diff --git a/test/Transforms/SLPVectorizer/X86/vect_copyable_in_binops.ll b/test/Transforms/SLPVectorizer/X86/vect_copyable_in_binops.ll
new file mode 100644
index 00000000000..2b593b78652
--- /dev/null
+++ b/test/Transforms/SLPVectorizer/X86/vect_copyable_in_binops.ll
@@ -0,0 +1,984 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -slp-vectorizer -S -mtriple=x86_64-unknown-linux-gnu -mcpu=bdver2 < %s | FileCheck %s
+
+define void @add0(i32* noalias %dst, i32* noalias %src) {
+; CHECK-LABEL: @add0(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[SRC]] to <4 x i32>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = add nsw <4 x i32> <i32 1, i32 1, i32 2, i32 3>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[DST]] to <4 x i32>*
+; CHECK-NEXT:    store <4 x i32> [[TMP2]], <4 x i32>* [[TMP3]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds i32, i32* %src, i64 1
+  %0 = load i32, i32* %src, align 4
+  %add = add nsw i32 %0, 1
+  %incdec.ptr1 = getelementptr inbounds i32, i32* %dst, i64 1
+  store i32 %add, i32* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds i32, i32* %src, i64 2
+  %1 = load i32, i32* %incdec.ptr, align 4
+  %add3 = add nsw i32 %1, 1
+  %incdec.ptr4 = getelementptr inbounds i32, i32* %dst, i64 2
+  store i32 %add3, i32* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds i32, i32* %src, i64 3
+  %2 = load i32, i32* %incdec.ptr2, align 4
+  %add6 = add nsw i32 %2, 2
+  %incdec.ptr7 = getelementptr inbounds i32, i32* %dst, i64 3
+  store i32 %add6, i32* %incdec.ptr4, align 4
+  %3 = load i32, i32* %incdec.ptr5, align 4
+  %add9 = add nsw i32 %3, 3
+  store i32 %add9, i32* %incdec.ptr7, align 4
+  ret void
+}
+
+define void @add1(i32* noalias %dst, i32* noalias %src) {
+; CHECK-LABEL: @add1(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[SRC]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
+; CHECK-NEXT:    store i32 [[TMP0]], i32* [[DST]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[INCDEC_PTR]], align 4
+; CHECK-NEXT:    [[ADD3:%.*]] = add nsw i32 [[TMP1]], 1
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
+; CHECK-NEXT:    store i32 [[ADD3]], i32* [[INCDEC_PTR1]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
+; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[INCDEC_PTR2]], align 4
+; CHECK-NEXT:    [[ADD6:%.*]] = add nsw i32 [[TMP2]], 2
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
+; CHECK-NEXT:    store i32 [[ADD6]], i32* [[INCDEC_PTR4]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[INCDEC_PTR5]], align 4
+; CHECK-NEXT:    [[ADD9:%.*]] = add nsw i32 [[TMP3]], 3
+; CHECK-NEXT:    store i32 [[ADD9]], i32* [[INCDEC_PTR7]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds i32, i32* %src, i64 1
+  %0 = load i32, i32* %src, align 4
+  %incdec.ptr1 = getelementptr inbounds i32, i32* %dst, i64 1
+  store i32 %0, i32* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds i32, i32* %src, i64 2
+  %1 = load i32, i32* %incdec.ptr, align 4
+  %add3 = add nsw i32 %1, 1
+  %incdec.ptr4 = getelementptr inbounds i32, i32* %dst, i64 2
+  store i32 %add3, i32* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds i32, i32* %src, i64 3
+  %2 = load i32, i32* %incdec.ptr2, align 4
+  %add6 = add nsw i32 %2, 2
+  %incdec.ptr7 = getelementptr inbounds i32, i32* %dst, i64 3
+  store i32 %add6, i32* %incdec.ptr4, align 4
+  %3 = load i32, i32* %incdec.ptr5, align 4
+  %add9 = add nsw i32 %3, 3
+  store i32 %add9, i32* %incdec.ptr7, align 4
+  ret void
+}
+
+define void @sub0(i32* noalias %dst, i32* noalias %src) {
+; CHECK-LABEL: @sub0(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[SRC]], align 4
+; CHECK-NEXT:    [[SUB:%.*]] = add nsw i32 [[TMP0]], -1
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
+; CHECK-NEXT:    store i32 [[SUB]], i32* [[DST]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[INCDEC_PTR]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
+; CHECK-NEXT:    store i32 [[TMP1]], i32* [[INCDEC_PTR1]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
+; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[INCDEC_PTR2]], align 4
+; CHECK-NEXT:    [[SUB5:%.*]] = add nsw i32 [[TMP2]], -2
+; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
+; CHECK-NEXT:    store i32 [[SUB5]], i32* [[INCDEC_PTR3]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[INCDEC_PTR4]], align 4
+; CHECK-NEXT:    [[SUB8:%.*]] = add nsw i32 [[TMP3]], -3
+; CHECK-NEXT:    store i32 [[SUB8]], i32* [[INCDEC_PTR6]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds i32, i32* %src, i64 1
+  %0 = load i32, i32* %src, align 4
+  %sub = add nsw i32 %0, -1
+  %incdec.ptr1 = getelementptr inbounds i32, i32* %dst, i64 1
+  store i32 %sub, i32* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds i32, i32* %src, i64 2
+  %1 = load i32, i32* %incdec.ptr, align 4
+  %incdec.ptr3 = getelementptr inbounds i32, i32* %dst, i64 2
+  store i32 %1, i32* %incdec.ptr1, align 4
+  %incdec.ptr4 = getelementptr inbounds i32, i32* %src, i64 3
+  %2 = load i32, i32* %incdec.ptr2, align 4
+  %sub5 = add nsw i32 %2, -2
+  %incdec.ptr6 = getelementptr inbounds i32, i32* %dst, i64 3
