[Mlir-commits] [mlir] [mlir][vector] Generalize multi_reduction innerparallel unrolling to N dimensions (PR #182301)

Erick Ochoa Lopez llvmlistbot at llvm.org
Thu Feb 19 07:51:23 PST 2026


================
@@ -494,7 +494,7 @@ struct UnrollMultiReductionInnerParallelBaseCase
         masks[i] = vector::ExtractOp::create(rewriter, loc, mask, i);
 
     Value result = multiReductionOp.getAcc();
-    for (auto [innerVector, innerMask] : llvm::zip(vectors, masks))
----------------
amd-eochoalo wrote:

https://github.com/llvm/llvm-project/pull/178974#discussion_r2785574187

> Can we use zip_equals?

https://github.com/llvm/llvm-project/pull/182301


More information about the Mlir-commits mailing list