[Mlir-commits] [mlir] [[mlir][linalg] Infer reduction-neutral padding values in rewriteAsPaddedOp (PR #216517)

Andrzej WarzyƄski llvmlistbot at llvm.org
Fri Sep 11 00:27:09 PDT 2026


================
@@ -263,6 +266,142 @@ static Value padOperand(OpBuilder &builder, TilingInterface opToPad,
                                paddingValue, /*nofold=*/false, dynDims);
 }
 
+/// Returns true if `operand` is indexed along at least one reduction dimension
+/// of `linalgOp`
+static bool isReducedOperand(linalg::LinalgOp linalgOp, OpOperand *operand,
+                             ArrayRef<utils::IteratorType> iterTypes) {
+  AffineMap map = linalgOp.getMatchingIndexingMap(operand);
+  return llvm::any_of(llvm::enumerate(iterTypes), [&](auto it) {
+    return it.value() == utils::IteratorType::reduction &&
+           map.isFunctionOfDim(it.index());
+  });
+}
+
+/// Set `paddingValues` with the padding value of every input of `contractOp`
+/// that is indexed along a reduction dimension. Fails if the pair admits no
+/// padding value.
+static LogicalResult
+setContractionPaddingValues(OpBuilder &builder, linalg::LinalgOp contractOp,
+                            Operation *mul, Operation *add,
+                            ArrayRef<utils::IteratorType> iterTypes,
+                            MutableArrayRef<Attribute> paddingValues) {
----------------
banach-space wrote:

With interface like this, what's the intended relation between `contractOp` and `mul` + `add`? IMHO, those ops should be extracted in this method to avoid confusion.

https://github.com/llvm/llvm-project/pull/216517


More information about the Mlir-commits mailing list