[Mlir-commits] [mlir] [mlir][tensor][sparse] don't drop encoding when infer result type (PR #91817)

[llvmlistbot at llvm.org]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-mlir-tensor

@llvm/pr-subscribers-mlir

Author: Peiming Liu (PeimingLiu)

<details>
<summary>Changes</summary>

A general question is: is it possible to support hooks here to infer the encoding? E.g., when the extracted tensor slice is rank-reduced, the encoding need to be updated accordingly as well.

---
Full diff: https://github.com/llvm/llvm-project/pull/91817.diff


1 Files Affected:

- (modified) mlir/lib/Dialect/Tensor/IR/TensorOps.cpp (+2-1) 


``````````diff
diff --git a/mlir/lib/Dialect/Tensor/IR/TensorOps.cpp b/mlir/lib/Dialect/Tensor/IR/TensorOps.cpp
index 1f94397e823f7..e41d59a0e0b94 100644
--- a/mlir/lib/Dialect/Tensor/IR/TensorOps.cpp
+++ b/mlir/lib/Dialect/Tensor/IR/TensorOps.cpp
@@ -2020,7 +2020,8 @@ RankedTensorType ExtractSliceOp::inferResultType(
   assert(static_cast<int64_t>(staticSizes.size()) ==
              sourceTensorType.getRank() &&
          "unexpected staticSizes not equal to rank of source");
-  return RankedTensorType::get(staticSizes, sourceTensorType.getElementType());
+  return RankedTensorType::get(staticSizes, sourceTensorType.getElementType(),
+                               sourceTensorType.getEncoding());
 }
 
 RankedTensorType ExtractSliceOp::inferResultType(

``````````

</details>


https://github.com/llvm/llvm-project/pull/91817