Skip to content

[mlir][docs] Fix typos in documentation for MLIR tensor dialect #119095

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Dec 7, 2024
Merged

[mlir][docs] Fix typos in documentation for MLIR tensor dialect #119095

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ae03534
[mlir][docs] Fix tensor.dim documentation referencing memref type
e3m3 Dec 7, 2024
b20f299
[mlir][docs] Fix tensor dialect documentation typos for ops
e3m3 Dec 7, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions mlir/include/mlir/Dialect/Tensor/IR/TensorOps.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -213,11 +213,11 @@ def Tensor_DimOp : Tensor_Op<"dim", [

// Return the dynamic dimension of %A.
%c1 = arith.constant 1 : index
%y = tensor.dim %A, %c1 : memref<4x?xf32>
%y = tensor.dim %A, %c1 : tensor<4x?xf32>

// Equivalent generic form:
%x = "tensor.dim"(%A, %c0) : (memref<4x?xf32>, index) -> index
%y = "tensor.dim"(%A, %c1) : (memref<4x?xf32>, index) -> index
%x = "tensor.dim"(%A, %c0) : (tensor<4x?xf32>, index) -> index
%y = "tensor.dim"(%A, %c1) : (tensor<4x?xf32>, index) -> index
```
}];

Expand Down Expand Up @@ -673,7 +673,7 @@ def Tensor_GatherOp : Tensor_Op<"gather", [

At the tensor-level, the index tensor is specified in an AoS form (i.e.
coordinate tuple is the most minor). It is the responsibility of further
lowerings and bufferiation to implement various concrete layouts.
lowerings and bufferization to implement various concrete layouts.

Note: As currently specified, the operation must lower to an abstraction that
performs copies to the output tensor. This is because the buffer type system
Expand Down Expand Up @@ -710,7 +710,7 @@ def Tensor_GatherOp : Tensor_Op<"gather", [

let extraClassDeclaration = [{
// TODO: InferTypeOpInterface once enough confidence is built with
// tensor<tensor> and its lwoering to memref<memref>.
// tensor<tensor> and its lowering to memref<memref>.
static RankedTensorType inferResultType(RankedTensorType sourceType,
RankedTensorType indicesType,
ArrayRef<int64_t> gatherDims,
Expand Down Expand Up @@ -1673,7 +1673,7 @@ def Tensor_ScatterOp : Tensor_Op<"scatter", [
source tensor has size `1`.
I.e. if the dest type is `axbxcxd` and the coordinates are [1, 3], then
the source type suffix is `ax1xcx1`.
Sactter also allows rank-reducing semantics where the shape `ax1xcx1` can be
Scatter also allows rank-reducing semantics where the shape `ax1xcx1` can be
further simplified to `axc`.

The elemental type of the indices tensor can be any integer type.
Expand All @@ -1693,7 +1693,7 @@ def Tensor_ScatterOp : Tensor_Op<"scatter", [

At the tensor-level, the index tensor is specified in an AoS form (i.e.
coordinate tuple is the most minor). It is the responsibility of further
lowerings and bufferiation to implement various concrete layouts.
lowerings and bufferization to implement various concrete layouts.

Note: As currently specified, the operation must lower to an abstraction that
performs copies to the output tensor. This is because the buffer type system
Expand Down Expand Up @@ -2115,7 +2115,7 @@ def Tensor_UnPackOp : Tensor_RelayoutOp<"unpack"> {
/// Check if this UnPackOp is like a simple unpad operation.
/// In other words, this operation:
/// 1. drops useless dimensions (dimension of size 1), and
/// 2. reduces dimensions in place (i.e., no tranpose.)
/// 2. reduces dimensions in place (i.e., no transpose.)
bool isLikeUnPad();
}];

Expand Down
Loading