diff --git a/mlir/lib/Dialect/Vector/Transforms/VectorTransferSplitRewritePatterns.cpp b/mlir/lib/Dialect/Vector/Transforms/VectorTransferSplitRewritePatterns.cpp
--- a/mlir/lib/Dialect/Vector/Transforms/VectorTransferSplitRewritePatterns.cpp
+++ b/mlir/lib/Dialect/Vector/Transforms/VectorTransferSplitRewritePatterns.cpp
@@ -441,8 +441,17 @@
 
 // TODO: Parallelism and threadlocal considerations with a ParallelScope trait.
 static Operation *getAutomaticAllocationScope(Operation *op) {
-  Operation *scope =
-      op->getParentWithTrait<OpTrait::AutomaticAllocationScope>();
+  // Find the closest surrounding allocation scope that is not a known looping
+  // construct (putting alloca's in loops doesn't always lower to deallocation
+  // until the end of the loop).
+  Operation *scope = nullptr;
+  for (Operation *parent = op->getParentOp(); parent != nullptr;
+       parent = parent->getParentOp()) {
+    if (parent->hasTrait<OpTrait::AutomaticAllocationScope>())
+      scope = parent;
+    if (!isa<scf::ForOp, AffineForOp>(parent))
+      break;
+  }
   assert(scope && "Expected op to be inside automatic allocation scope");
   return scope;
 }
diff --git a/mlir/test/Dialect/Vector/vector-transfer-full-partial-split.mlir b/mlir/test/Dialect/Vector/vector-transfer-full-partial-split.mlir
--- a/mlir/test/Dialect/Vector/vector-transfer-full-partial-split.mlir
+++ b/mlir/test/Dialect/Vector/vector-transfer-full-partial-split.mlir
@@ -412,3 +412,23 @@
   }
   return %token : !async.token
 }
+
+// -----
+
+func.func private @fake_side_effecting_fun(%0: vector<2x2xf32>) -> ()
+
+// Ensure that `alloca`s are inserted outside of loops even though loops are
+// consdered allocation scopes.
+// CHECK-LABEL: transfer_read_within_scf_for
+func.func @transfer_read_within_scf_for(%A : memref<?x?xf32>, %lb : index, %ub : index, %step : index) {
+  %c0 = arith.constant 0 : index
+  %f0 = arith.constant 0.0 : f32
+  // CHECK: alloca
+  // CHECK: scf.for
+  // CHECK-NOT: alloca
+  scf.for %i = %lb to %ub step %step {
+    %0 = vector.transfer_read %A[%c0, %c0], %f0 : memref<?x?xf32>, vector<2x2xf32>
+    func.call @fake_side_effecting_fun(%0) : (vector<2x2xf32>) -> ()
+  }
+  return
+}