diff --git a/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreBegin.ll b/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreBegin.ll
index 843436fd7dae..69615f52bbcd 100644
--- a/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreBegin.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreBegin.ll
@@ -1,12 +1,20 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -basicaa -dse -S | FileCheck %s
 
 define void @write4to7(i32* nocapture %p) {
 ; CHECK-LABEL: @write4to7(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[ARRAYIDX0:%.*]] = getelementptr inbounds i32, i32* [[P:%.*]], i64 1
+; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[ARRAYIDX0]] to i8*
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[P3]], i64 4
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 [[TMP0]], i8 0, i64 24, i1 false)
+; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 1
+; CHECK-NEXT:    store i32 1, i32* [[ARRAYIDX1]], align 4
+; CHECK-NEXT:    ret void
+;
 entry:
   %arrayidx0 = getelementptr inbounds i32, i32* %p, i64 1
   %p3 = bitcast i32* %arrayidx0 to i8*
-; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %p3, i64 4
-; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 [[GEP]], i8 0, i64 24, i1 false)
   call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 28, i1 false)
   %arrayidx1 = getelementptr inbounds i32, i32* %p, i64 1
   store i32 1, i32* %arrayidx1, align 4
@@ -15,10 +23,15 @@ entry:
 
 define void @write0to3(i32* nocapture %p) {
 ; CHECK-LABEL: @write0to3(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[P:%.*]] to i8*
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[P3]], i64 4
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 [[TMP0]], i8 0, i64 24, i1 false)
+; CHECK-NEXT:    store i32 1, i32* [[P]], align 4
+; CHECK-NEXT:    ret void
+;
 entry:
   %p3 = bitcast i32* %p to i8*
-; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %p3, i64 4
-; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 [[GEP]], i8 0, i64 24, i1 false)
   call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 28, i1 false)
   store i32 1, i32* %p, align 4
   ret void
@@ -26,10 +39,16 @@ entry:
 
 define void @write0to7(i32* nocapture %p) {
 ; CHECK-LABEL: @write0to7(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[P:%.*]] to i8*
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[P3]], i64 8
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 [[TMP0]], i8 0, i64 24, i1 false)
+; CHECK-NEXT:    [[P4:%.*]] = bitcast i32* [[P]] to i64*
+; CHECK-NEXT:    store i64 1, i64* [[P4]], align 8
+; CHECK-NEXT:    ret void
+;
 entry:
   %p3 = bitcast i32* %p to i8*
-; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %p3, i64 8
-; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 [[GEP]], i8 0, i64 24, i1 false)
   call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false)
   %p4 = bitcast i32* %p to i64*
   store i64 1, i64* %p4, align 8
@@ -38,11 +57,18 @@ entry:
 
 define void @write0to7_2(i32* nocapture %p) {
 ; CHECK-LABEL: @write0to7_2(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[ARRAYIDX0:%.*]] = getelementptr inbounds i32, i32* [[P:%.*]], i64 1
+; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[ARRAYIDX0]] to i8*
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[P3]], i64 4
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 [[TMP0]], i8 0, i64 24, i1 false)
+; CHECK-NEXT:    [[P4:%.*]] = bitcast i32* [[P]] to i64*
+; CHECK-NEXT:    store i64 1, i64* [[P4]], align 8
+; CHECK-NEXT:    ret void
+;
 entry:
   %arrayidx0 = getelementptr inbounds i32, i32* %p, i64 1
   %p3 = bitcast i32* %arrayidx0 to i8*
-; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %p3, i64 4
-; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 [[GEP]], i8 0, i64 24, i1 false)
   call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 28, i1 false)
   %p4 = bitcast i32* %p to i64*
   store i64 1, i64* %p4, align 8
@@ -53,9 +79,14 @@ entry:
 ; start pointer is changed.
 define void @dontwrite0to3_align8(i32* nocapture %p) {
 ; CHECK-LABEL: @dontwrite0to3_align8(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[P:%.*]] to i8*
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 8 [[P3]], i8 0, i64 32, i1 false)
+; CHECK-NEXT:    store i32 1, i32* [[P]], align 4
+; CHECK-NEXT:    ret void
+;
 entry:
   %p3 = bitcast i32* %p to i8*
-; CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 %p3, i8 0, i64 32, i1 false)
   call void @llvm.memset.p0i8.i64(i8* align 8 %p3, i8 0, i64 32, i1 false)
   store i32 1, i32* %p, align 4
   ret void
@@ -63,9 +94,15 @@ entry:
 
