diff --git a/llvm/test/Transforms/SLPVectorizer/AArch64/load-used-by-two-stores.ll b/llvm/test/Transforms/SLPVectorizer/AArch64/load-used-by-two-stores.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/SLPVectorizer/AArch64/load-used-by-two-stores.ll
@@ -0,0 +1,219 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -slp-vectorizer -S < %s -mtriple=aarch64-- | FileCheck %s
+
+; This test check that we can vectorize the simple pattern of a load with more
+; than one store user:
+;   L0       L1
+;  /  \     /  \
+; S0  S'0  S1  S'1
+
+define void @load_used_by_two_stores_double(double *%ptr) {
+; CHECK-LABEL: @load_used_by_two_stores_double(
+; CHECK-NEXT:    [[GEP0:%.*]] = getelementptr inbounds double, double* [[PTR:%.*]], i64 0
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr inbounds double, double* [[PTR]], i64 1
+; CHECK-NEXT:    [[LD0:%.*]] = load double, double* [[GEP0]], align 8
+; CHECK-NEXT:    [[LD1:%.*]] = load double, double* [[GEP1]], align 8
+; CHECK-NEXT:    store double [[LD0]], double* [[GEP0]], align 8
+; CHECK-NEXT:    store double [[LD1]], double* [[GEP1]], align 8
+; CHECK-NEXT:    store double [[LD0]], double* [[GEP0]], align 8
+; CHECK-NEXT:    store double [[LD1]], double* [[GEP1]], align 8
+; CHECK-NEXT:    ret void
+;
+  %gep0 = getelementptr inbounds double, double* %ptr, i64 0
+  %gep1 = getelementptr inbounds double, double* %ptr, i64 1
+  %ld0 = load double, double *%gep0, align 8
+  %ld1 = load double, double *%gep1, align 8
+
+  store double %ld0, double *%gep0, align 8
+  store double %ld1, double *%gep1, align 8
+
+  store double %ld0, double *%gep0, align 8
+  store double %ld1, double *%gep1, align 8
+  ret void
+}
+
+define void @load_used_by_two_stores_i32(i32 *%ptr) {
+; CHECK-LABEL: @load_used_by_two_stores_i32(
+; CHECK-NEXT:    [[GEP0:%.*]] = getelementptr inbounds i32, i32* [[PTR:%.*]], i64 0
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr inbounds i32, i32* [[PTR]], i64 1
+; CHECK-NEXT:    [[GEP2:%.*]] = getelementptr inbounds i32, i32* [[PTR]], i64 2
+; CHECK-NEXT:    [[GEP3:%.*]] = getelementptr inbounds i32, i32* [[PTR]], i64 3
+; CHECK-NEXT:    [[LD0:%.*]] = load i32, i32* [[GEP0]], align 8
+; CHECK-NEXT:    [[LD1:%.*]] = load i32, i32* [[GEP1]], align 8
+; CHECK-NEXT:    [[LD2:%.*]] = load i32, i32* [[GEP2]], align 8
+; CHECK-NEXT:    [[LD3:%.*]] = load i32, i32* [[GEP3]], align 8
+; CHECK-NEXT:    store i32 [[LD0]], i32* [[GEP0]], align 8
+; CHECK-NEXT:    store i32 [[LD1]], i32* [[GEP1]], align 8
+; CHECK-NEXT:    store i32 [[LD2]], i32* [[GEP2]], align 8
+; CHECK-NEXT:    store i32 [[LD3]], i32* [[GEP3]], align 8
+; CHECK-NEXT:    store i32 [[LD0]], i32* [[GEP0]], align 8
+; CHECK-NEXT:    store i32 [[LD1]], i32* [[GEP1]], align 8
+; CHECK-NEXT:    store i32 [[LD2]], i32* [[GEP2]], align 8
+; CHECK-NEXT:    store i32 [[LD3]], i32* [[GEP3]], align 8
+; CHECK-NEXT:    ret void
+;
+  %gep0 = getelementptr inbounds i32, i32* %ptr, i64 0
+  %gep1 = getelementptr inbounds i32, i32* %ptr, i64 1
+  %gep2 = getelementptr inbounds i32, i32* %ptr, i64 2
+  %gep3 = getelementptr inbounds i32, i32* %ptr, i64 3
+
+  %ld0 = load i32, i32 *%gep0, align 8
+  %ld1 = load i32, i32 *%gep1, align 8
+  %ld2 = load i32, i32 *%gep2, align 8
+  %ld3 = load i32, i32 *%gep3, align 8
+
+
+  store i32 %ld0, i32 *%gep0, align 8
+  store i32 %ld1, i32 *%gep1, align 8
+  store i32 %ld2, i32 *%gep2, align 8
+  store i32 %ld3, i32 *%gep3, align 8
+
+
+  store i32 %ld0, i32 *%gep0, align 8
+  store i32 %ld1, i32 *%gep1, align 8
+  store i32 %ld2, i32 *%gep2, align 8
