colin
/
mlir-hlo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

PR #41662: NFC - minor spelling tweaks 

Imported from GitHub PR https://github.com/tensorflow/tensorflow/pull/41662

This PR addresses minor spelling tweaks in documents
Copybara import of the project:

--
b806191a117990a479944b40ec7a4b79843287a2 by Kazuaki Ishizaki <ishizaki@jp.ibm.com>:

fix trivial typo

COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/tensorflow/pull/41662 from kiszk:spelling_tweaks_docs b806191a117990a479944b40ec7a4b79843287a2
PiperOrigin-RevId: 322955351
This commit is contained in:
Kazuaki Ishizaki 2020-07-24 01:30:44 -07:00 committed by TensorFlow MLIR Team
parent 8f262ae8f5
commit 882468da13
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
include/mlir-hlo/Dialect/mhlo/IR/infer_fusibility_op_interface.td
View File

@ -140,7 +140,7 @@ def InferFusibilityOpInterface : OpInterface<"InferFusibilityOpInterface"> {
Here the effective workload shape roughly represents the maximum Here the effective workload shape roughly represents the maximum
parallelism can be used during the codegen stage. It's used to check parallelism can be used during the codegen stage. It's used to check
the shape-compatibility of the operation. During fusion, we only the shape-compatibility of the operation. During fusion, we only
try to fuse shape-compatible ops for performace. try to fuse shape-compatible ops for performance.
For example, the effective workload shape of an elementwise op is its For example, the effective workload shape of an elementwise op is its
output shape, while the effective workload shape of a reduction op may output shape, while the effective workload shape of a reduction op may
be its operand shape. be its operand shape.