 define void @dontwrite0to1(i32* nocapture %p) {
 ; CHECK-LABEL: @dontwrite0to1(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[P:%.*]] to i8*
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 [[P3]], i8 0, i64 32, i1 false)
+; CHECK-NEXT:    [[P4:%.*]] = bitcast i32* [[P]] to i16*
+; CHECK-NEXT:    store i16 1, i16* [[P4]], align 4
+; CHECK-NEXT:    ret void
+;
 entry:
   %p3 = bitcast i32* %p to i8*
-; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false)
   call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false)
   %p4 = bitcast i32* %p to i16*
   store i16 1, i16* %p4, align 4
@@ -74,10 +111,19 @@ entry:
 
 define void @dontwrite2to9(i32* nocapture %p) {
 ; CHECK-LABEL: @dontwrite2to9(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[ARRAYIDX0:%.*]] = getelementptr inbounds i32, i32* [[P:%.*]], i64 1
+; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[ARRAYIDX0]] to i8*
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 [[P3]], i8 0, i64 32, i1 false)
+; CHECK-NEXT:    [[P4:%.*]] = bitcast i32* [[P]] to i16*
+; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i16, i16* [[P4]], i64 1
+; CHECK-NEXT:    [[P5:%.*]] = bitcast i16* [[ARRAYIDX2]] to i64*
+; CHECK-NEXT:    store i64 1, i64* [[P5]], align 8
+; CHECK-NEXT:    ret void
+;
 entry:
   %arrayidx0 = getelementptr inbounds i32, i32* %p, i64 1
   %p3 = bitcast i32* %arrayidx0 to i8*
-; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false)
   call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false)
   %p4 = bitcast i32* %p to i16*
   %arrayidx2 = getelementptr inbounds i16, i16* %p4, i64 1
@@ -87,10 +133,19 @@ entry:
 }
 
 define void @write8To15AndThen0To7(i64* nocapture %P) {
-entry:
 ; CHECK-LABEL: @write8To15AndThen0To7(
-; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %mybase0, i64 16
-; CHECK: tail call void @llvm.memset.p0i8.i64(i8* align 8 [[GEP]], i8 0, i64 16, i1 false)
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[BASE0:%.*]] = bitcast i64* [[P:%.*]] to i8*
+; CHECK-NEXT:    [[MYBASE0:%.*]] = getelementptr inbounds i8, i8* [[BASE0]], i64 0
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[MYBASE0]], i64 16
+; CHECK-NEXT:    tail call void @llvm.memset.p0i8.i64(i8* align 8 [[TMP0]], i8 0, i64 16, i1 false)
+; CHECK-NEXT:    [[BASE64_0:%.*]] = getelementptr inbounds i64, i64* [[P]], i64 0
+; CHECK-NEXT:    [[BASE64_1:%.*]] = getelementptr inbounds i64, i64* [[P]], i64 1
+; CHECK-NEXT:    store i64 1, i64* [[BASE64_1]]
+; CHECK-NEXT:    store i64 2, i64* [[BASE64_0]]
+; CHECK-NEXT:    ret void
+;
+entry:
 
   %base0 = bitcast i64* %P to i8*
   %mybase0 = getelementptr inbounds i8, i8* %base0, i64 0
diff --git a/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreEnd.ll b/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreEnd.ll
index 7743c619ae18..00282e0648a9 100644
--- a/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreEnd.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreEnd.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -basicaa -dse -S | FileCheck %s
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 
@@ -9,10 +10,17 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3
 
 define void @write24to28(i32* nocapture %p) nounwind uwtable ssp {
 ; CHECK-LABEL: @write24to28(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[ARRAYIDX0:%.*]] = getelementptr inbounds i32, i32* [[P:%.*]], i64 1
+; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[ARRAYIDX0]] to i8*
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 [[P3]], i8 0, i64 24, i1 false)
+; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 7
+; CHECK-NEXT:    store i32 1, i32* [[ARRAYIDX1]], align 4
+; CHECK-NEXT:    ret void
+;
 entry:
   %arrayidx0 = getelementptr inbounds i32, i32* %p, i64 1
   %p3 = bitcast i32* %arrayidx0 to i8*
-; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 24, i1 false)
   call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 28, i1 false)
   %arrayidx1 = getelementptr inbounds i32, i32* %p, i64 7
   store i32 1, i32* %arrayidx1, align 4
@@ -21,9 +29,15 @@ entry:
 
