We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 746412a commit fdfc873Copy full SHA for fdfc873
mlir/include/mlir/Conversion/Passes.td
@@ -1454,7 +1454,9 @@ def ConvertVectorToLLVMPass : Pass<"convert-vector-to-llvm"> {
1454
"operations instead of the alignment of the element type of the "
1455
"memref. This flag is intended for use with hardware which requires"
1456
"vector alignment, or in application contexts where it is known all "
1457
- "vector access are naturally aligned. ">,
+ "vector access are naturally aligned. If operations have an "
1458
+ "alignment attribute set, the alignment attribute takes priority "
1459
+ "over this option ">,
1460
Option<"amx", "enable-amx",
1461
"bool", /*default=*/"false",
1462
"Enables the use of AMX dialect while lowering the vector "
0 commit comments