diff --git a/llvm/test/Transforms/SLPVectorizer/AArch64/reduce-add-i64.ll b/llvm/test/Transforms/SLPVectorizer/AArch64/reduce-add-i64.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/SLPVectorizer/AArch64/reduce-add-i64.ll
@@ -0,0 +1,467 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -S -slp-vectorizer %s --mtriple=aarch64-- | FileCheck %s
+
+; This test checks whether load-zext-add and load-add reduction patterns
+; get vectorized by SLP.
+
+define i64 @red_zext_ld_2xi64(ptr %ptr) {
+; CHECK-LABEL: @red_zext_ld_2xi64(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[LD0:%.*]] = load i8, ptr [[PTR:%.*]], align 1
+; CHECK-NEXT:    [[ZEXT:%.*]] = zext i8 [[LD0]] to i64
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 1
+; CHECK-NEXT:    [[LD1:%.*]] = load i8, ptr [[GEP]], align 1
+; CHECK-NEXT:    [[ZEXT_1:%.*]] = zext i8 [[LD1]] to i64
+; CHECK-NEXT:    [[ADD_1:%.*]] = add nuw nsw i64 [[ZEXT]], [[ZEXT_1]]
+; CHECK-NEXT:    ret i64 [[ADD_1]]
+;
+entry:
+  %ld0 = load i8, ptr %ptr
+  %zext = zext i8 %ld0 to i64
+  %gep = getelementptr inbounds i8, ptr %ptr, i64 1
+  %ld1 = load i8, ptr %gep
+  %zext.1 = zext i8 %ld1 to i64
+  %add.1 = add nuw nsw i64 %zext, %zext.1
+  ret i64 %add.1
+}
+
+define i64 @red_zext_ld_4xi64(ptr %ptr) {
+; CHECK-LABEL: @red_zext_ld_4xi64(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[LD0:%.*]] = load i8, ptr [[PTR:%.*]], align 1
+; CHECK-NEXT:    [[ZEXT:%.*]] = zext i8 [[LD0]] to i64
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 1
+; CHECK-NEXT:    [[LD1:%.*]] = load i8, ptr [[GEP]], align 1
+; CHECK-NEXT:    [[ZEXT_1:%.*]] = zext i8 [[LD1]] to i64
+; CHECK-NEXT:    [[ADD_1:%.*]] = add nuw nsw i64 [[ZEXT]], [[ZEXT_1]]
+; CHECK-NEXT:    [[GEP_1:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 2
+; CHECK-NEXT:    [[LD2:%.*]] = load i8, ptr [[GEP_1]], align 1
+; CHECK-NEXT:    [[ZEXT_2:%.*]] = zext i8 [[LD2]] to i64
+; CHECK-NEXT:    [[ADD_2:%.*]] = add nuw nsw i64 [[ADD_1]], [[ZEXT_2]]
+; CHECK-NEXT:    [[GEP_2:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 3
+; CHECK-NEXT:    [[LD3:%.*]] = load i8, ptr [[GEP_2]], align 1
+; CHECK-NEXT:    [[ZEXT_3:%.*]] = zext i8 [[LD3]] to i64
+; CHECK-NEXT:    [[ADD_3:%.*]] = add nuw nsw i64 [[ADD_2]], [[ZEXT_3]]
+; CHECK-NEXT:    ret i64 [[ADD_3]]
+;
+entry:
+  %ld0 = load i8, ptr %ptr
+  %zext = zext i8 %ld0 to i64
+  %gep = getelementptr inbounds i8, ptr %ptr, i64 1
+  %ld1 = load i8, ptr %gep
+  %zext.1 = zext i8 %ld1 to i64
+  %add.1 = add nuw nsw i64 %zext, %zext.1
+  %gep.1 = getelementptr inbounds i8, ptr %ptr, i64 2
+  %ld2 = load i8, ptr %gep.1
+  %zext.2 = zext i8 %ld2 to i64
+  %add.2 = add nuw nsw i64 %add.1, %zext.2
+  %gep.2 = getelementptr inbounds i8, ptr %ptr, i64 3
+  %ld3 = load i8, ptr %gep.2
+  %zext.3 = zext i8 %ld3 to i64
+  %add.3 = add nuw nsw i64 %add.2, %zext.3
+  ret i64 %add.3
+}
+
+define i64 @red_zext_ld_8xi64(ptr %ptr) {