 define void @write28to32(i32* nocapture %p) nounwind uwtable ssp {
 ; CHECK-LABEL: @write28to32(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[P:%.*]] to i8*
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 [[P3]], i8 0, i64 28, i1 false)
+; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 7
+; CHECK-NEXT:    store i32 1, i32* [[ARRAYIDX1]], align 4
+; CHECK-NEXT:    ret void
+;
 entry:
   %p3 = bitcast i32* %p to i8*
-; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 28, i1 false)
   call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false)
   %arrayidx1 = getelementptr inbounds i32, i32* %p, i64 7
   store i32 1, i32* %arrayidx1, align 4
@@ -32,9 +46,15 @@ entry:
 
 define void @dontwrite28to32memset(i32* nocapture %p) nounwind uwtable ssp {
 ; CHECK-LABEL: @dontwrite28to32memset(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[P:%.*]] to i8*
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 16 [[P3]], i8 0, i64 32, i1 false)
+; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 7
+; CHECK-NEXT:    store i32 1, i32* [[ARRAYIDX1]], align 4
+; CHECK-NEXT:    ret void
+;
 entry:
   %p3 = bitcast i32* %p to i8*
-; CHECK: call void @llvm.memset.p0i8.i64(i8* align 16 %p3, i8 0, i64 32, i1 false)
   call void @llvm.memset.p0i8.i64(i8* align 16 %p3, i8 0, i64 32, i1 false)
   %arrayidx1 = getelementptr inbounds i32, i32* %p, i64 7
   store i32 1, i32* %arrayidx1, align 4
@@ -43,9 +63,15 @@ entry:
 
 define void @write32to36(%struct.vec2plusi* nocapture %p) nounwind uwtable ssp {
 ; CHECK-LABEL: @write32to36(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast %struct.vec2plusi* [[P:%.*]] to i8*
+; CHECK-NEXT:    tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 [[TMP0]], i8* align 16 bitcast (%struct.vec2plusi* @glob2 to i8*), i64 32, i1 false)
+; CHECK-NEXT:    [[C:%.*]] = getelementptr inbounds [[STRUCT_VEC2PLUSI:%.*]], %struct.vec2plusi* [[P]], i64 0, i32 2
+; CHECK-NEXT:    store i32 1, i32* [[C]], align 4
+; CHECK-NEXT:    ret void
+;
 entry:
   %0 = bitcast %struct.vec2plusi* %p to i8*
-; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2plusi* @glob2 to i8*), i64 32, i1 false)
   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2plusi* @glob2 to i8*), i64 36, i1 false)
   %c = getelementptr inbounds %struct.vec2plusi, %struct.vec2plusi* %p, i64 0, i32 2
   store i32 1, i32* %c, align 4
@@ -54,9 +80,15 @@ entry:
 
 define void @write16to32(%struct.vec2* nocapture %p) nounwind uwtable ssp {
 ; CHECK-LABEL: @write16to32(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast %struct.vec2* [[P:%.*]] to i8*
+; CHECK-NEXT:    tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 [[TMP0]], i8* align 16 bitcast (%struct.vec2* @glob1 to i8*), i64 16, i1 false)
+; CHECK-NEXT:    [[C:%.*]] = getelementptr inbounds [[STRUCT_VEC2:%.*]], %struct.vec2* [[P]], i64 0, i32 1
+; CHECK-NEXT:    store <4 x i32> <i32 1, i32 2, i32 3, i32 4>, <4 x i32>* [[C]], align 4
+; CHECK-NEXT:    ret void
+;
 entry:
   %0 = bitcast %struct.vec2* %p to i8*
-; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2* @glob1 to i8*), i64 16, i1 false)
   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2* @glob1 to i8*), i64 32, i1 false)
   %c = getelementptr inbounds %struct.vec2, %struct.vec2* %p, i64 0, i32 1
   store <4 x i32> <i32 1, i32 2, i32 3, i32 4>, <4 x i32>* %c, align 4
@@ -65,9 +97,15 @@ entry:
 
