diff --git a/test/Transforms/SLPVectorizer/X86/horizontal-list.ll b/test/Transforms/SLPVectorizer/X86/horizontal-list.ll
new file mode 100644
index 00000000000..ce20b45753c
--- /dev/null
+++ b/test/Transforms/SLPVectorizer/X86/horizontal-list.ll
@@ -0,0 +1,290 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -slp-vectorizer -slp-vectorize-hor -slp-vectorize-hor-store -S < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=bdver2 | FileCheck %s
+
+@n = external local_unnamed_addr global i32, align 4
+@arr = common local_unnamed_addr global [20 x float] zeroinitializer, align 16
+@arr1 = common local_unnamed_addr global [20 x float] zeroinitializer, align 16
+@res = external local_unnamed_addr global float, align 4
+
+define float @baz() {
+; CHECK-LABEL: @baz(
+; CHECK:         [[TMP0:%.*]] = load i32, i32* @n, align 4
+; CHECK-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP0]], 3
+; CHECK-NEXT:    [[CONV:%.*]] = sitofp i32 [[MUL]] to float
+; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 0), align 16
+; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 0), align 16
+; CHECK-NEXT:    [[MUL4:%.*]] = fmul fast float [[TMP2]], [[TMP1]]
+; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[MUL4]], [[CONV]]
+; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 1), align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 1), align 4
+; CHECK-NEXT:    [[MUL4_1:%.*]] = fmul fast float [[TMP4]], [[TMP3]]
+; CHECK-NEXT:    [[ADD_1:%.*]] = fadd fast float [[MUL4_1]], [[ADD]]
+; CHECK-NEXT:    [[TMP5:%.*]] = load <2 x float>, <2 x float>* bitcast (float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 2) to <2 x float>*), align 8
+; CHECK-NEXT:    [[TMP6:%.*]] = load <2 x float>, <2 x float>* bitcast (float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 2) to <2 x float>*), align 8
+; CHECK-NEXT:    [[TMP7:%.*]] = fmul fast <2 x float> [[TMP6]], [[TMP5]]
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x float> [[TMP7]], i32 0
+; CHECK-NEXT:    [[ADD_2:%.*]] = fadd fast float [[TMP8]], [[ADD_1]]
+; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <2 x float> [[TMP7]], i32 1
+; CHECK-NEXT:    [[ADD_3:%.*]] = fadd fast float [[TMP9]], [[ADD_2]]
+; CHECK-NEXT:    [[ADD7:%.*]] = fadd fast float [[ADD_3]], [[CONV]]
+; CHECK-NEXT:    [[ADD19:%.*]] = fadd fast float [[MUL4]], [[ADD7]]
+; CHECK-NEXT:    [[ADD19_1:%.*]] = fadd fast float [[MUL4_1]], [[ADD19]]
+; CHECK-NEXT:    [[ADD19_2:%.*]] = fadd fast float [[TMP8]], [[ADD19_1]]
+; CHECK-NEXT:    [[ADD19_3:%.*]] = fadd fast float [[TMP9]], [[ADD19_2]]
+; CHECK-NEXT:    store float [[ADD19_3]], float* @res, align 4
+; CHECK-NEXT:    ret float [[ADD19_3]]
+;
+entry:
+  %0 = load i32, i32* @n, align 4
+  %mul = mul nsw i32 %0, 3
+  %conv = sitofp i32 %mul to float
+  %1 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 0), align 16
+  %2 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 0), align 16
+  %mul4 = fmul fast float %2, %1
+  %add = fadd fast float %mul4, %conv
+  %3 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 1), align 4
+  %4 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 1), align 4
+  %mul4.1 = fmul fast float %4, %3
+  %add.1 = fadd fast float %mul4.1, %add
+  %5 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 2), align 8
+  %6 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 2), align 8
+  %mul4.2 = fmul fast float %6, %5
+  %add.2 = fadd fast float %mul4.2, %add.1
+  %7 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 3), align 4
+  %8 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 3), align 4
+  %mul4.3 = fmul fast float %8, %7
+  %add.3 = fadd fast float %mul4.3, %add.2
+  %add7 = fadd fast float %add.3, %conv
+  %add19 = fadd fast float %mul4, %add7
+  %add19.1 = fadd fast float %mul4.1, %add19
+  %add19.2 = fadd fast float %mul4.2, %add19.1
+  %add19.3 = fadd fast float %mul4.3, %add19.2
+  store float %add19.3, float* @res, align 4
+  ret float %add19.3
+}
+
+define float @bazz() {
+; CHECK-LABEL: @bazz(
+; CHECK:         [[TMP0:%.*]] = load i32, i32* @n, align 4
+; CHECK-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP0]], 3
+; CHECK-NEXT:    [[CONV:%.*]] = sitofp i32 [[MUL]] to float
+; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 0), align 16
+; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 0), align 16
+; CHECK-NEXT:    [[MUL4:%.*]] = fmul fast float [[TMP2]], [[TMP1]]
+; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[MUL4]], [[CONV]]
+; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 1), align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 1), align 4
+; CHECK-NEXT:    [[MUL4_1:%.*]] = fmul fast float [[TMP4]], [[TMP3]]
+; CHECK-NEXT:    [[ADD_1:%.*]] = fadd fast float [[MUL4_1]], [[ADD]]
+; CHECK-NEXT:    [[TMP5:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 2), align 8
+; CHECK-NEXT:    [[TMP6:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 2), align 8
+; CHECK-NEXT:    [[MUL4_2:%.*]] = fmul fast float [[TMP6]], [[TMP5]]
+; CHECK-NEXT:    [[ADD_2:%.*]] = fadd fast float [[MUL4_2]], [[ADD_1]]
+; CHECK-NEXT:    [[TMP7:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 3), align 4
+; CHECK-NEXT:    [[TMP8:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 3), align 4
+; CHECK-NEXT:    [[MUL4_3:%.*]] = fmul fast float [[TMP8]], [[TMP7]]
+; CHECK-NEXT:    [[ADD_3:%.*]] = fadd fast float [[MUL4_3]], [[ADD_2]]
+; CHECK-NEXT:    [[MUL5:%.*]] = shl nsw i32 [[TMP0]], 2
+; CHECK-NEXT:    [[CONV6:%.*]] = sitofp i32 [[MUL5]] to float
+; CHECK-NEXT:    [[ADD7:%.*]] = fadd fast float [[ADD_3]], [[CONV6]]
+; CHECK-NEXT:    [[TMP9:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 4), align 16
+; CHECK-NEXT:    [[TMP10:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 4), align 16
+; CHECK-NEXT:    [[MUL18:%.*]] = fmul fast float [[TMP10]], [[TMP9]]
+; CHECK-NEXT:    [[ADD19:%.*]] = fadd fast float [[MUL18]], [[ADD7]]
+; CHECK-NEXT:    [[TMP11:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 5), align 4
+; CHECK-NEXT:    [[TMP12:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 5), align 4
+; CHECK-NEXT:    [[MUL18_1:%.*]] = fmul fast float [[TMP12]], [[TMP11]]
+; CHECK-NEXT:    [[ADD19_1:%.*]] = fadd fast float [[MUL18_1]], [[ADD19]]
+; CHECK-NEXT:    [[TMP13:%.*]] = load <2 x float>, <2 x float>* bitcast (float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 6) to <2 x float>*), align 8
+; CHECK-NEXT:    [[TMP14:%.*]] = load <2 x float>, <2 x float>* bitcast (float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 6) to <2 x float>*), align 8
+; CHECK-NEXT:    [[TMP15:%.*]] = fmul fast <2 x float> [[TMP14]], [[TMP13]]
+; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <2 x float> [[TMP15]], i32 0
+; CHECK-NEXT:    [[ADD19_2:%.*]] = fadd fast float [[TMP16]], [[ADD19_1]]
+; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <2 x float> [[TMP15]], i32 1
+; CHECK-NEXT:    [[ADD19_3:%.*]] = fadd fast float [[TMP17]], [[ADD19_2]]
+; CHECK-NEXT:    store float [[ADD19_3]], float* @res, align 4
+; CHECK-NEXT:    ret float [[ADD19_3]]
+;
+entry:
+  %0 = load i32, i32* @n, align 4
+  %mul = mul nsw i32 %0, 3
+  %conv = sitofp i32 %mul to float
+  %1 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 0), align 16
+  %2 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 0), align 16
+  %mul4 = fmul fast float %2, %1
+  %add = fadd fast float %mul4, %conv
+  %3 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 1), align 4
+  %4 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 1), align 4
+  %mul4.1 = fmul fast float %4, %3
+  %add.1 = fadd fast float %mul4.1, %add
+  %5 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 2), align 8
+  %6 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 2), align 8
+  %mul4.2 = fmul fast float %6, %5
+  %add.2 = fadd fast float %mul4.2, %add.1
+  %7 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 3), align 4
+  %8 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 3), align 4
+  %mul4.3 = fmul fast float %8, %7
+  %add.3 = fadd fast float %mul4.3, %add.2
+  %mul5 = shl nsw i32 %0, 2
+  %conv6 = sitofp i32 %mul5 to float
+  %add7 = fadd fast float %add.3, %conv6
+  %9 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 4), align 16
+  %10 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 4), align 16
+  %mul18 = fmul fast float %10, %9
+  %add19 = fadd fast float %mul18, %add7
+  %11 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 5), align 4
+  %12 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 5), align 4