+; CHECK-LABEL: @red_zext_ld_8xi64(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[LD0:%.*]] = load i8, ptr [[PTR:%.*]], align 1
+; CHECK-NEXT:    [[ZEXT:%.*]] = zext i8 [[LD0]] to i64
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 1
+; CHECK-NEXT:    [[LD1:%.*]] = load i8, ptr [[GEP]], align 1
+; CHECK-NEXT:    [[ZEXT_1:%.*]] = zext i8 [[LD1]] to i64
+; CHECK-NEXT:    [[ADD_1:%.*]] = add nuw nsw i64 [[ZEXT]], [[ZEXT_1]]
+; CHECK-NEXT:    [[GEP_1:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 2
+; CHECK-NEXT:    [[LD2:%.*]] = load i8, ptr [[GEP_1]], align 1
+; CHECK-NEXT:    [[ZEXT_2:%.*]] = zext i8 [[LD2]] to i64
+; CHECK-NEXT:    [[ADD_2:%.*]] = add nuw nsw i64 [[ADD_1]], [[ZEXT_2]]
+; CHECK-NEXT:    [[GEP_2:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 3
+; CHECK-NEXT:    [[LD3:%.*]] = load i8, ptr [[GEP_2]], align 1
+; CHECK-NEXT:    [[ZEXT_3:%.*]] = zext i8 [[LD3]] to i64
+; CHECK-NEXT:    [[ADD_3:%.*]] = add nuw nsw i64 [[ADD_2]], [[ZEXT_3]]
+; CHECK-NEXT:    [[GEP_3:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 4
+; CHECK-NEXT:    [[LD4:%.*]] = load i8, ptr [[GEP_3]], align 1
+; CHECK-NEXT:    [[ZEXT_4:%.*]] = zext i8 [[LD4]] to i64
+; CHECK-NEXT:    [[ADD_4:%.*]] = add nuw nsw i64 [[ADD_3]], [[ZEXT_4]]
+; CHECK-NEXT:    [[GEP_4:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 5
+; CHECK-NEXT:    [[LD5:%.*]] = load i8, ptr [[GEP_4]], align 1
+; CHECK-NEXT:    [[ZEXT_5:%.*]] = zext i8 [[LD5]] to i64
+; CHECK-NEXT:    [[ADD_5:%.*]] = add nuw nsw i64 [[ADD_4]], [[ZEXT_5]]
+; CHECK-NEXT:    [[GEP_5:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 6
+; CHECK-NEXT:    [[LD6:%.*]] = load i8, ptr [[GEP_5]], align 1
+; CHECK-NEXT:    [[ZEXT_6:%.*]] = zext i8 [[LD6]] to i64
+; CHECK-NEXT:    [[ADD_6:%.*]] = add nuw nsw i64 [[ADD_5]], [[ZEXT_6]]
+; CHECK-NEXT:    [[GEP_6:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 7
+; CHECK-NEXT:    [[LD7:%.*]] = load i8, ptr [[GEP_6]], align 1
+; CHECK-NEXT:    [[ZEXT_7:%.*]] = zext i8 [[LD7]] to i64
+; CHECK-NEXT:    [[ADD_7:%.*]] = add nuw nsw i64 [[ADD_6]], [[ZEXT_7]]
+; CHECK-NEXT:    ret i64 [[ADD_7]]
+;
+entry:
+  %ld0 = load i8, ptr %ptr
+  %zext = zext i8 %ld0 to i64
+  %gep = getelementptr inbounds i8, ptr %ptr, i64 1
+  %ld1 = load i8, ptr %gep
+  %zext.1 = zext i8 %ld1 to i64
+  %add.1 = add nuw nsw i64 %zext, %zext.1
+  %gep.1 = getelementptr inbounds i8, ptr %ptr, i64 2
+  %ld2 = load i8, ptr %gep.1
+  %zext.2 = zext i8 %ld2 to i64
+  %add.2 = add nuw nsw i64 %add.1, %zext.2
+  %gep.2 = getelementptr inbounds i8, ptr %ptr, i64 3
+  %ld3 = load i8, ptr %gep.2
+  %zext.3 = zext i8 %ld3 to i64
+  %add.3 = add nuw nsw i64 %add.2, %zext.3
+  %gep.3 = getelementptr inbounds i8, ptr %ptr, i64 4
+  %ld4 = load i8, ptr %gep.3
+  %zext.4 = zext i8 %ld4 to i64
+  %add.4 = add nuw nsw i64 %add.3, %zext.4
+  %gep.4 = getelementptr inbounds i8, ptr %ptr, i64 5
