diff --git a/llvm/test/Transforms/LoopVectorize/vplan-vectorize-inner-loop-reduction.ll b/llvm/test/Transforms/LoopVectorize/vplan-vectorize-inner-loop-reduction.ll
--- a/llvm/test/Transforms/LoopVectorize/vplan-vectorize-inner-loop-reduction.ll
+++ b/llvm/test/Transforms/LoopVectorize/vplan-vectorize-inner-loop-reduction.ll
@@ -17,10 +17,37 @@
 ; }
 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
+
+; CHECK: vector.body:
+; CHECK-NEXT: %[[FOR1_INDEX:.*]] = phi i64 [ 0, %[[LABEL_PR:.*]] ], [ %{{.*}}, %[[LABEL_FOR1_LATCH:.*]] ]
+; CHECK: %[[VEC_INDEX:.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, %[[LABEL_PR]] ], [ %{{.*}}, %[[LABEL_FOR1_LATCH]] ]
+; CHECK-NEXT: %[[A_PTR:.*]] = getelementptr inbounds double, double* %a.in, <4 x i64> %[[VEC_INDEX]]
+; CHECK-NEXT: %[[MASKED_GATHER1:.*]] = call <4 x double> @[[LLVM_INTRINSIC:.*]](<4 x double*> %[[A_PTR]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x double> undef)
+; CHECK-NEXT: %[[B_PTR:.*]] = getelementptr inbounds double, double* %b.in, <4 x i64> %[[VEC_INDEX]]
+; CHECK-NEXT: %[[MASKED_GATHER2:.*]] = call <4 x double> @[[LLVM_INTRINSIC]](<4 x double*> %[[B_PTR]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x double> undef)
+; CHECK-NEXT: br label %[[FOR2_HEADER:.*]]
+
+; CHECK: [[FOR2_HEADER]]:
+; CHECK-NEXT: %[[FOR2_INDEX:.*]] = phi <4 x i32> [ %[[FOR2_INDEX_NEXT:.*]], %[[FOR2_HEADER]] ], [ zeroinitializer, %vector.body ]
+; CHECK-NEXT: %[[REDUCTION:.*]] = phi <4 x double> [ %[[REDUCTION_NEXT:.*]], %[[FOR2_HEADER]] ], [ %[[MASKED_GATHER1]], %vector.body ]
+; CHECK-NEXT: %[[REDUCTION_NEXT]] = fadd <4 x double> %[[MASKED_GATHER2]], %[[REDUCTION]]
+; CHECK-NEXT: %[[FOR2_INDEX_NEXT]] = add nuw nsw <4 x i32> %[[FOR2_INDEX]], <i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT: %[[VEC_PTR:.*]] = icmp eq <4 x i32> %[[FOR2_INDEX_NEXT]], <i32 10000, i32 10000, i32 10000, i32 10000>
+; CHECK-NEXT: %[[EXIT_COND:.*]] = extractelement <4 x i1> %[[VEC_PTR]], i32 0
+; CHECK-NEXT: br i1 %[[EXIT_COND]], label %[[FOR1_LATCH:.*]], label %{{.*}}
+
+; CHECK: [[FOR1_LATCH]]:
+; CHECK-NEXT: %[[REDUCTION:.*]] = phi <4 x double> [ %[[REDUCTION_NEXT]], %[[FOR2_HEADER]] ]
+; CHECK-NEXT: %[[C_PTR:.*]] = getelementptr inbounds double, double* %c.out, <4 x i64> %[[VEC_INDEX]]
+; CHECK-NEXT: call void @{{.*}}(<4 x double> %[[REDUCTION]], <4 x double*> %[[C_PTR]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
+; CHECK-NEXT: %[[VEC_INDEX_NEXT:.*]] = add nuw nsw <4 x i64> %[[VEC_INDEX]], <i64 1, i64 1, i64 1, i64 1>
+; CHECK-NEXT: %[[VEC_PTR:.*]] = icmp eq <4 x i64> %[[VEC_INDEX_NEXT]], <i64 1000, i64 1000, i64 1000, i64 1000>
+; CHECK-NEXT: %{{.*}} = extractelement <4 x i1> %[[VEC_PTR]], i32 0
+; CHECK-NEXT: %[[FOR1_INDEX_NEXT:.*]] = add i64 %[[FOR1_INDEX]], 4
+; CHECK-NEXT: %{{.*}} = add <4 x i64> %[[VEC_INDEX]], <i64 4, i64 4, i64 4, i64 4>
+; CHECK-NEXT: %[[EXIT_COND:.*]] = icmp eq i64 %[[FOR1_INDEX_NEXT]], 1000
+; CHECK-NEXT: br i1 %[[EXIT_COND]], label %{{.*}}, label %vector.body
+
 entry:
   br label %for1.header