[Mlir-commits] [mlir] [mlir][tensor][NFC] Fix typos of `tensor.gather` (PR #106888)

[llvmlistbot at llvm.org]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-mlir-tensor

Author: Longsheng Mou (CoTinker)

<details>
<summary>Changes</summary>

This patch fix typos in description of `tensor.gather`.

---
Full diff: https://github.com/llvm/llvm-project/pull/106888.diff


1 Files Affected:

- (modified) mlir/include/mlir/Dialect/Tensor/IR/TensorOps.td (+6-6) 


``````````diff
diff --git a/mlir/include/mlir/Dialect/Tensor/IR/TensorOps.td b/mlir/include/mlir/Dialect/Tensor/IR/TensorOps.td
index cafc3d91fd1e9d..e06dc646036fb7 100644
--- a/mlir/include/mlir/Dialect/Tensor/IR/TensorOps.td
+++ b/mlir/include/mlir/Dialect/Tensor/IR/TensorOps.td
@@ -624,9 +624,9 @@ def Tensor_GatherOp : Tensor_Op<"gather", [
         // element (i.e. 0-D subset) at the coordinates triple in %source.
         //
         %out = tensor.gather %source[%indices] gather_dims([0, 1, 2]) :
-          (tensor<4x4x4xf32>, tensor<1x2x 3xindex>) -> tensor<1x2x 1x1x1xf32>
+          (tensor<4x4x4xf32>, tensor<1x2x3xindex>) -> tensor<1x2x1x1x1xf32>
 
-        // Note: result type may be further rank-reduced to tensor<1x2x f32>.
+        // Note: result type may be further rank-reduced to tensor<1x2xf32>.
     ```
 
     A slice variant is provided to allow specifying whole slices of the source
@@ -640,9 +640,9 @@ def Tensor_GatherOp : Tensor_Op<"gather", [
         // corresponding to the `gather_dims` attribute specified by %indices.
         //
         %out = tensor.gather %source[%indices] gather_dims([1]) :
-          (tensor<3x4x5xf32>, tensor<6x7x 1xindex>) -> tensor<6x7x 3x1x5xf32>
+          (tensor<3x4x5xf32>, tensor<6x7x1xindex>) -> tensor<6x7x3x1x5xf32>
 
-        // Note: result type may be further rank-reduced to tensor<6x7x 3x5xf32>.
+        // Note: result type may be further rank-reduced to tensor<6x7x3x5xf32>.
     ```
 
     The dimensions specified in the gather_dims attribute are ones for which the
@@ -682,12 +682,12 @@ def Tensor_GatherOp : Tensor_Op<"gather", [
         // memref<?x4x1xf32> is a contiguous buffer of ?x4x1 elements.
         // gather from random source slices must copy to the contiguous output.
         %out = memref.gather %source[%indices] gather_dims([1]) :
-          (memref<4x4xf32>, memref<?x 1xindex>) -> memref<?x 4x1xf32>
+          (memref<4x4xf32>, memref<?x1xindex>) -> memref<?x4x1xf32>
 
         // Nested buffer support would allow gather to directly index into the
         // source buffer (i.e. represent a jagged view into the source).
         %out = memref.gather %source[%indices] gather_dims([1]) :
-          (memref<4x4xf32>, memref<?x 1xindex>) -> memref<? x memref<4x1xf32>>
+          (memref<4x4xf32>, memref<?x1xindex>) -> memref<?x memref<4x1xf32>>
     ```
   }];
 

``````````

</details>


https://github.com/llvm/llvm-project/pull/106888