+  %ld5 = load i8, ptr %gep.4
+  %zext.5 = zext i8 %ld5 to i64
+  %add.5 = add nuw nsw i64 %add.4, %zext.5
+  %gep.5 = getelementptr inbounds i8, ptr %ptr, i64 6
+  %ld6 = load i8, ptr %gep.5
+  %zext.6 = zext i8 %ld6 to i64
+  %add.6 = add nuw nsw i64 %add.5, %zext.6
+  %gep.6 = getelementptr inbounds i8, ptr %ptr, i64 7
+  %ld7 = load i8, ptr %gep.6
+  %zext.7 = zext i8 %ld7 to i64
+  %add.7 = add nuw nsw i64 %add.6, %zext.7
+  ret i64 %add.7
+}
+
+define i64 @red_zext_ld_16xi64(ptr %ptr) {
+; CHECK-LABEL: @red_zext_ld_16xi64(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[LD0:%.*]] = load i8, ptr [[PTR:%.*]], align 1
+; CHECK-NEXT:    [[ZEXT:%.*]] = zext i8 [[LD0]] to i64
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 1
+; CHECK-NEXT:    [[LD1:%.*]] = load i8, ptr [[GEP]], align 1
+; CHECK-NEXT:    [[ZEXT_1:%.*]] = zext i8 [[LD1]] to i64
+; CHECK-NEXT:    [[ADD_1:%.*]] = add nuw nsw i64 [[ZEXT]], [[ZEXT_1]]
+; CHECK-NEXT:    [[GEP_1:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 2
+; CHECK-NEXT:    [[LD2:%.*]] = load i8, ptr [[GEP_1]], align 1
+; CHECK-NEXT:    [[ZEXT_2:%.*]] = zext i8 [[LD2]] to i64
+; CHECK-NEXT:    [[ADD_2:%.*]] = add nuw nsw i64 [[ADD_1]], [[ZEXT_2]]
+; CHECK-NEXT:    [[GEP_2:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 3
+; CHECK-NEXT:    [[LD3:%.*]] = load i8, ptr [[GEP_2]], align 1
+; CHECK-NEXT:    [[ZEXT_3:%.*]] = zext i8 [[LD3]] to i64
+; CHECK-NEXT:    [[ADD_3:%.*]] = add nuw nsw i64 [[ADD_2]], [[ZEXT_3]]
+; CHECK-NEXT:    [[GEP_3:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 4
+; CHECK-NEXT:    [[LD4:%.*]] = load i8, ptr [[GEP_3]], align 1
+; CHECK-NEXT:    [[ZEXT_4:%.*]] = zext i8 [[LD4]] to i64
+; CHECK-NEXT:    [[ADD_4:%.*]] = add nuw nsw i64 [[ADD_3]], [[ZEXT_4]]
+; CHECK-NEXT:    [[GEP_4:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 5
+; CHECK-NEXT:    [[LD5:%.*]] = load i8, ptr [[GEP_4]], align 1
+; CHECK-NEXT:    [[ZEXT_5:%.*]] = zext i8 [[LD5]] to i64
+; CHECK-NEXT:    [[ADD_5:%.*]] = add nuw nsw i64 [[ADD_4]], [[ZEXT_5]]
+; CHECK-NEXT:    [[GEP_5:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 6
+; CHECK-NEXT:    [[LD6:%.*]] = load i8, ptr [[GEP_5]], align 1
+; CHECK-NEXT:    [[ZEXT_6:%.*]] = zext i8 [[LD6]] to i64
+; CHECK-NEXT:    [[ADD_6:%.*]] = add nuw nsw i64 [[ADD_5]], [[ZEXT_6]]
+; CHECK-NEXT:    [[GEP_6:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 7
+; CHECK-NEXT:    [[LD7:%.*]] = load i8, ptr [[GEP_6]], align 1
+; CHECK-NEXT:    [[ZEXT_7:%.*]] = zext i8 [[LD7]] to i64
+; CHECK-NEXT:    [[ADD_7:%.*]] = add nuw nsw i64 [[ADD_6]], [[ZEXT_7]]
+; CHECK-NEXT:    [[GEP_7:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 8
+; CHECK-NEXT:    [[LD8:%.*]] = load i8, ptr [[GEP_7]], align 1
+; CHECK-NEXT:    [[ZEXT_8:%.*]] = zext i8 [[LD8]] to i64
+; CHECK-NEXT:    [[ADD_8:%.*]] = add nuw nsw i64 [[ADD_7]], [[ZEXT_8]]