+  store i32 %sub5, i32* %incdec.ptr3, align 4
+  %3 = load i32, i32* %incdec.ptr4, align 4
+  %sub8 = add nsw i32 %3, -3
+  store i32 %sub8, i32* %incdec.ptr6, align 4
+  ret void
+}
+
+define void @sub1(i32* noalias %dst, i32* noalias %src) {
+; CHECK-LABEL: @sub1(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
+; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[SRC]] to <4 x i32>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = add nsw <4 x i32> <i32 4, i32 -1, i32 -2, i32 -3>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[DST]] to <4 x i32>*
+; CHECK-NEXT:    store <4 x i32> [[TMP2]], <4 x i32>* [[TMP3]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds i32, i32* %src, i64 1
+  %0 = load i32, i32* %src, align 4
+  %add = add nsw i32 %0, 4
+  %incdec.ptr1 = getelementptr inbounds i32, i32* %dst, i64 1
+  store i32 %add, i32* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds i32, i32* %src, i64 2
+  %1 = load i32, i32* %incdec.ptr, align 4
+  %sub = add nsw i32 %1, -1
+  %incdec.ptr3 = getelementptr inbounds i32, i32* %dst, i64 2
+  store i32 %sub, i32* %incdec.ptr1, align 4
+  %incdec.ptr4 = getelementptr inbounds i32, i32* %src, i64 3
+  %2 = load i32, i32* %incdec.ptr2, align 4
+  %sub5 = add nsw i32 %2, -2
+  %incdec.ptr6 = getelementptr inbounds i32, i32* %dst, i64 3
+  store i32 %sub5, i32* %incdec.ptr3, align 4
+  %3 = load i32, i32* %incdec.ptr4, align 4
+  %sub8 = add nsw i32 %3, -3
+  store i32 %sub8, i32* %incdec.ptr6, align 4
+  ret void
+}
+
+define void @sub2(i32* noalias %dst, i32* noalias %src) {
+; CHECK-LABEL: @sub2(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[SRC]] to <4 x i32>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = add nsw <4 x i32> <i32 -1, i32 -1, i32 -2, i32 -3>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[DST]] to <4 x i32>*
+; CHECK-NEXT:    store <4 x i32> [[TMP2]], <4 x i32>* [[TMP3]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds i32, i32* %src, i64 1
+  %0 = load i32, i32* %src, align 4
+  %sub = add nsw i32 %0, -1
+  %incdec.ptr1 = getelementptr inbounds i32, i32* %dst, i64 1
+  store i32 %sub, i32* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds i32, i32* %src, i64 2
+  %1 = load i32, i32* %incdec.ptr, align 4
+  %sub3 = add nsw i32 %1, -1
+  %incdec.ptr4 = getelementptr inbounds i32, i32* %dst, i64 2
+  store i32 %sub3, i32* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds i32, i32* %src, i64 3
+  %2 = load i32, i32* %incdec.ptr2, align 4
+  %sub6 = add nsw i32 %2, -2
+  %incdec.ptr7 = getelementptr inbounds i32, i32* %dst, i64 3
+  store i32 %sub6, i32* %incdec.ptr4, align 4
+  %3 = load i32, i32* %incdec.ptr5, align 4
+  %sub9 = add nsw i32 %3, -3
+  store i32 %sub9, i32* %incdec.ptr7, align 4
+  ret void
+}
+
+define void @addsub0(i32* noalias %dst, i32* noalias %src) {
+; CHECK-LABEL: @addsub0(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[SRC]], align 4
+; CHECK-NEXT:    [[SUB:%.*]] = add nsw i32 [[TMP0]], -1
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
+; CHECK-NEXT:    store i32 [[SUB]], i32* [[DST]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[INCDEC_PTR]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
+; CHECK-NEXT:    store i32 [[TMP1]], i32* [[INCDEC_PTR1]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
+; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[INCDEC_PTR2]], align 4
+; CHECK-NEXT:    [[SUB5:%.*]] = add nsw i32 [[TMP2]], -2
+; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
+; CHECK-NEXT:    store i32 [[SUB5]], i32* [[INCDEC_PTR3]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[INCDEC_PTR4]], align 4
+; CHECK-NEXT:    [[SUB8:%.*]] = sub nsw i32 [[TMP3]], -3
+; CHECK-NEXT:    store i32 [[SUB8]], i32* [[INCDEC_PTR6]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds i32, i32* %src, i64 1
+  %0 = load i32, i32* %src, align 4
+  %sub = add nsw i32 %0, -1
+  %incdec.ptr1 = getelementptr inbounds i32, i32* %dst, i64 1
+  store i32 %sub, i32* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds i32, i32* %src, i64 2
+  %1 = load i32, i32* %incdec.ptr, align 4
+  %incdec.ptr3 = getelementptr inbounds i32, i32* %dst, i64 2
+  store i32 %1, i32* %incdec.ptr1, align 4
+  %incdec.ptr4 = getelementptr inbounds i32, i32* %src, i64 3
+  %2 = load i32, i32* %incdec.ptr2, align 4
+  %sub5 = add nsw i32 %2, -2
+  %incdec.ptr6 = getelementptr inbounds i32, i32* %dst, i64 3
+  store i32 %sub5, i32* %incdec.ptr3, align 4
+  %3 = load i32, i32* %incdec.ptr4, align 4
+  %sub8 = sub nsw i32 %3, -3
+  store i32 %sub8, i32* %incdec.ptr6, align 4
+  ret void
+}
+
+define void @addsub1(i32* noalias %dst, i32* noalias %src) {
+; CHECK-LABEL: @addsub1(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[SRC]], align 4
+; CHECK-NEXT:    [[SUB:%.*]] = add nsw i32 [[TMP0]], -1
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
+; CHECK-NEXT:    store i32 [[SUB]], i32* [[DST]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[INCDEC_PTR]], align 4
+; CHECK-NEXT:    [[SUB1:%.*]] = sub nsw i32 [[TMP1]], -1
+; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
