Index: llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -21121,14 +21121,17 @@
   // If we know required SrcValue1 and SrcValue2 have relatively large
   // alignment compared to the size and offset of the access, we may be able
   // to prove they do not alias. This check is conservative for now to catch
-  // cases created by splitting vector types.
+  // cases created by splitting vector types, it only works when the offsets are
+  // multiples of the size of the data.
   int64_t SrcValOffset0 = MUC0.MMO->getOffset();
   int64_t SrcValOffset1 = MUC1.MMO->getOffset();
   unsigned OrigAlignment0 = MUC0.MMO->getBaseAlignment();
   unsigned OrigAlignment1 = MUC1.MMO->getBaseAlignment();
   if (OrigAlignment0 == OrigAlignment1 && SrcValOffset0 != SrcValOffset1 &&
       MUC0.NumBytes.hasValue() && MUC1.NumBytes.hasValue() &&
-      *MUC0.NumBytes == *MUC1.NumBytes && OrigAlignment0 > *MUC0.NumBytes) {
+      *MUC0.NumBytes == *MUC1.NumBytes && OrigAlignment0 > *MUC0.NumBytes &&
+      SrcValOffset0 % *MUC0.NumBytes == 0 &&
+      SrcValOffset1 % *MUC0.NumBytes == 0) {
     int64_t OffAlign0 = SrcValOffset0 % OrigAlignment0;
     int64_t OffAlign1 = SrcValOffset1 % OrigAlignment1;
 
Index: llvm/test/CodeGen/ARM/memset-align.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/ARM/memset-align.ll
@@ -0,0 +1,39 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=thumbv8-unknown-linux-android10000 -o - | FileCheck %s
+
+%struct.af = type <{ i64, i64, i8, i8, i8, [5 x i8] }>
+
+define void @test() {
+; CHECK-LABEL: test:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    .save {r7, lr}
+; CHECK-NEXT:    push {r7, lr}
+; CHECK-NEXT:    .pad #24
+; CHECK-NEXT:    sub sp, #24
+; CHECK-NEXT:    mov r0, sp
+; CHECK-NEXT:    mov.w r1, #-1
+; CHECK-NEXT:    vmov.i32 q8, #0x0
+; CHECK-NEXT:    movs r2, #15
+; CHECK-NEXT:    mov r3, r0
+; CHECK-NEXT:    strd r1, r1, [sp, #8]
+; CHECK-NEXT:    strd r1, r1, [sp]
+; CHECK-NEXT:    str r1, [sp, #16]
+; CHECK-NEXT:    vst1.64 {d16, d17}, [r3], r2
+; CHECK-NEXT:    movs r2, #0
+; CHECK-NEXT:    str r2, [r3]
+; CHECK-NEXT:    str r1, [sp, #20]
+; CHECK-NEXT:    bl callee
+; CHECK-NEXT:    add sp, #24
+; CHECK-NEXT:    pop {r7, pc}
+entry:
+  %a = alloca %struct.af, align 8
+  %0 = bitcast %struct.af* %a to i8*
+  %1 = bitcast %struct.af* %a to i8*
+  call void @llvm.memset.p0i8.i64(i8* align 8 %1, i8 -1, i64 24, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 8 %0, i8 0, i64 19, i1 false)
+  call void @callee(%struct.af* %a)
+  ret void
+}
+
+declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1 immarg)
+declare void @callee(%struct.af*) local_unnamed_addr #1