+; CHECK-NEXT:    [[GEP_8:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 9
+; CHECK-NEXT:    [[LD9:%.*]] = load i8, ptr [[GEP_8]], align 1
+; CHECK-NEXT:    [[ZEXT_9:%.*]] = zext i8 [[LD9]] to i64
+; CHECK-NEXT:    [[ADD_9:%.*]] = add nuw nsw i64 [[ADD_8]], [[ZEXT_9]]
+; CHECK-NEXT:    [[GEP_9:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 10
+; CHECK-NEXT:    [[LD10:%.*]] = load i8, ptr [[GEP_9]], align 1
+; CHECK-NEXT:    [[ZEXT_10:%.*]] = zext i8 [[LD10]] to i64
+; CHECK-NEXT:    [[ADD_10:%.*]] = add nuw nsw i64 [[ADD_9]], [[ZEXT_10]]
+; CHECK-NEXT:    [[GEP_10:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 11
+; CHECK-NEXT:    [[LD11:%.*]] = load i8, ptr [[GEP_10]], align 1
+; CHECK-NEXT:    [[ZEXT_11:%.*]] = zext i8 [[LD11]] to i64
+; CHECK-NEXT:    [[ADD_11:%.*]] = add nuw nsw i64 [[ADD_10]], [[ZEXT_11]]
+; CHECK-NEXT:    [[GEP_11:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 12
+; CHECK-NEXT:    [[LD12:%.*]] = load i8, ptr [[GEP_11]], align 1
+; CHECK-NEXT:    [[ZEXT_12:%.*]] = zext i8 [[LD12]] to i64
+; CHECK-NEXT:    [[ADD_12:%.*]] = add nuw nsw i64 [[ADD_11]], [[ZEXT_12]]
+; CHECK-NEXT:    [[GEP_12:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 13
+; CHECK-NEXT:    [[LD13:%.*]] = load i8, ptr [[GEP_12]], align 1
+; CHECK-NEXT:    [[ZEXT_13:%.*]] = zext i8 [[LD13]] to i64
+; CHECK-NEXT:    [[ADD_13:%.*]] = add nuw nsw i64 [[ADD_12]], [[ZEXT_13]]
+; CHECK-NEXT:    [[GEP_13:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 14
+; CHECK-NEXT:    [[LD14:%.*]] = load i8, ptr [[GEP_13]], align 1
+; CHECK-NEXT:    [[ZEXT_14:%.*]] = zext i8 [[LD14]] to i64
+; CHECK-NEXT:    [[ADD_14:%.*]] = add nuw nsw i64 [[ADD_13]], [[ZEXT_14]]
+; CHECK-NEXT:    [[GEP_14:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i64 15
+; CHECK-NEXT:    [[LD15:%.*]] = load i8, ptr [[GEP_14]], align 1
+; CHECK-NEXT:    [[ZEXT_15:%.*]] = zext i8 [[LD15]] to i64
+; CHECK-NEXT:    [[ADD_15:%.*]] = add nuw nsw i64 [[ADD_14]], [[ZEXT_15]]
+; CHECK-NEXT:    ret i64 [[ADD_15]]
+;
+entry:
+  %ld0 = load i8, ptr %ptr
+  %zext = zext i8 %ld0 to i64
+  %gep = getelementptr inbounds i8, ptr %ptr, i64 1
+  %ld1 = load i8, ptr %gep
+  %zext.1 = zext i8 %ld1 to i64
+  %add.1 = add nuw nsw i64 %zext, %zext.1
+  %gep.1 = getelementptr inbounds i8, ptr %ptr, i64 2
+  %ld2 = load i8, ptr %gep.1
+  %zext.2 = zext i8 %ld2 to i64
+  %add.2 = add nuw nsw i64 %add.1, %zext.2
+  %gep.2 = getelementptr inbounds i8, ptr %ptr, i64 3
+  %ld3 = load i8, ptr %gep.2
+  %zext.3 = zext i8 %ld3 to i64
+  %add.3 = add nuw nsw i64 %add.2, %zext.3
+  %gep.3 = getelementptr inbounds i8, ptr %ptr, i64 4
+  %ld4 = load i8, ptr %gep.3
+  %zext.4 = zext i8 %ld4 to i64
+  %add.4 = add nuw nsw i64 %add.3, %zext.4
+  %gep.4 = getelementptr inbounds i8, ptr %ptr, i64 5
+  %ld5 = load i8, ptr %gep.4
+  %zext.5 = zext i8 %ld5 to i64
+  %add.5 = add nuw nsw i64 %add.4, %zext.5
+  %gep.5 = getelementptr inbounds i8, ptr %ptr, i64 6