+; CHECK-NEXT:    store i32 [[SUB1]], i32* [[INCDEC_PTR1]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
+; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[INCDEC_PTR2]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
+; CHECK-NEXT:    store i32 [[TMP2]], i32* [[INCDEC_PTR3]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[INCDEC_PTR4]], align 4
+; CHECK-NEXT:    [[SUB8:%.*]] = sub nsw i32 [[TMP3]], -3
+; CHECK-NEXT:    store i32 [[SUB8]], i32* [[INCDEC_PTR6]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds i32, i32* %src, i64 1
+  %0 = load i32, i32* %src, align 4
+  %sub = add nsw i32 %0, -1
+  %incdec.ptr1 = getelementptr inbounds i32, i32* %dst, i64 1
+  store i32 %sub, i32* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds i32, i32* %src, i64 2
+  %1 = load i32, i32* %incdec.ptr, align 4
+  %sub1 = sub nsw i32 %1, -1
+  %incdec.ptr3 = getelementptr inbounds i32, i32* %dst, i64 2
+  store i32 %sub1, i32* %incdec.ptr1, align 4
+  %incdec.ptr4 = getelementptr inbounds i32, i32* %src, i64 3
+  %2 = load i32, i32* %incdec.ptr2, align 4
+  %incdec.ptr6 = getelementptr inbounds i32, i32* %dst, i64 3
+  store i32 %2, i32* %incdec.ptr3, align 4
+  %3 = load i32, i32* %incdec.ptr4, align 4
+  %sub8 = sub nsw i32 %3, -3
+  store i32 %sub8, i32* %incdec.ptr6, align 4
+  ret void
+}
+
+define void @mul(i32* noalias %dst, i32* noalias %src) {
+; CHECK-LABEL: @mul(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[SRC]], align 4
+; CHECK-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP0]], 257
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
+; CHECK-NEXT:    store i32 [[MUL]], i32* [[DST]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[INCDEC_PTR]], align 4
+; CHECK-NEXT:    [[MUL3:%.*]] = mul nsw i32 [[TMP1]], -3
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
+; CHECK-NEXT:    store i32 [[MUL3]], i32* [[INCDEC_PTR1]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
+; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[INCDEC_PTR2]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
+; CHECK-NEXT:    store i32 [[TMP2]], i32* [[INCDEC_PTR4]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[INCDEC_PTR5]], align 4
+; CHECK-NEXT:    [[MUL9:%.*]] = mul nsw i32 [[TMP3]], -9
+; CHECK-NEXT:    store i32 [[MUL9]], i32* [[INCDEC_PTR7]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds i32, i32* %src, i64 1
+  %0 = load i32, i32* %src, align 4
+  %mul = mul nsw i32 %0, 257
+  %incdec.ptr1 = getelementptr inbounds i32, i32* %dst, i64 1
+  store i32 %mul, i32* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds i32, i32* %src, i64 2
+  %1 = load i32, i32* %incdec.ptr, align 4
+  %mul3 = mul nsw i32 %1, -3
+  %incdec.ptr4 = getelementptr inbounds i32, i32* %dst, i64 2
+  store i32 %mul3, i32* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds i32, i32* %src, i64 3
+  %2 = load i32, i32* %incdec.ptr2, align 4
+  %incdec.ptr7 = getelementptr inbounds i32, i32* %dst, i64 3
+  store i32 %2, i32* %incdec.ptr4, align 4
+  %3 = load i32, i32* %incdec.ptr5, align 4
+  %mul9 = mul nsw i32 %3, -9
+  store i32 %mul9, i32* %incdec.ptr7, align 4
+  ret void
+}
+
+define void @shl0(i32* noalias %dst, i32* noalias %src) {
+; CHECK-LABEL: @shl0(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[SRC]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
+; CHECK-NEXT:    store i32 [[TMP0]], i32* [[DST]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[INCDEC_PTR]], align 4
+; CHECK-NEXT:    [[SHL:%.*]] = shl i32 [[TMP1]], 1
+; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
+; CHECK-NEXT:    store i32 [[SHL]], i32* [[INCDEC_PTR1]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
+; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[INCDEC_PTR2]], align 4
+; CHECK-NEXT:    [[SHL5:%.*]] = shl i32 [[TMP2]], 2
+; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
+; CHECK-NEXT:    store i32 [[SHL5]], i32* [[INCDEC_PTR3]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[INCDEC_PTR4]], align 4
+; CHECK-NEXT:    [[SHL8:%.*]] = shl i32 [[TMP3]], 3
+; CHECK-NEXT:    store i32 [[SHL8]], i32* [[INCDEC_PTR6]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds i32, i32* %src, i64 1
+  %0 = load i32, i32* %src, align 4
+  %incdec.ptr1 = getelementptr inbounds i32, i32* %dst, i64 1
+  store i32 %0, i32* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds i32, i32* %src, i64 2
+  %1 = load i32, i32* %incdec.ptr, align 4
+  %shl = shl i32 %1, 1
+  %incdec.ptr3 = getelementptr inbounds i32, i32* %dst, i64 2
+  store i32 %shl, i32* %incdec.ptr1, align 4
+  %incdec.ptr4 = getelementptr inbounds i32, i32* %src, i64 3
+  %2 = load i32, i32* %incdec.ptr2, align 4
+  %shl5 = shl i32 %2, 2
+  %incdec.ptr6 = getelementptr inbounds i32, i32* %dst, i64 3
+  store i32 %shl5, i32* %incdec.ptr3, align 4
+  %3 = load i32, i32* %incdec.ptr4, align 4
+  %shl8 = shl i32 %3, 3
+  store i32 %shl8, i32* %incdec.ptr6, align 4
+  ret void
+}
+
+define void @shl1(i32* noalias %dst, i32* noalias %src) {
