diff --git a/llvm/test/Transforms/LoopVectorize/vplan-vectorize-inner-loop-reduction.ll b/llvm/test/Transforms/LoopVectorize/vplan-vectorize-inner-loop-reduction.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/vplan-vectorize-inner-loop-reduction.ll
@@ -0,0 +1,55 @@
+; RUN: opt -loop-vectorize -force-vector-width=4 -enable-vplan-native-path -S %s | FileCheck %s
+
+; Vectorize explict marked outer loop using vplan native path. Inner loop
+; contains simple double add reduction. IR is compiled and modified by hand
+; from following C code:
+; void inner_loop_reduction(const double* restrict in_a, const double* restrict in_b, double* restrict out)
+; {
+;     #pragma clang loop vectorize(enable)
+;     for (int i = 0; i < 1000; ++i) {
+;         double a = in_a[i];
+;         double b = in_b[i];
+;         for (int j = 0; j < 10000; ++j) {
+;             a = a + b;
+;         }
+;         out[i] = a;
+;     }
+; }
+define void @inner_loop_reduction(double* noalias nocapture readonly %a.in, double* noalias nocapture readonly %b.in, double* noalias nocapture %c.out) {
+; CHECK-LABEL: @inner_loop_reduction(
+; CHECK: fadd <4 x double>
+; CHECK: add nuw nsw <4 x i32>
+; CHECK: icmp eq <4 x i32>
+; CHECK: "llvm.loop.isvectorized", i32 1
+entry:
+  br label %for1.header
+
+for1.header:                                              ; preds = %entry
+  %indvar1 = phi i64 [ 0, %entry ], [ %indvar11, %for1.latch ]
+  %a.ptr = getelementptr inbounds double, double* %a.in, i64 %indvar1
+  %a = load double, double* %a.ptr, align 8
+  %b.ptr = getelementptr inbounds double, double* %b.in, i64 %indvar1
+  %b = load double, double* %b.ptr, align 8
+  br label %for2.header
+
+for2.header:                                              ; preds = %for1.header, %for2.header
+  %indvar2 = phi i32 [ 0, %for1.header ], [ %indvar21, %for2.header ]
+  %a.reduction = phi double [ %a, %for1.header ], [ %a.reduction1, %for2.header ]
+  %a.reduction1 = fadd double %b, %a.reduction
+  %indvar21 = add nuw nsw i32 %indvar2, 1
+  %for2.cond = icmp eq i32 %indvar21, 10000
+  br i1 %for2.cond, label %for1.latch, label %for2.header
+
+for1.latch:                                               ; preds = %for2.header
+  %c.ptr = getelementptr inbounds double, double* %c.out, i64 %indvar1
+  store double %a.reduction1, double* %c.ptr, align 8
+  %indvar11 = add nuw nsw i64 %indvar1, 1
+  %for1.cond = icmp eq i64 %indvar11, 1000
+  br i1 %for1.cond, label %exit, label %for1.header, !llvm.loop !0
+
+exit:                                                    ; preds = %for1.latch
+  ret void
+}
+
+!0 = distinct !{!0, !1}
+!1 = !{!"llvm.loop.vectorize.enable", i1 true}