+  %ld6 = load i8, ptr %gep.5
+  %zext.6 = zext i8 %ld6 to i64
+  %add.6 = add nuw nsw i64 %add.5, %zext.6
+  %gep.6 = getelementptr inbounds i8, ptr %ptr, i64 7
+  %ld7 = load i8, ptr %gep.6
+  %zext.7 = zext i8 %ld7 to i64
+  %add.7 = add nuw nsw i64 %add.6, %zext.7
+  %gep.7 = getelementptr inbounds i8, ptr %ptr, i64 8
+  %ld8 = load i8, ptr %gep.7
+  %zext.8 = zext i8 %ld8 to i64
+  %add.8 = add nuw nsw i64 %add.7, %zext.8
+  %gep.8 = getelementptr inbounds i8, ptr %ptr, i64 9
+  %ld9 = load i8, ptr %gep.8
+  %zext.9 = zext i8 %ld9 to i64
+  %add.9 = add nuw nsw i64 %add.8, %zext.9
+  %gep.9 = getelementptr inbounds i8, ptr %ptr, i64 10
+  %ld10 = load i8, ptr %gep.9
+  %zext.10 = zext i8 %ld10 to i64
+  %add.10 = add nuw nsw i64 %add.9, %zext.10
+  %gep.10 = getelementptr inbounds i8, ptr %ptr, i64 11
+  %ld11 = load i8, ptr %gep.10
+  %zext.11 = zext i8 %ld11 to i64
+  %add.11 = add nuw nsw i64 %add.10, %zext.11
+  %gep.11 = getelementptr inbounds i8, ptr %ptr, i64 12
+  %ld12 = load i8, ptr %gep.11
+  %zext.12 = zext i8 %ld12 to i64
+  %add.12 = add nuw nsw i64 %add.11, %zext.12
+  %gep.12 = getelementptr inbounds i8, ptr %ptr, i64 13
+  %ld13 = load i8, ptr %gep.12
+  %zext.13 = zext i8 %ld13 to i64
+  %add.13 = add nuw nsw i64 %add.12, %zext.13
+  %gep.13 = getelementptr inbounds i8, ptr %ptr, i64 14
+  %ld14 = load i8, ptr %gep.13
+  %zext.14 = zext i8 %ld14 to i64
+  %add.14 = add nuw nsw i64 %add.13, %zext.14
+  %gep.14 = getelementptr inbounds i8, ptr %ptr, i64 15
+  %ld15 = load i8, ptr %gep.14
+  %zext.15 = zext i8 %ld15 to i64
+  %add.15 = add nuw nsw i64 %add.14, %zext.15
+  ret i64 %add.15
+}
+
+
+
+define i64 @red_ld_2xi64(ptr %ptr) {
+; CHECK-LABEL: @red_ld_2xi64(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[LD0:%.*]] = load i64, ptr [[PTR:%.*]], align 4
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 1
+; CHECK-NEXT:    [[LD1:%.*]] = load i64, ptr [[GEP]], align 4
+; CHECK-NEXT:    [[ADD_1:%.*]] = add nuw nsw i64 [[LD0]], [[LD1]]
+; CHECK-NEXT:    ret i64 [[ADD_1]]
+;
+entry:
+  %ld0 = load i64, ptr %ptr
+  %gep = getelementptr inbounds i64, ptr %ptr, i64 1
+  %ld1 = load i64, ptr %gep
+  %add.1 = add nuw nsw i64 %ld0, %ld1
+  ret i64 %add.1
+}
+
+define i64 @red_ld_4xi64(ptr %ptr) {
+; CHECK-LABEL: @red_ld_4xi64(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[LD0:%.*]] = load i64, ptr [[PTR:%.*]], align 4
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 1
+; CHECK-NEXT:    [[LD1:%.*]] = load i64, ptr [[GEP]], align 4
+; CHECK-NEXT:    [[ADD_1:%.*]] = add nuw nsw i64 [[LD0]], [[LD1]]
+; CHECK-NEXT:    [[GEP_1:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 2
+; CHECK-NEXT:    [[LD2:%.*]] = load i64, ptr [[GEP_1]], align 4
+; CHECK-NEXT:    [[ADD_2:%.*]] = add nuw nsw i64 [[ADD_1]], [[LD2]]
+; CHECK-NEXT:    [[GEP_2:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 3