+; CHECK-LABEL: @shl1(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[SRC]] to <4 x i32>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = shl <4 x i32> [[TMP1]], <i32 7, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[DST]] to <4 x i32>*
+; CHECK-NEXT:    store <4 x i32> [[TMP2]], <4 x i32>* [[TMP3]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds i32, i32* %src, i64 1
+  %0 = load i32, i32* %src, align 4
+  %shl = shl i32 %0, 7
+  %incdec.ptr1 = getelementptr inbounds i32, i32* %dst, i64 1
+  store i32 %shl, i32* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds i32, i32* %src, i64 2
+  %1 = load i32, i32* %incdec.ptr, align 4
+  %shl3 = shl i32 %1, 1
+  %incdec.ptr4 = getelementptr inbounds i32, i32* %dst, i64 2
+  store i32 %shl3, i32* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds i32, i32* %src, i64 3
+  %2 = load i32, i32* %incdec.ptr2, align 4
+  %shl6 = shl i32 %2, 2
+  %incdec.ptr7 = getelementptr inbounds i32, i32* %dst, i64 3
+  store i32 %shl6, i32* %incdec.ptr4, align 4
+  %3 = load i32, i32* %incdec.ptr5, align 4
+  %shl9 = shl i32 %3, 3
+  store i32 %shl9, i32* %incdec.ptr7, align 4
+  ret void
+}
+
+define void @add0f(float* noalias %dst, float* noalias %src) {
+; CHECK-LABEL: @add0f(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[SRC]] to <4 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd fast <4 x float> <float 1.000000e+00, float 1.000000e+00, float 2.000000e+00, float 3.000000e+00>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[DST]] to <4 x float>*
+; CHECK-NEXT:    store <4 x float> [[TMP2]], <4 x float>* [[TMP3]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds float, float* %src, i64 1
+  %0 = load float, float* %src, align 4
+  %add = fadd fast float %0, 1.000000e+00
+  %incdec.ptr1 = getelementptr inbounds float, float* %dst, i64 1
+  store float %add, float* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds float, float* %src, i64 2
+  %1 = load float, float* %incdec.ptr, align 4
+  %add3 = fadd fast float %1, 1.000000e+00
+  %incdec.ptr4 = getelementptr inbounds float, float* %dst, i64 2
+  store float %add3, float* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds float, float* %src, i64 3
+  %2 = load float, float* %incdec.ptr2, align 4
+  %add6 = fadd fast float %2, 2.000000e+00
+  %incdec.ptr7 = getelementptr inbounds float, float* %dst, i64 3
+  store float %add6, float* %incdec.ptr4, align 4
+  %3 = load float, float* %incdec.ptr5, align 4
+  %add9 = fadd fast float %3, 3.000000e+00
+  store float %add9, float* %incdec.ptr7, align 4
+  ret void
+}
+
+define void @add1f(float* noalias %dst, float* noalias %src) {
+; CHECK-LABEL: @add1f(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[SRC]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
+; CHECK-NEXT:    store float [[TMP0]], float* [[DST]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[INCDEC_PTR]], align 4
+; CHECK-NEXT:    [[ADD3:%.*]] = fadd fast float [[TMP1]], 1.000000e+00
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
+; CHECK-NEXT:    store float [[ADD3]], float* [[INCDEC_PTR1]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
+; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[INCDEC_PTR2]], align 4
+; CHECK-NEXT:    [[ADD6:%.*]] = fadd fast float [[TMP2]], 2.000000e+00
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
+; CHECK-NEXT:    store float [[ADD6]], float* [[INCDEC_PTR4]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[INCDEC_PTR5]], align 4
+; CHECK-NEXT:    [[ADD9:%.*]] = fadd fast float [[TMP3]], 3.000000e+00
+; CHECK-NEXT:    store float [[ADD9]], float* [[INCDEC_PTR7]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds float, float* %src, i64 1
+  %0 = load float, float* %src, align 4
+  %incdec.ptr1 = getelementptr inbounds float, float* %dst, i64 1
+  store float %0, float* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds float, float* %src, i64 2
+  %1 = load float, float* %incdec.ptr, align 4
+  %add3 = fadd fast float %1, 1.000000e+00
+  %incdec.ptr4 = getelementptr inbounds float, float* %dst, i64 2
+  store float %add3, float* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds float, float* %src, i64 3
+  %2 = load float, float* %incdec.ptr2, align 4
+  %add6 = fadd fast float %2, 2.000000e+00
+  %incdec.ptr7 = getelementptr inbounds float, float* %dst, i64 3
+  store float %add6, float* %incdec.ptr4, align 4
+  %3 = load float, float* %incdec.ptr5, align 4
+  %add9 = fadd fast float %3, 3.000000e+00
+  store float %add9, float* %incdec.ptr7, align 4
+  ret void
+}
+
+define void @sub0f(float* noalias %dst, float* noalias %src) {
+; CHECK-LABEL: @sub0f(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[SRC]], align 4
+; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP0]], -1.000000e+00
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
+; CHECK-NEXT:    store float [[ADD]], float* [[DST]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[INCDEC_PTR]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
+; CHECK-NEXT:    store float [[TMP1]], float* [[INCDEC_PTR1]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
+; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[INCDEC_PTR2]], align 4