 define void @dontwrite28to32memcpy(%struct.vec2* nocapture %p) nounwind uwtable ssp {
 ; CHECK-LABEL: @dontwrite28to32memcpy(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast %struct.vec2* [[P:%.*]] to i8*
+; CHECK-NEXT:    tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 [[TMP0]], i8* align 16 bitcast (%struct.vec2* @glob1 to i8*), i64 32, i1 false)
+; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds [[STRUCT_VEC2:%.*]], %struct.vec2* [[P]], i64 0, i32 0, i64 7
+; CHECK-NEXT:    store i32 1, i32* [[ARRAYIDX1]], align 4
+; CHECK-NEXT:    ret void
+;
 entry:
   %0 = bitcast %struct.vec2* %p to i8*
-; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2* @glob1 to i8*), i64 32, i1 false)
   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2* @glob1 to i8*), i64 32, i1 false)
   %arrayidx1 = getelementptr inbounds %struct.vec2, %struct.vec2* %p, i64 0, i32 0, i64 7
   store i32 1, i32* %arrayidx1, align 4
@@ -80,14 +118,23 @@ declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
 %struct.trapframe = type { i64, i64, i64 }
 
 ; bugzilla 11455 - make sure negative GEP's don't break this optimisation
-; CHECK-LABEL: @cpu_lwp_fork(
 define void @cpu_lwp_fork(%struct.trapframe* %md_regs, i64 %pcb_rsp0) nounwind uwtable noinline ssp {
+; CHECK-LABEL: @cpu_lwp_fork(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = inttoptr i64 [[PCB_RSP0:%.*]] to %struct.trapframe*
+; CHECK-NEXT:    [[ADD_PTR:%.*]] = getelementptr inbounds [[STRUCT_TRAPFRAME:%.*]], %struct.trapframe* [[TMP0]], i64 -1
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast %struct.trapframe* [[ADD_PTR]] to i8*
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast %struct.trapframe* [[MD_REGS:%.*]] to i8*
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[TMP1]], i8* [[TMP2]], i64 24, i1 false)
+; CHECK-NEXT:    [[TF_TRAPNO:%.*]] = getelementptr inbounds [[STRUCT_TRAPFRAME]], %struct.trapframe* [[TMP0]], i64 -1, i32 1
+; CHECK-NEXT:    store i64 3, i64* [[TF_TRAPNO]], align 8
+; CHECK-NEXT:    ret void
+;
 entry:
   %0 = inttoptr i64 %pcb_rsp0 to %struct.trapframe*
   %add.ptr = getelementptr inbounds %struct.trapframe, %struct.trapframe* %0, i64 -1
   %1 = bitcast %struct.trapframe* %add.ptr to i8*
   %2 = bitcast %struct.trapframe* %md_regs to i8*
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %1, i8* %2, i64 24, i1 false)
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* %1, i8* %2, i64 24, i1 false)
   %tf_trapno = getelementptr inbounds %struct.trapframe, %struct.trapframe* %0, i64 -1, i32 1
   store i64 3, i64* %tf_trapno, align 8
@@ -95,9 +142,18 @@ entry:
 }
 
 define void @write16To23AndThen24To31(i64* nocapture %P, i64 %n64, i32 %n32, i16 %n16, i8 %n8) {
-entry:
 ; CHECK-LABEL: @write16To23AndThen24To31(
-; CHECK: tail call void @llvm.memset.p0i8.i64(i8* align 8 %mybase0, i8 0, i64 16, i1 false)
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[BASE0:%.*]] = bitcast i64* [[P:%.*]] to i8*
+; CHECK-NEXT:    [[MYBASE0:%.*]] = getelementptr inbounds i8, i8* [[BASE0]], i64 0
+; CHECK-NEXT:    tail call void @llvm.memset.p0i8.i64(i8* align 8 [[MYBASE0]], i8 0, i64 16, i1 false)
+; CHECK-NEXT:    [[BASE64_2:%.*]] = getelementptr inbounds i64, i64* [[P]], i64 2
+; CHECK-NEXT:    [[BASE64_3:%.*]] = getelementptr inbounds i64, i64* [[P]], i64 3
+; CHECK-NEXT:    store i64 3, i64* [[BASE64_2]]
+; CHECK-NEXT:    store i64 3, i64* [[BASE64_3]]
+; CHECK-NEXT:    ret void
+;
+entry:
 
   %base0 = bitcast i64* %P to i8*
   %mybase0 = getelementptr inbounds i8, i8* %base0, i64 0