+; CHECK-NEXT:    [[LD3:%.*]] = load i64, ptr [[GEP_2]], align 4
+; CHECK-NEXT:    [[ADD_3:%.*]] = add nuw nsw i64 [[ADD_2]], [[LD3]]
+; CHECK-NEXT:    ret i64 [[ADD_3]]
+;
+entry:
+  %ld0 = load i64, ptr %ptr
+  %gep = getelementptr inbounds i64, ptr %ptr, i64 1
+  %ld1 = load i64, ptr %gep
+  %add.1 = add nuw nsw i64 %ld0, %ld1
+  %gep.1 = getelementptr inbounds i64, ptr %ptr, i64 2
+  %ld2 = load i64, ptr %gep.1
+  %add.2 = add nuw nsw i64 %add.1, %ld2
+  %gep.2 = getelementptr inbounds i64, ptr %ptr, i64 3
+  %ld3 = load i64, ptr %gep.2
+  %add.3 = add nuw nsw i64 %add.2, %ld3
+  ret i64 %add.3
+}
+
+define i64 @red_ld_8xi64(ptr %ptr) {
+; CHECK-LABEL: @red_ld_8xi64(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[LD0:%.*]] = load i64, ptr [[PTR:%.*]], align 4
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 1
+; CHECK-NEXT:    [[LD1:%.*]] = load i64, ptr [[GEP]], align 4
+; CHECK-NEXT:    [[ADD_1:%.*]] = add nuw nsw i64 [[LD0]], [[LD1]]
+; CHECK-NEXT:    [[GEP_1:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 2
+; CHECK-NEXT:    [[LD2:%.*]] = load i64, ptr [[GEP_1]], align 4
+; CHECK-NEXT:    [[ADD_2:%.*]] = add nuw nsw i64 [[ADD_1]], [[LD2]]
+; CHECK-NEXT:    [[GEP_2:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 3
+; CHECK-NEXT:    [[LD3:%.*]] = load i64, ptr [[GEP_2]], align 4
+; CHECK-NEXT:    [[ADD_3:%.*]] = add nuw nsw i64 [[ADD_2]], [[LD3]]
+; CHECK-NEXT:    [[GEP_3:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 4
+; CHECK-NEXT:    [[LD4:%.*]] = load i64, ptr [[GEP_3]], align 4
+; CHECK-NEXT:    [[ADD_4:%.*]] = add nuw nsw i64 [[ADD_3]], [[LD4]]
+; CHECK-NEXT:    [[GEP_4:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 5
+; CHECK-NEXT:    [[LD5:%.*]] = load i64, ptr [[GEP_4]], align 4
+; CHECK-NEXT:    [[ADD_5:%.*]] = add nuw nsw i64 [[ADD_4]], [[LD5]]
+; CHECK-NEXT:    [[GEP_5:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 6
+; CHECK-NEXT:    [[LD6:%.*]] = load i64, ptr [[GEP_5]], align 4
+; CHECK-NEXT:    [[ADD_6:%.*]] = add nuw nsw i64 [[ADD_5]], [[LD6]]
+; CHECK-NEXT:    [[GEP_6:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 7
+; CHECK-NEXT:    [[LD7:%.*]] = load i64, ptr [[GEP_6]], align 4
+; CHECK-NEXT:    [[ADD_7:%.*]] = add nuw nsw i64 [[ADD_6]], [[LD7]]
+; CHECK-NEXT:    ret i64 [[ADD_7]]
+;
+entry:
+  %ld0 = load i64, ptr %ptr
+  %gep = getelementptr inbounds i64, ptr %ptr, i64 1
+  %ld1 = load i64, ptr %gep
+  %add.1 = add nuw nsw i64 %ld0, %ld1
+  %gep.1 = getelementptr inbounds i64, ptr %ptr, i64 2
+  %ld2 = load i64, ptr %gep.1
+  %add.2 = add nuw nsw i64 %add.1, %ld2
+  %gep.2 = getelementptr inbounds i64, ptr %ptr, i64 3
+  %ld3 = load i64, ptr %gep.2
+  %add.3 = add nuw nsw i64 %add.2, %ld3
+  %gep.3 = getelementptr inbounds i64, ptr %ptr, i64 4
+  %ld4 = load i64, ptr %gep.3
+  %add.4 = add nuw nsw i64 %add.3, %ld4
+  %gep.4 = getelementptr inbounds i64, ptr %ptr, i64 5