+; CHECK-NEXT:    [[ADD6:%.*]] = fadd fast float [[TMP2]], -2.000000e+00
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
+; CHECK-NEXT:    store float [[ADD6]], float* [[INCDEC_PTR4]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[INCDEC_PTR5]], align 4
+; CHECK-NEXT:    [[ADD9:%.*]] = fadd fast float [[TMP3]], -3.000000e+00
+; CHECK-NEXT:    store float [[ADD9]], float* [[INCDEC_PTR7]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds float, float* %src, i64 1
+  %0 = load float, float* %src, align 4
+  %add = fadd fast float %0, -1.000000e+00
+  %incdec.ptr1 = getelementptr inbounds float, float* %dst, i64 1
+  store float %add, float* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds float, float* %src, i64 2
+  %1 = load float, float* %incdec.ptr, align 4
+  %incdec.ptr4 = getelementptr inbounds float, float* %dst, i64 2
+  store float %1, float* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds float, float* %src, i64 3
+  %2 = load float, float* %incdec.ptr2, align 4
+  %add6 = fadd fast float %2, -2.000000e+00
+  %incdec.ptr7 = getelementptr inbounds float, float* %dst, i64 3
+  store float %add6, float* %incdec.ptr4, align 4
+  %3 = load float, float* %incdec.ptr5, align 4
+  %add9 = fadd fast float %3, -3.000000e+00
+  store float %add9, float* %incdec.ptr7, align 4
+  ret void
+}
+
+define void @sub1f(float* noalias %dst, float* noalias %src) {
+; CHECK-LABEL: @sub1f(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
+; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[SRC]] to <4 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd fast <4 x float> <float 4.000000e+00, float -1.000000e+00, float -2.000000e+00, float -3.000000e+00>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[DST]] to <4 x float>*
+; CHECK-NEXT:    store <4 x float> [[TMP2]], <4 x float>* [[TMP3]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds float, float* %src, i64 1
+  %0 = load float, float* %src, align 4
+  %add = fadd fast float %0, 4.000000e+00
+  %incdec.ptr1 = getelementptr inbounds float, float* %dst, i64 1
+  store float %add, float* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds float, float* %src, i64 2
+  %1 = load float, float* %incdec.ptr, align 4
+  %sub = fadd fast float %1, -1.000000e+00
+  %incdec.ptr3 = getelementptr inbounds float, float* %dst, i64 2
+  store float %sub, float* %incdec.ptr1, align 4
+  %incdec.ptr4 = getelementptr inbounds float, float* %src, i64 3
+  %2 = load float, float* %incdec.ptr2, align 4
+  %sub5 = fadd fast float %2, -2.000000e+00
+  %incdec.ptr6 = getelementptr inbounds float, float* %dst, i64 3
+  store float %sub5, float* %incdec.ptr3, align 4
+  %3 = load float, float* %incdec.ptr4, align 4
+  %sub8 = fadd fast float %3, -3.000000e+00
+  store float %sub8, float* %incdec.ptr6, align 4
+  ret void
+}
+
+define void @sub2f(float* noalias %dst, float* noalias %src) {
+; CHECK-LABEL: @sub2f(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[SRC]] to <4 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd fast <4 x float> <float -1.000000e+00, float -1.000000e+00, float -2.000000e+00, float -3.000000e+00>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[DST]] to <4 x float>*
+; CHECK-NEXT:    store <4 x float> [[TMP2]], <4 x float>* [[TMP3]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds float, float* %src, i64 1
+  %0 = load float, float* %src, align 4
+  %sub = fadd fast float %0, -1.000000e+00
+  %incdec.ptr1 = getelementptr inbounds float, float* %dst, i64 1
+  store float %sub, float* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds float, float* %src, i64 2
+  %1 = load float, float* %incdec.ptr, align 4
+  %sub3 = fadd fast float %1, -1.000000e+00
+  %incdec.ptr4 = getelementptr inbounds float, float* %dst, i64 2
+  store float %sub3, float* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds float, float* %src, i64 3
+  %2 = load float, float* %incdec.ptr2, align 4
+  %sub6 = fadd fast float %2, -2.000000e+00
+  %incdec.ptr7 = getelementptr inbounds float, float* %dst, i64 3
+  store float %sub6, float* %incdec.ptr4, align 4
+  %3 = load float, float* %incdec.ptr5, align 4
+  %sub9 = fadd fast float %3, -3.000000e+00
+  store float %sub9, float* %incdec.ptr7, align 4
+  ret void
+}
+
+define void @addsub0f(float* noalias %dst, float* noalias %src) {
+; CHECK-LABEL: @addsub0f(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[SRC]], align 4
+; CHECK-NEXT:    [[SUB:%.*]] = fadd fast float [[TMP0]], -1.000000e+00
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
+; CHECK-NEXT:    store float [[SUB]], float* [[DST]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[INCDEC_PTR]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
+; CHECK-NEXT:    store float [[TMP1]], float* [[INCDEC_PTR1]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
+; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[INCDEC_PTR2]], align 4
+; CHECK-NEXT:    [[SUB5:%.*]] = fadd fast float [[TMP2]], -2.000000e+00
+; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
+; CHECK-NEXT:    store float [[SUB5]], float* [[INCDEC_PTR3]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[INCDEC_PTR4]], align 4
