[Mlir-commits] [mlir] [Affine] Parallelize loops with MemoryEffects::Free ops. (PR #172388)

Mehdi Amini llvmlistbot at llvm.org
Fri Dec 19 03:20:14 PST 2025


================
@@ -152,6 +171,7 @@ bool mlir::affine::isLoopMemoryParallel(AffineForOp forOp) {
         loadAndStoreOps.push_back(op);
     } else if (!isa<AffineForOp, AffineYieldOp, AffineIfOp>(op) &&
                !hasSingleEffect<MemoryEffects::Allocate>(op) &&
+               !isDeallocationOfLocallyDefined(op, forOp) &&
----------------
joker-eph wrote:

What do you mean by "this semantics"? 


https://github.com/llvm/llvm-project/pull/172388


More information about the Mlir-commits mailing list