+  %mul18.1 = fmul fast float %12, %11
+  %add19.1 = fadd fast float %mul18.1, %add19
+  %13 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 6), align 8
+  %14 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 6), align 8
+  %mul18.2 = fmul fast float %14, %13
+  %add19.2 = fadd fast float %mul18.2, %add19.1
+  %15 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 7), align 4
+  %16 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 7), align 4
+  %mul18.3 = fmul fast float %16, %15
+  %add19.3 = fadd fast float %mul18.3, %add19.2
+  store float %add19.3, float* @res, align 4
+  ret float %add19.3
+}
+
+define float @bazzz() {
+; CHECK-LABEL: @bazzz(
+; CHECK:         [[TMP0:%.*]] = load i32, i32* @n, align 4
+; CHECK-NEXT:    [[CONV:%.*]] = sitofp i32 [[TMP0]] to float
+; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 0), align 16
+; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 0), align 16
+; CHECK-NEXT:    [[MUL:%.*]] = fmul fast float [[TMP2]], [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 1), align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 1), align 4
+; CHECK-NEXT:    [[MUL_1:%.*]] = fmul fast float [[TMP4]], [[TMP3]]
+; CHECK-NEXT:    [[TMP5:%.*]] = fadd fast float [[MUL_1]], [[MUL]]
+; CHECK-NEXT:    [[TMP6:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 2), align 8
+; CHECK-NEXT:    [[TMP7:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 2), align 8
+; CHECK-NEXT:    [[MUL_2:%.*]] = fmul fast float [[TMP7]], [[TMP6]]
+; CHECK-NEXT:    [[TMP8:%.*]] = fadd fast float [[MUL_2]], [[TMP5]]
+; CHECK-NEXT:    [[TMP9:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 3), align 4
+; CHECK-NEXT:    [[TMP10:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 3), align 4
+; CHECK-NEXT:    [[MUL_3:%.*]] = fmul fast float [[TMP10]], [[TMP9]]
+; CHECK-NEXT:    [[TMP11:%.*]] = fadd fast float [[MUL_3]], [[TMP8]]
+; CHECK-NEXT:    [[TMP12:%.*]] = fmul fast float [[CONV]], [[TMP11]]
+; CHECK-NEXT:    store float [[TMP12]], float* @res, align 4
+; CHECK-NEXT:    ret float [[TMP12]]
+;
+entry:
+  %0 = load i32, i32* @n, align 4
+  %conv = sitofp i32 %0 to float
+  %1 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 0), align 16
+  %2 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 0), align 16
+  %mul = fmul fast float %2, %1
+  %3 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 1), align 4
+  %4 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 1), align 4
+  %mul.1 = fmul fast float %4, %3
+  %5 = fadd fast float %mul.1, %mul
+  %6 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 2), align 8
+  %7 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 2), align 8
+  %mul.2 = fmul fast float %7, %6
+  %8 = fadd fast float %mul.2, %5
+  %9 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 3), align 4
+  %10 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 3), align 4
+  %mul.3 = fmul fast float %10, %9
+  %11 = fadd fast float %mul.3, %8
+  %12 = fmul fast float %conv, %11
+  store float %12, float* @res, align 4
+  ret float %12
+}
+
+define i32 @foo() {
+; CHECK-LABEL: @foo(
+; CHECK:         [[TMP0:%.*]] = load i32, i32* @n, align 4
+; CHECK-NEXT:    [[CONV:%.*]] = sitofp i32 [[TMP0]] to float
+; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 0), align 16
+; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 0), align 16
+; CHECK-NEXT:    [[MUL:%.*]] = fmul fast float [[TMP2]], [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 1), align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 1), align 4
+; CHECK-NEXT:    [[MUL_1:%.*]] = fmul fast float [[TMP4]], [[TMP3]]
+; CHECK-NEXT:    [[TMP5:%.*]] = fadd fast float [[MUL_1]], [[MUL]]
+; CHECK-NEXT:    [[TMP6:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 2), align 8
+; CHECK-NEXT:    [[TMP7:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 2), align 8
+; CHECK-NEXT:    [[MUL_2:%.*]] = fmul fast float [[TMP7]], [[TMP6]]
+; CHECK-NEXT:    [[TMP8:%.*]] = fadd fast float [[MUL_2]], [[TMP5]]
+; CHECK-NEXT:    [[TMP9:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 3), align 4
+; CHECK-NEXT:    [[TMP10:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 3), align 4