+; CHECK-NEXT:    [[SUB8:%.*]] = fsub fast float [[TMP3]], -3.000000e+00
+; CHECK-NEXT:    store float [[SUB8]], float* [[INCDEC_PTR6]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds float, float* %src, i64 1
+  %0 = load float, float* %src, align 4
+  %sub = fadd fast float %0, -1.000000e+00
+  %incdec.ptr1 = getelementptr inbounds float, float* %dst, i64 1
+  store float %sub, float* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds float, float* %src, i64 2
+  %1 = load float, float* %incdec.ptr, align 4
+  %incdec.ptr3 = getelementptr inbounds float, float* %dst, i64 2
+  store float %1, float* %incdec.ptr1, align 4
+  %incdec.ptr4 = getelementptr inbounds float, float* %src, i64 3
+  %2 = load float, float* %incdec.ptr2, align 4
+  %sub5 = fadd fast float %2, -2.000000e+00
+  %incdec.ptr6 = getelementptr inbounds float, float* %dst, i64 3
+  store float %sub5, float* %incdec.ptr3, align 4
+  %3 = load float, float* %incdec.ptr4, align 4
+  %sub8 = fsub fast float %3, -3.000000e+00
+  store float %sub8, float* %incdec.ptr6, align 4
+  ret void
+}
+
+define void @addsub1f(float* noalias %dst, float* noalias %src) {
+; CHECK-LABEL: @addsub1f(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[SRC]], align 4
+; CHECK-NEXT:    [[SUB:%.*]] = fadd fast float [[TMP0]], -1.000000e+00
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
+; CHECK-NEXT:    store float [[SUB]], float* [[DST]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[INCDEC_PTR]], align 4
+; CHECK-NEXT:    [[SUB1:%.*]] = fsub fast float [[TMP1]], -1.000000e+00
+; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
+; CHECK-NEXT:    store float [[SUB1]], float* [[INCDEC_PTR1]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
+; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[INCDEC_PTR2]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
+; CHECK-NEXT:    store float [[TMP2]], float* [[INCDEC_PTR3]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[INCDEC_PTR4]], align 4
+; CHECK-NEXT:    [[SUB8:%.*]] = fsub fast float [[TMP3]], -3.000000e+00
+; CHECK-NEXT:    store float [[SUB8]], float* [[INCDEC_PTR6]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds float, float* %src, i64 1
+  %0 = load float, float* %src, align 4
+  %sub = fadd fast float %0, -1.000000e+00
+  %incdec.ptr1 = getelementptr inbounds float, float* %dst, i64 1
+  store float %sub, float* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds float, float* %src, i64 2
+  %1 = load float, float* %incdec.ptr, align 4
+  %sub1 = fsub fast float %1, -1.000000e+00
+  %incdec.ptr3 = getelementptr inbounds float, float* %dst, i64 2
+  store float %sub1, float* %incdec.ptr1, align 4
+  %incdec.ptr4 = getelementptr inbounds float, float* %src, i64 3
+  %2 = load float, float* %incdec.ptr2, align 4
+  %incdec.ptr6 = getelementptr inbounds float, float* %dst, i64 3
+  store float %2, float* %incdec.ptr3, align 4
+  %3 = load float, float* %incdec.ptr4, align 4
+  %sub8 = fsub fast float %3, -3.000000e+00
+  store float %sub8, float* %incdec.ptr6, align 4
+  ret void
+}
+
+define void @mulf(float* noalias %dst, float* noalias %src) {
+; CHECK-LABEL: @mulf(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[SRC]], align 4
+; CHECK-NEXT:    [[SUB:%.*]] = fmul fast float [[TMP0]], 2.570000e+02
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
+; CHECK-NEXT:    store float [[SUB]], float* [[DST]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[INCDEC_PTR]], align 4
+; CHECK-NEXT:    [[SUB3:%.*]] = fmul fast float [[TMP1]], -3.000000e+00
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
+; CHECK-NEXT:    store float [[SUB3]], float* [[INCDEC_PTR1]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
+; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[INCDEC_PTR2]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
+; CHECK-NEXT:    store float [[TMP2]], float* [[INCDEC_PTR4]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[INCDEC_PTR5]], align 4
+; CHECK-NEXT:    [[SUB9:%.*]] = fmul fast float [[TMP3]], -9.000000e+00
+; CHECK-NEXT:    store float [[SUB9]], float* [[INCDEC_PTR7]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds float, float* %src, i64 1
+  %0 = load float, float* %src, align 4
+  %sub = fmul fast float %0, 2.570000e+02
+  %incdec.ptr1 = getelementptr inbounds float, float* %dst, i64 1
+  store float %sub, float* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds float, float* %src, i64 2
+  %1 = load float, float* %incdec.ptr, align 4
+  %sub3 = fmul fast float %1, -3.000000e+00
+  %incdec.ptr4 = getelementptr inbounds float, float* %dst, i64 2
+  store float %sub3, float* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds float, float* %src, i64 3
+  %2 = load float, float* %incdec.ptr2, align 4
+  %incdec.ptr7 = getelementptr inbounds float, float* %dst, i64 3
+  store float %2, float* %incdec.ptr4, align 4
+  %3 = load float, float* %incdec.ptr5, align 4
+  %sub9 = fmul fast float %3, -9.000000e+00
+  store float %sub9, float* %incdec.ptr7, align 4
+  ret void
+}
+
+define void @add0fn(float* noalias %dst, float* noalias %src) {
