.

If this is not working for you, it is probably because you do not have write
permissions for the repository. In which case you can instead tag reviewers by
name in a comment by using @ followed by their GitHub username.

If you have received no comments on your PR for a week, you can request a review
by "ping"ing the PR by adding a comment “Ping”. The common courtesy "ping" rate
is once a week. Please remember that you are asking for valuable time from other developers.

If you have further questions, they may be answered by the LLVM GitHub User Guide.

You can also ask questions in a comment on this PR, on the LLVM Discord or on the forums.

[llvmbot]

@llvm/pr-subscribers-mlir-tensor

@llvm/pr-subscribers-mlir

Author: Alexey Z. (last5bits)

Changes

Previously, InsertSliceOpSourceCastInserter was incorrectly applied to a case when tensor types have an encoding attribute attached to them. The type newSrcType was missing that attribute from the old srcType, which made the expression srcType == newSrcType false, since tensor<2x2xf32, "foo"> is not equal to tensor<2x2xf32>. That lead to an endless back and forth between InsertSliceOpSourceCastInserter that would introduce a cast and InsertSliceOpCastFolder that would remove it right after.

---

Full diff: https://github.com/llvm/llvm-project/pull/81045.diff

2 Files Affected:

• (modified) mlir/lib/Dialect/Tensor/IR/TensorOps.cpp (+2-2)
• (modified) mlir/test/Dialect/Tensor/canonicalize.mlir (+18)

diff --git a/mlir/lib/Dialect/Tensor/IR/TensorOps.cpp b/mlir/lib/Dialect/Tensor/IR/TensorOps.cpp
index b21e89ae3a5713..8298cf102e28a3 100644
--- a/mlir/lib/Dialect/Tensor/IR/TensorOps.cpp
+++ b/mlir/lib/Dialect/Tensor/IR/TensorOps.cpp
@@ -2663,8 +2663,8 @@ struct InsertSliceOpSourceCastInserter final
     if (!hasValidSizesOffsets(newSrcShape))
       return failure();
 
-    RankedTensorType newSrcType =
-        RankedTensorType::get(newSrcShape, srcType.getElementType());
+    RankedTensorType newSrcType = RankedTensorType::get(
+        newSrcShape, srcType.getElementType(), srcType.getEncoding());
     if (srcType == newSrcType ||
         !preservesStaticInformation(srcType, newSrcType) ||
         !tensor::CastOp::areCastCompatible(srcType, newSrcType))
diff --git a/mlir/test/Dialect/Tensor/canonicalize.mlir b/mlir/test/Dialect/Tensor/canonicalize.mlir
index 7192a719ceb13d..90c715bf2eb2da 100644
--- a/mlir/test/Dialect/Tensor/canonicalize.mlir
+++ b/mlir/test/Dialect/Tensor/canonicalize.mlir
@@ -555,6 +555,24 @@ func.func @insert_slice_canonicalize(%arg0 : tensor<?x?x?xf32>, %arg1 : index,
 
 // -----
 
+// Do not insert a cast for the following example. The new source type wouldn't be "more static" than the old one.
+func.func @insert_slice_canonicalize_encoding(%arg0 : tensor<2x2xf32, "foo">,
+                                              %arg1 : tensor<4x4xf32, "foo">) -> tensor<4x4xf32, "foo">
+{
+  %0 = tensor.insert_slice %arg0 into %arg1[0, 0] [2, 2] [1, 1] : tensor<2x2xf32, "foo"> into tensor<4x4xf32, "foo">
+  return %0 : tensor<4x4xf32, "foo">
+}
+// CHECK-LABEL: func @insert_slice_canonicalize_encoding
+//  CHECK-SAME:     %[[ARG0:[a-zA-Z0-9_]+]]: tensor<2x2xf32, "foo">
+//  CHECK-SAME:     %[[ARG1:[a-zA-Z0-9_]+]]: tensor<4x4xf32, "foo">
+//       CHECK-NOT: tensor.cast
+//       CHECK:   %[[RESULT:.+]] = tensor.insert_slice %[[ARG0]] into %[[ARG1]]
+//  CHECK-SAME:      [0, 0] [2, 2] [1, 1]
+//  CHECK-SAME:      : tensor<2x2xf32, "foo"> into tensor<4x4xf32, "foo">
+//       CHECK:   return %[[RESULT]]
+
+// -----
+
 func.func @slice_to_insert_slice_canonicalize(%arg0 : tensor<?x?x?xf32>, %arg1 : index,
     %arg2 : index, %arg3 : tensor<?x?x?xf32>) -> tensor<?x?x?xf32>
 {

[github-actions]

@last5bits Congratulations on having your first Pull Request (PR) merged into the LLVM Project!

Your changes will be combined with recent changes from other authors, then tested
by our build bots. If there is a problem with a build, you may recieve a report in an email or a comment on this PR.

Please check whether problems have been caused by your change specifically, as
the builds can include changes from many authors. It is not uncommon for your
change to be included in a build that fails due to someone else's changes, or
infrastructure issues.

How to do this, and the rest of the post-merge process, is covered in detail here.

If your change does cause a problem, it may be reverted, or you can revert it yourself.
This is a normal part of LLVM development. You can fix your changes and open a new PR to merge them again.

If you don't get any reports, no action is required from you. Your changes are working as expected, well done!