[Mlir-commits] [mlir] [mlir][Vector] Update patterns for flattening vector.xfer Ops (1/N) (PR #73522)
Benjamin Maxwell
llvmlistbot at llvm.org
Tue Nov 28 07:10:06 PST 2023
================
@@ -487,26 +487,88 @@ class TransferWriteDropUnitDimsPattern
} // namespace
-/// Return true if the memref type has its inner dimension matching the given
-/// shape. Otherwise return false.
-static int64_t hasMatchingInnerContigousShape(MemRefType memrefType,
- ArrayRef<int64_t> targetShape) {
- auto shape = memrefType.getShape();
- SmallVector<int64_t> strides;
+/// Return true if `vectorType` is a contiguous slice of `memrefType`.
+///
+/// Compares `vectorType` against the trailing dimensions of `memrefType`
+/// to check whether `vectorType` is a contiguous slice of `memrefType`. This
+/// is implemented by iterating over the dims of `vectorType` and `memrefType`
+/// and comparing them starting from the inner-most/right-most dims.
+///
+/// Note that there might be some restriction on the leading dim of
+/// `VectorType`:
+/// 1. if all the trialing dims of `vectorType` match the trailing dims
----------------
MacDue wrote:
```suggestion
/// 1. if all the trailing dims of `vectorType` match the trailing dims
```
https://github.com/llvm/llvm-project/pull/73522
More information about the Mlir-commits
mailing list