+; CHECK-LABEL: @add0fn(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[SRC]] to <4 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd <4 x float> <float 1.000000e+00, float 1.000000e+00, float 2.000000e+00, float 3.000000e+00>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[DST]] to <4 x float>*
+; CHECK-NEXT:    store <4 x float> [[TMP2]], <4 x float>* [[TMP3]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds float, float* %src, i64 1
+  %0 = load float, float* %src, align 4
+  %add = fadd float %0, 1.000000e+00
+  %incdec.ptr1 = getelementptr inbounds float, float* %dst, i64 1
+  store float %add, float* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds float, float* %src, i64 2
+  %1 = load float, float* %incdec.ptr, align 4
+  %add3 = fadd float %1, 1.000000e+00
+  %incdec.ptr4 = getelementptr inbounds float, float* %dst, i64 2
+  store float %add3, float* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds float, float* %src, i64 3
+  %2 = load float, float* %incdec.ptr2, align 4
+  %add6 = fadd float %2, 2.000000e+00
+  %incdec.ptr7 = getelementptr inbounds float, float* %dst, i64 3
+  store float %add6, float* %incdec.ptr4, align 4
+  %3 = load float, float* %incdec.ptr5, align 4
+  %add9 = fadd float %3, 3.000000e+00
+  store float %add9, float* %incdec.ptr7, align 4
+  ret void
+}
+
+define void @add1fn(float* noalias %dst, float* noalias %src) {
+; CHECK-LABEL: @add1fn(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[SRC]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
+; CHECK-NEXT:    store float [[TMP0]], float* [[DST]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[INCDEC_PTR]], align 4
+; CHECK-NEXT:    [[ADD3:%.*]] = fadd float [[TMP1]], 1.000000e+00
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
+; CHECK-NEXT:    store float [[ADD3]], float* [[INCDEC_PTR1]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
+; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[INCDEC_PTR2]], align 4
+; CHECK-NEXT:    [[ADD6:%.*]] = fadd float [[TMP2]], 2.000000e+00
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
+; CHECK-NEXT:    store float [[ADD6]], float* [[INCDEC_PTR4]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[INCDEC_PTR5]], align 4
+; CHECK-NEXT:    [[ADD9:%.*]] = fadd float [[TMP3]], 3.000000e+00
+; CHECK-NEXT:    store float [[ADD9]], float* [[INCDEC_PTR7]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds float, float* %src, i64 1
+  %0 = load float, float* %src, align 4
+  %incdec.ptr1 = getelementptr inbounds float, float* %dst, i64 1
+  store float %0, float* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds float, float* %src, i64 2
+  %1 = load float, float* %incdec.ptr, align 4
+  %add3 = fadd float %1, 1.000000e+00
+  %incdec.ptr4 = getelementptr inbounds float, float* %dst, i64 2
+  store float %add3, float* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds float, float* %src, i64 3
+  %2 = load float, float* %incdec.ptr2, align 4
+  %add6 = fadd float %2, 2.000000e+00
+  %incdec.ptr7 = getelementptr inbounds float, float* %dst, i64 3
+  store float %add6, float* %incdec.ptr4, align 4
+  %3 = load float, float* %incdec.ptr5, align 4
+  %add9 = fadd float %3, 3.000000e+00
+  store float %add9, float* %incdec.ptr7, align 4
+  ret void
+}
+
+define void @sub0fn(float* noalias %dst, float* noalias %src) {
+; CHECK-LABEL: @sub0fn(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[SRC]], align 4
+; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP0]], -1.000000e+00
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
+; CHECK-NEXT:    store float [[ADD]], float* [[DST]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[INCDEC_PTR]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
+; CHECK-NEXT:    store float [[TMP1]], float* [[INCDEC_PTR1]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
+; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[INCDEC_PTR2]], align 4
+; CHECK-NEXT:    [[ADD6:%.*]] = fadd float [[TMP2]], -2.000000e+00
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
+; CHECK-NEXT:    store float [[ADD6]], float* [[INCDEC_PTR4]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[INCDEC_PTR5]], align 4
+; CHECK-NEXT:    [[ADD9:%.*]] = fadd float [[TMP3]], -3.000000e+00
+; CHECK-NEXT:    store float [[ADD9]], float* [[INCDEC_PTR7]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds float, float* %src, i64 1
+  %0 = load float, float* %src, align 4
+  %add = fadd fast float %0, -1.000000e+00
+  %incdec.ptr1 = getelementptr inbounds float, float* %dst, i64 1
+  store float %add, float* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds float, float* %src, i64 2
+  %1 = load float, float* %incdec.ptr, align 4
+  %incdec.ptr4 = getelementptr inbounds float, float* %dst, i64 2
+  store float %1, float* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds float, float* %src, i64 3
+  %2 = load float, float* %incdec.ptr2, align 4
+  %add6 = fadd float %2, -2.000000e+00
+  %incdec.ptr7 = getelementptr inbounds float, float* %dst, i64 3
+  store float %add6, float* %incdec.ptr4, align 4