+; CHECK-NEXT:    [[MUL_3:%.*]] = fmul fast float [[TMP10]], [[TMP9]]
+; CHECK-NEXT:    [[TMP11:%.*]] = fadd fast float [[MUL_3]], [[TMP8]]
+; CHECK-NEXT:    [[TMP12:%.*]] = fmul fast float [[CONV]], [[TMP11]]
+; CHECK-NEXT:    [[CONV4:%.*]] = fptosi float [[TMP12]] to i32
+; CHECK-NEXT:    store i32 [[CONV4]], i32* @n, align 4
+; CHECK-NEXT:    ret i32 [[CONV4]]
+;
+entry:
+  %0 = load i32, i32* @n, align 4
+  %conv = sitofp i32 %0 to float
+  %1 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 0), align 16
+  %2 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 0), align 16
+  %mul = fmul fast float %2, %1
+  %3 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 1), align 4
+  %4 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 1), align 4
+  %mul.1 = fmul fast float %4, %3
+  %5 = fadd fast float %mul.1, %mul
+  %6 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 2), align 8
+  %7 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 2), align 8
+  %mul.2 = fmul fast float %7, %6
+  %8 = fadd fast float %mul.2, %5
+  %9 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 3), align 4
+  %10 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 3), align 4
+  %mul.3 = fmul fast float %10, %9
+  %11 = fadd fast float %mul.3, %8
+  %12 = fmul fast float %conv, %11
+  %conv4 = fptosi float %12 to i32
+  store i32 %conv4, i32* @n, align 4
+  ret i32 %conv4
+}
+
+define float @bar() {
+; CHECK-LABEL: @bar(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <2 x float>, <2 x float>* bitcast ([20 x float]* @arr to <2 x float>*), align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x float>, <2 x float>* bitcast ([20 x float]* @arr1 to <2 x float>*), align 16
+; CHECK-NEXT:    [[TMP2:%.*]] = fmul fast <2 x float> [[TMP1]], [[TMP0]]
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x float> [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x float> [[TMP2]], i32 1
+; CHECK-NEXT:    [[CMP4:%.*]] = fcmp fast ogt float [[TMP3]], [[TMP4]]
+; CHECK-NEXT:    [[MAX_0_MUL3:%.*]] = select i1 [[CMP4]], float [[TMP3]], float [[TMP4]]
+; CHECK-NEXT:    [[TMP5:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 2), align 8
+; CHECK-NEXT:    [[TMP6:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 2), align 8
+; CHECK-NEXT:    [[MUL3_1:%.*]] = fmul fast float [[TMP6]], [[TMP5]]
+; CHECK-NEXT:    [[CMP4_1:%.*]] = fcmp fast ogt float [[MAX_0_MUL3]], [[MUL3_1]]
+; CHECK-NEXT:    [[MAX_0_MUL3_1:%.*]] = select i1 [[CMP4_1]], float [[MAX_0_MUL3]], float [[MUL3_1]]
+; CHECK-NEXT:    [[TMP7:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 3), align 4
+; CHECK-NEXT:    [[TMP8:%.*]] = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 3), align 4
+; CHECK-NEXT:    [[MUL3_2:%.*]] = fmul fast float [[TMP8]], [[TMP7]]
+; CHECK-NEXT:    [[CMP4_2:%.*]] = fcmp fast ogt float [[MAX_0_MUL3_1]], [[MUL3_2]]
+; CHECK-NEXT:    [[MAX_0_MUL3_2:%.*]] = select i1 [[CMP4_2]], float [[MAX_0_MUL3_1]], float [[MUL3_2]]
+; CHECK-NEXT:    store float [[MAX_0_MUL3_2]], float* @res, align 4
+; CHECK-NEXT:    ret float [[MAX_0_MUL3_2]]
+;
+entry:
+  %0 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 0), align 16
+  %1 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 0), align 16
+  %mul = fmul fast float %1, %0
+  %2 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 1), align 4
+  %3 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 1), align 4
+  %mul3 = fmul fast float %3, %2
+  %cmp4 = fcmp fast ogt float %mul, %mul3
+  %max.0.mul3 = select i1 %cmp4, float %mul, float %mul3
+  %4 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 2), align 8
+  %5 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 2), align 8
+  %mul3.1 = fmul fast float %5, %4
+  %cmp4.1 = fcmp fast ogt float %max.0.mul3, %mul3.1
+  %max.0.mul3.1 = select i1 %cmp4.1, float %max.0.mul3, float %mul3.1
+  %6 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr, i64 0, i64 3), align 4
+  %7 = load float, float* getelementptr inbounds ([20 x float], [20 x float]* @arr1, i64 0, i64 3), align 4
+  %mul3.2 = fmul fast float %7, %6
+  %cmp4.2 = fcmp fast ogt float %max.0.mul3.1, %mul3.2
+  %max.0.mul3.2 = select i1 %cmp4.2, float %max.0.mul3.1, float %mul3.2
+  store float %max.0.mul3.2, float* @res, align 4
+  ret float %max.0.mul3.2
+}
+