+  store i32 %ld3, i32 *%gep3, align 8
+
+  ret void
+}
+
+define void @load_used_by_two_stores_i8(i8 *%ptr) {
+; CHECK-LABEL: @load_used_by_two_stores_i8(
+; CHECK-NEXT:    [[GEP0:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 0
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 1
+; CHECK-NEXT:    [[GEP2:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 2
+; CHECK-NEXT:    [[GEP3:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 3
+; CHECK-NEXT:    [[GEP4:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 4
+; CHECK-NEXT:    [[GEP5:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 5
+; CHECK-NEXT:    [[GEP6:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 6
+; CHECK-NEXT:    [[GEP7:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 7
+; CHECK-NEXT:    [[GEP8:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 8
+; CHECK-NEXT:    [[GEP9:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 9
+; CHECK-NEXT:    [[GEP10:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 10
+; CHECK-NEXT:    [[GEP11:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 11
+; CHECK-NEXT:    [[GEP12:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 12
+; CHECK-NEXT:    [[GEP13:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 13
+; CHECK-NEXT:    [[GEP14:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 14
+; CHECK-NEXT:    [[GEP15:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 15
+; CHECK-NEXT:    [[LD0:%.*]] = load i8, i8* [[GEP0]], align 8
+; CHECK-NEXT:    [[LD1:%.*]] = load i8, i8* [[GEP1]], align 8
+; CHECK-NEXT:    [[LD2:%.*]] = load i8, i8* [[GEP2]], align 8
+; CHECK-NEXT:    [[LD3:%.*]] = load i8, i8* [[GEP3]], align 8
+; CHECK-NEXT:    [[LD4:%.*]] = load i8, i8* [[GEP4]], align 8
+; CHECK-NEXT:    [[LD5:%.*]] = load i8, i8* [[GEP5]], align 8
+; CHECK-NEXT:    [[LD6:%.*]] = load i8, i8* [[GEP6]], align 8
+; CHECK-NEXT:    [[LD7:%.*]] = load i8, i8* [[GEP7]], align 8
+; CHECK-NEXT:    [[LD8:%.*]] = load i8, i8* [[GEP8]], align 8
+; CHECK-NEXT:    [[LD9:%.*]] = load i8, i8* [[GEP9]], align 8
+; CHECK-NEXT:    [[LD10:%.*]] = load i8, i8* [[GEP10]], align 8
+; CHECK-NEXT:    [[LD11:%.*]] = load i8, i8* [[GEP11]], align 8
+; CHECK-NEXT:    [[LD12:%.*]] = load i8, i8* [[GEP12]], align 8
+; CHECK-NEXT:    [[LD13:%.*]] = load i8, i8* [[GEP13]], align 8
+; CHECK-NEXT:    [[LD14:%.*]] = load i8, i8* [[GEP14]], align 8
+; CHECK-NEXT:    [[LD15:%.*]] = load i8, i8* [[GEP15]], align 8
+; CHECK-NEXT:    store i8 [[LD0]], i8* [[GEP0]], align 8
+; CHECK-NEXT:    store i8 [[LD1]], i8* [[GEP1]], align 8
+; CHECK-NEXT:    store i8 [[LD2]], i8* [[GEP2]], align 8
+; CHECK-NEXT:    store i8 [[LD3]], i8* [[GEP3]], align 8
+; CHECK-NEXT:    store i8 [[LD4]], i8* [[GEP4]], align 8
+; CHECK-NEXT:    store i8 [[LD5]], i8* [[GEP5]], align 8
+; CHECK-NEXT:    store i8 [[LD6]], i8* [[GEP6]], align 8
+; CHECK-NEXT:    store i8 [[LD7]], i8* [[GEP7]], align 8
+; CHECK-NEXT:    store i8 [[LD8]], i8* [[GEP8]], align 8
+; CHECK-NEXT:    store i8 [[LD9]], i8* [[GEP9]], align 8
+; CHECK-NEXT:    store i8 [[LD10]], i8* [[GEP10]], align 8
+; CHECK-NEXT:    store i8 [[LD11]], i8* [[GEP11]], align 8
+; CHECK-NEXT:    store i8 [[LD12]], i8* [[GEP12]], align 8
+; CHECK-NEXT:    store i8 [[LD13]], i8* [[GEP13]], align 8
+; CHECK-NEXT:    store i8 [[LD14]], i8* [[GEP14]], align 8
+; CHECK-NEXT:    store i8 [[LD15]], i8* [[GEP15]], align 8
+; CHECK-NEXT:    store i8 [[LD0]], i8* [[GEP0]], align 8
+; CHECK-NEXT:    store i8 [[LD1]], i8* [[GEP1]], align 8