+  %3 = load float, float* %incdec.ptr5, align 4
+  %add9 = fadd float %3, -3.000000e+00
+  store float %add9, float* %incdec.ptr7, align 4
+  ret void
+}
+
+define void @sub1fn(float* noalias %dst, float* noalias %src) {
+; CHECK-LABEL: @sub1fn(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
+; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[SRC]] to <4 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd <4 x float> <float 4.000000e+00, float -1.000000e+00, float -2.000000e+00, float -3.000000e+00>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[DST]] to <4 x float>*
+; CHECK-NEXT:    store <4 x float> [[TMP2]], <4 x float>* [[TMP3]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds float, float* %src, i64 1
+  %0 = load float, float* %src, align 4
+  %add = fadd float %0, 4.000000e+00
+  %incdec.ptr1 = getelementptr inbounds float, float* %dst, i64 1
+  store float %add, float* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds float, float* %src, i64 2
+  %1 = load float, float* %incdec.ptr, align 4
+  %sub = fadd float %1, -1.000000e+00
+  %incdec.ptr3 = getelementptr inbounds float, float* %dst, i64 2
+  store float %sub, float* %incdec.ptr1, align 4
+  %incdec.ptr4 = getelementptr inbounds float, float* %src, i64 3
+  %2 = load float, float* %incdec.ptr2, align 4
+  %sub5 = fadd float %2, -2.000000e+00
+  %incdec.ptr6 = getelementptr inbounds float, float* %dst, i64 3
+  store float %sub5, float* %incdec.ptr3, align 4
+  %3 = load float, float* %incdec.ptr4, align 4
+  %sub8 = fadd float %3, -3.000000e+00
+  store float %sub8, float* %incdec.ptr6, align 4
+  ret void
+}
+
+define void @sub2fn(float* noalias %dst, float* noalias %src) {
+; CHECK-LABEL: @sub2fn(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[SRC]] to <4 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd <4 x float> <float -1.000000e+00, float -1.000000e+00, float -2.000000e+00, float -3.000000e+00>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[DST]] to <4 x float>*
+; CHECK-NEXT:    store <4 x float> [[TMP2]], <4 x float>* [[TMP3]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds float, float* %src, i64 1
+  %0 = load float, float* %src, align 4
+  %sub = fadd float %0, -1.000000e+00
+  %incdec.ptr1 = getelementptr inbounds float, float* %dst, i64 1
+  store float %sub, float* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds float, float* %src, i64 2
+  %1 = load float, float* %incdec.ptr, align 4
+  %sub3 = fadd float %1, -1.000000e+00
+  %incdec.ptr4 = getelementptr inbounds float, float* %dst, i64 2
+  store float %sub3, float* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds float, float* %src, i64 3
+  %2 = load float, float* %incdec.ptr2, align 4
+  %sub6 = fadd float %2, -2.000000e+00
+  %incdec.ptr7 = getelementptr inbounds float, float* %dst, i64 3
+  store float %sub6, float* %incdec.ptr4, align 4
+  %3 = load float, float* %incdec.ptr5, align 4
+  %sub9 = fadd float %3, -3.000000e+00
+  store float %sub9, float* %incdec.ptr7, align 4
+  ret void
+}
+
+define void @mulfn(float* noalias %dst, float* noalias %src) {
+; CHECK-LABEL: @mulfn(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[SRC]], align 4
+; CHECK-NEXT:    [[SUB:%.*]] = fmul float [[TMP0]], 2.570000e+02
+; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
+; CHECK-NEXT:    store float [[SUB]], float* [[DST]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
+; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[INCDEC_PTR]], align 4
+; CHECK-NEXT:    [[SUB3:%.*]] = fmul float [[TMP1]], -3.000000e+00
+; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
+; CHECK-NEXT:    store float [[SUB3]], float* [[INCDEC_PTR1]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
+; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[INCDEC_PTR2]], align 4
+; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
+; CHECK-NEXT:    store float [[TMP2]], float* [[INCDEC_PTR4]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[INCDEC_PTR5]], align 4
+; CHECK-NEXT:    [[SUB9:%.*]] = fmul fast float [[TMP3]], -9.000000e+00
+; CHECK-NEXT:    store float [[SUB9]], float* [[INCDEC_PTR7]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %incdec.ptr = getelementptr inbounds float, float* %src, i64 1
+  %0 = load float, float* %src, align 4
+  %sub = fmul float %0, 2.570000e+02
+  %incdec.ptr1 = getelementptr inbounds float, float* %dst, i64 1
+  store float %sub, float* %dst, align 4
+  %incdec.ptr2 = getelementptr inbounds float, float* %src, i64 2
+  %1 = load float, float* %incdec.ptr, align 4
+  %sub3 = fmul float %1, -3.000000e+00
+  %incdec.ptr4 = getelementptr inbounds float, float* %dst, i64 2
+  store float %sub3, float* %incdec.ptr1, align 4
+  %incdec.ptr5 = getelementptr inbounds float, float* %src, i64 3
+  %2 = load float, float* %incdec.ptr2, align 4
+  %incdec.ptr7 = getelementptr inbounds float, float* %dst, i64 3
+  store float %2, float* %incdec.ptr4, align 4
+  %3 = load float, float* %incdec.ptr5, align 4
+  %sub9 = fmul fast float %3, -9.000000e+00
+  store float %sub9, float* %incdec.ptr7, align 4
+  ret void
+}