+  %ld5 = load i64, ptr %gep.4
+  %add.5 = add nuw nsw i64 %add.4, %ld5
+  %gep.5 = getelementptr inbounds i64, ptr %ptr, i64 6
+  %ld6 = load i64, ptr %gep.5
+  %add.6 = add nuw nsw i64 %add.5, %ld6
+  %gep.6 = getelementptr inbounds i64, ptr %ptr, i64 7
+  %ld7 = load i64, ptr %gep.6
+  %add.7 = add nuw nsw i64 %add.6, %ld7
+  ret i64 %add.7
+}
+
+define i64 @red_ld_16xi64(ptr %ptr) {
+; CHECK-LABEL: @red_ld_16xi64(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[LD0:%.*]] = load i64, ptr [[PTR:%.*]], align 4
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 1
+; CHECK-NEXT:    [[LD1:%.*]] = load i64, ptr [[GEP]], align 4
+; CHECK-NEXT:    [[ADD_1:%.*]] = add nuw nsw i64 [[LD0]], [[LD1]]
+; CHECK-NEXT:    [[GEP_1:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 2
+; CHECK-NEXT:    [[LD2:%.*]] = load i64, ptr [[GEP_1]], align 4
+; CHECK-NEXT:    [[ADD_2:%.*]] = add nuw nsw i64 [[ADD_1]], [[LD2]]
+; CHECK-NEXT:    [[GEP_2:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 3
+; CHECK-NEXT:    [[LD3:%.*]] = load i64, ptr [[GEP_2]], align 4
+; CHECK-NEXT:    [[ADD_3:%.*]] = add nuw nsw i64 [[ADD_2]], [[LD3]]
+; CHECK-NEXT:    [[GEP_3:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 4
+; CHECK-NEXT:    [[LD4:%.*]] = load i64, ptr [[GEP_3]], align 4
+; CHECK-NEXT:    [[ADD_4:%.*]] = add nuw nsw i64 [[ADD_3]], [[LD4]]
+; CHECK-NEXT:    [[GEP_4:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 5
+; CHECK-NEXT:    [[LD5:%.*]] = load i64, ptr [[GEP_4]], align 4
+; CHECK-NEXT:    [[ADD_5:%.*]] = add nuw nsw i64 [[ADD_4]], [[LD5]]
+; CHECK-NEXT:    [[GEP_5:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 6
+; CHECK-NEXT:    [[LD6:%.*]] = load i64, ptr [[GEP_5]], align 4
+; CHECK-NEXT:    [[ADD_6:%.*]] = add nuw nsw i64 [[ADD_5]], [[LD6]]
+; CHECK-NEXT:    [[GEP_6:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 7
+; CHECK-NEXT:    [[LD7:%.*]] = load i64, ptr [[GEP_6]], align 4
+; CHECK-NEXT:    [[ADD_7:%.*]] = add nuw nsw i64 [[ADD_6]], [[LD7]]
+; CHECK-NEXT:    [[GEP_7:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 8
+; CHECK-NEXT:    [[LD8:%.*]] = load i64, ptr [[GEP_7]], align 4
+; CHECK-NEXT:    [[ADD_8:%.*]] = add nuw nsw i64 [[ADD_7]], [[LD8]]
+; CHECK-NEXT:    [[GEP_8:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 9
+; CHECK-NEXT:    [[LD9:%.*]] = load i64, ptr [[GEP_8]], align 4
+; CHECK-NEXT:    [[ADD_9:%.*]] = add nuw nsw i64 [[ADD_8]], [[LD9]]
+; CHECK-NEXT:    [[GEP_9:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 10
+; CHECK-NEXT:    [[LD10:%.*]] = load i64, ptr [[GEP_9]], align 4
+; CHECK-NEXT:    [[ADD_10:%.*]] = add nuw nsw i64 [[ADD_9]], [[LD10]]
+; CHECK-NEXT:    [[GEP_10:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 11
+; CHECK-NEXT:    [[LD11:%.*]] = load i64, ptr [[GEP_10]], align 4
+; CHECK-NEXT:    [[ADD_11:%.*]] = add nuw nsw i64 [[ADD_10]], [[LD11]]
