Skip to content

Commit fe85566

Browse files
authored
[mlir][vector][docs] Fix broken markdown link (#101813)
The link has been "broken" since #73792 that updated "## DeeperDive" to "## LLVM Lowering Tradeoffs". This patch fixes the MD link for the affected sub-section: * Before: [deeper dive section](#DeeperDive) * After: [LLVM Lowering Tradeoffs](#llvm-lowering-tradeoffs) I've also rephrased the surrounding comment a bit - to better match the updated section name.
1 parent f231d3d commit fe85566

File tree

1 file changed

+7
-6
lines changed

1 file changed

+7
-6
lines changed

mlir/docs/Dialects/Vector.md

Lines changed: 7 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -73,12 +73,13 @@ following top-down rewrites and conversions:
7373

7474
### LLVM level
7575

76-
On CPU, the `n-D` `vector` type currently lowers to `!llvm<array<vector>>`. More
77-
concretely, `vector<4x8x128xf32>` lowers to `!llvm<[4 x [ 8 x [ 128 x float
78-
]]]>`. There are tradeoffs involved related to how one can access subvectors and
79-
how one uses `llvm.extractelement`, `llvm.insertelement` and
80-
`llvm.shufflevector`. A [deeper dive section](#DeeperDive) discusses the current
81-
lowering choices and tradeoffs.
76+
On CPU, the `n-D` `vector` type currently lowers to `!llvm<array<vector>>`.
77+
More concretely, `vector<4x8x128xf32>` lowers to `!llvm<[4 x [ 8 x [ 128 x
78+
float ]]]>`. There are tradeoffs involved related to how one can access
79+
subvectors and how one uses `llvm.extractelement`, `llvm.insertelement` and
80+
`llvm.shufflevector`. The section on [LLVM Lowering
81+
Tradeoffs](#llvm-lowering-tradeoffs) offers a deeper dive into the current
82+
design choices and tradeoffs.
8283

8384
### Hardware Vector Ops
8485

0 commit comments

Comments
 (0)