+; CHECK-NEXT:    store i8 [[LD2]], i8* [[GEP2]], align 8
+; CHECK-NEXT:    store i8 [[LD3]], i8* [[GEP3]], align 8
+; CHECK-NEXT:    store i8 [[LD4]], i8* [[GEP4]], align 8
+; CHECK-NEXT:    store i8 [[LD5]], i8* [[GEP5]], align 8
+; CHECK-NEXT:    store i8 [[LD6]], i8* [[GEP6]], align 8
+; CHECK-NEXT:    store i8 [[LD7]], i8* [[GEP7]], align 8
+; CHECK-NEXT:    store i8 [[LD8]], i8* [[GEP8]], align 8
+; CHECK-NEXT:    store i8 [[LD9]], i8* [[GEP9]], align 8
+; CHECK-NEXT:    store i8 [[LD10]], i8* [[GEP10]], align 8
+; CHECK-NEXT:    store i8 [[LD11]], i8* [[GEP11]], align 8
+; CHECK-NEXT:    store i8 [[LD12]], i8* [[GEP12]], align 8
+; CHECK-NEXT:    store i8 [[LD13]], i8* [[GEP13]], align 8
+; CHECK-NEXT:    store i8 [[LD14]], i8* [[GEP14]], align 8
+; CHECK-NEXT:    store i8 [[LD15]], i8* [[GEP15]], align 8
+; CHECK-NEXT:    ret void
+;
+  %gep0 = getelementptr inbounds i8, i8* %ptr, i64 0
+  %gep1 = getelementptr inbounds i8, i8* %ptr, i64 1
+  %gep2 = getelementptr inbounds i8, i8* %ptr, i64 2
+  %gep3 = getelementptr inbounds i8, i8* %ptr, i64 3
+  %gep4 = getelementptr inbounds i8, i8* %ptr, i64 4
+  %gep5 = getelementptr inbounds i8, i8* %ptr, i64 5
+  %gep6 = getelementptr inbounds i8, i8* %ptr, i64 6
+  %gep7 = getelementptr inbounds i8, i8* %ptr, i64 7
+  %gep8 = getelementptr inbounds i8, i8* %ptr, i64 8
+  %gep9 = getelementptr inbounds i8, i8* %ptr, i64 9
+  %gep10 = getelementptr inbounds i8, i8* %ptr, i64 10
+  %gep11 = getelementptr inbounds i8, i8* %ptr, i64 11
+  %gep12 = getelementptr inbounds i8, i8* %ptr, i64 12
+  %gep13 = getelementptr inbounds i8, i8* %ptr, i64 13
+  %gep14 = getelementptr inbounds i8, i8* %ptr, i64 14
+  %gep15 = getelementptr inbounds i8, i8* %ptr, i64 15
+
+  %ld0 = load i8, i8 *%gep0, align 8
+  %ld1 = load i8, i8 *%gep1, align 8
+  %ld2 = load i8, i8 *%gep2, align 8
+  %ld3 = load i8, i8 *%gep3, align 8
+  %ld4 = load i8, i8 *%gep4, align 8
+  %ld5 = load i8, i8 *%gep5, align 8
+  %ld6 = load i8, i8 *%gep6, align 8
+  %ld7 = load i8, i8 *%gep7, align 8
+  %ld8 = load i8, i8 *%gep8, align 8
+  %ld9 = load i8, i8 *%gep9, align 8
+  %ld10 = load i8, i8 *%gep10, align 8
+  %ld11 = load i8, i8 *%gep11, align 8
+  %ld12 = load i8, i8 *%gep12, align 8
+  %ld13 = load i8, i8 *%gep13, align 8
+  %ld14 = load i8, i8 *%gep14, align 8
+  %ld15 = load i8, i8 *%gep15, align 8
+
+
+  store i8 %ld0, i8 *%gep0, align 8
+  store i8 %ld1, i8 *%gep1, align 8
+  store i8 %ld2, i8 *%gep2, align 8
+  store i8 %ld3, i8 *%gep3, align 8
+  store i8 %ld4, i8 *%gep4, align 8
+  store i8 %ld5, i8 *%gep5, align 8
+  store i8 %ld6, i8 *%gep6, align 8
+  store i8 %ld7, i8 *%gep7, align 8
+  store i8 %ld8, i8 *%gep8, align 8
+  store i8 %ld9, i8 *%gep9, align 8
+  store i8 %ld10, i8 *%gep10, align 8
+  store i8 %ld11, i8 *%gep11, align 8
+  store i8 %ld12, i8 *%gep12, align 8
+  store i8 %ld13, i8 *%gep13, align 8
+  store i8 %ld14, i8 *%gep14, align 8
+  store i8 %ld15, i8 *%gep15, align 8
+
+
+  store i8 %ld0, i8 *%gep0, align 8
+  store i8 %ld1, i8 *%gep1, align 8
+  store i8 %ld2, i8 *%gep2, align 8
+  store i8 %ld3, i8 *%gep3, align 8
+  store i8 %ld4, i8 *%gep4, align 8
+  store i8 %ld5, i8 *%gep5, align 8
+  store i8 %ld6, i8 *%gep6, align 8
+  store i8 %ld7, i8 *%gep7, align 8
+  store i8 %ld8, i8 *%gep8, align 8
+  store i8 %ld9, i8 *%gep9, align 8
+  store i8 %ld10, i8 *%gep10, align 8
+  store i8 %ld11, i8 *%gep11, align 8
+  store i8 %ld12, i8 *%gep12, align 8
+  store i8 %ld13, i8 *%gep13, align 8
+  store i8 %ld14, i8 *%gep14, align 8
+  store i8 %ld15, i8 *%gep15, align 8
+
+  ret void
+}