+; CHECK-NEXT:    [[GEP_11:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 12
+; CHECK-NEXT:    [[LD12:%.*]] = load i64, ptr [[GEP_11]], align 4
+; CHECK-NEXT:    [[ADD_12:%.*]] = add nuw nsw i64 [[ADD_11]], [[LD12]]
+; CHECK-NEXT:    [[GEP_12:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 13
+; CHECK-NEXT:    [[LD13:%.*]] = load i64, ptr [[GEP_12]], align 4
+; CHECK-NEXT:    [[ADD_13:%.*]] = add nuw nsw i64 [[ADD_12]], [[LD13]]
+; CHECK-NEXT:    [[GEP_13:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 14
+; CHECK-NEXT:    [[LD14:%.*]] = load i64, ptr [[GEP_13]], align 4
+; CHECK-NEXT:    [[ADD_14:%.*]] = add nuw nsw i64 [[ADD_13]], [[LD14]]
+; CHECK-NEXT:    [[GEP_14:%.*]] = getelementptr inbounds i64, ptr [[PTR]], i64 15
+; CHECK-NEXT:    [[LD15:%.*]] = load i64, ptr [[GEP_14]], align 4
+; CHECK-NEXT:    [[ADD_15:%.*]] = add nuw nsw i64 [[ADD_14]], [[LD15]]
+; CHECK-NEXT:    ret i64 [[ADD_15]]
+;
+entry:
+  %ld0 = load i64, ptr %ptr
+  %gep = getelementptr inbounds i64, ptr %ptr, i64 1
+  %ld1 = load i64, ptr %gep
+  %add.1 = add nuw nsw i64 %ld0, %ld1
+  %gep.1 = getelementptr inbounds i64, ptr %ptr, i64 2
+  %ld2 = load i64, ptr %gep.1
+  %add.2 = add nuw nsw i64 %add.1, %ld2
+  %gep.2 = getelementptr inbounds i64, ptr %ptr, i64 3
+  %ld3 = load i64, ptr %gep.2
+  %add.3 = add nuw nsw i64 %add.2, %ld3
+  %gep.3 = getelementptr inbounds i64, ptr %ptr, i64 4
+  %ld4 = load i64, ptr %gep.3
+  %add.4 = add nuw nsw i64 %add.3, %ld4
+  %gep.4 = getelementptr inbounds i64, ptr %ptr, i64 5
+  %ld5 = load i64, ptr %gep.4
+  %add.5 = add nuw nsw i64 %add.4, %ld5
+  %gep.5 = getelementptr inbounds i64, ptr %ptr, i64 6
+  %ld6 = load i64, ptr %gep.5
+  %add.6 = add nuw nsw i64 %add.5, %ld6
+  %gep.6 = getelementptr inbounds i64, ptr %ptr, i64 7
+  %ld7 = load i64, ptr %gep.6
+  %add.7 = add nuw nsw i64 %add.6, %ld7
+  %gep.7 = getelementptr inbounds i64, ptr %ptr, i64 8
+  %ld8 = load i64, ptr %gep.7
+  %add.8 = add nuw nsw i64 %add.7, %ld8
+  %gep.8 = getelementptr inbounds i64, ptr %ptr, i64 9
+  %ld9 = load i64, ptr %gep.8
+  %add.9 = add nuw nsw i64 %add.8, %ld9
+  %gep.9 = getelementptr inbounds i64, ptr %ptr, i64 10
+  %ld10 = load i64, ptr %gep.9
+  %add.10 = add nuw nsw i64 %add.9, %ld10
+  %gep.10 = getelementptr inbounds i64, ptr %ptr, i64 11
+  %ld11 = load i64, ptr %gep.10
+  %add.11 = add nuw nsw i64 %add.10, %ld11
+  %gep.11 = getelementptr inbounds i64, ptr %ptr, i64 12
+  %ld12 = load i64, ptr %gep.11
+  %add.12 = add nuw nsw i64 %add.11, %ld12
+  %gep.12 = getelementptr inbounds i64, ptr %ptr, i64 13
+  %ld13 = load i64, ptr %gep.12
+  %add.13 = add nuw nsw i64 %add.12, %ld13
+  %gep.13 = getelementptr inbounds i64, ptr %ptr, i64 14
+  %ld14 = load i64, ptr %gep.13
+  %add.14 = add nuw nsw i64 %add.13, %ld14
+  %gep.14 = getelementptr inbounds i64, ptr %ptr, i64 15
+  %ld15 = load i64, ptr %gep.14
+  %add.15 = add nuw nsw i64 %add.14, %ld15
+  ret i64 %add.15
+}