diff --git a/llvm/test/Transforms/LoopVectorize/X86/invariant-store-vectorization.ll b/llvm/test/Transforms/LoopVectorize/X86/invariant-store-vectorization.ll
index 69f578cf789eb..6ba61396afd40 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/invariant-store-vectorization.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/invariant-store-vectorization.ll
@@ -6,39 +6,106 @@ target triple = "x86_64-unknown-linux-gnu"
 
 ; first test checks that loop with a reduction and a uniform store gets
 ; vectorized.
-; CHECK-LABEL: inv_val_store_to_inv_address_with_reduction
-; CHECK-LABEL: vector.memcheck:
-; CHECK:    found.conflict
 
-; CHECK-LABEL: vector.body:
-; CHECK:         %vec.phi = phi <16 x i32>  [ zeroinitializer, %vector.ph ], [ [[ADD:%[a-zA-Z0-9.]+]], %vector.body ]
-; CHECK:         %wide.load = load <16 x i32>
-; CHECK:         [[ADD]] = add <16 x i32> %vec.phi, %wide.load
-; CHECK:         store i32 %ntrunc, i32* %a
-; CHECK-NOT:     store i32 %ntrunc, i32* %a
-; CHECK:         %index.next = add i64 %index, 64
-
-; CHECK-LABEL: middle.block:
-; CHECK:         %rdx.shuf = shufflevector <16 x i32>
 define i32 @inv_val_store_to_inv_address_with_reduction(i32* %a, i64 %n, i32* %b) {
+; CHECK-LABEL: @inv_val_store_to_inv_address_with_reduction(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[NTRUNC:%.*]] = trunc i64 [[N:%.*]] to i32
+; CHECK-NEXT:    [[TMP0:%.*]] = icmp sgt i64 [[N]], 1
+; CHECK-NEXT:    [[SMAX:%.*]] = select i1 [[TMP0]], i64 [[N]], i64 1
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[SMAX]], 64
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
+; CHECK:       vector.memcheck:
+; CHECK-NEXT:    [[B2:%.*]] = bitcast i32* [[B:%.*]] to i8*
+; CHECK-NEXT:    [[A1:%.*]] = bitcast i32* [[A:%.*]] to i8*
+; CHECK-NEXT:    [[UGLYGEP:%.*]] = getelementptr i8, i8* [[A1]], i64 1
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp sgt i64 [[N]], 1
+; CHECK-NEXT:    [[SMAX3:%.*]] = select i1 [[TMP1]], i64 [[N]], i64 1
+; CHECK-NEXT:    [[SCEVGEP:%.*]] = getelementptr i32, i32* [[B]], i64 [[SMAX3]]
+; CHECK-NEXT:    [[BOUND0:%.*]] = icmp ugt i32* [[SCEVGEP]], [[A]]
+; CHECK-NEXT:    [[BOUND1:%.*]] = icmp ugt i8* [[UGLYGEP]], [[B2]]
+; CHECK-NEXT:    [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
+; CHECK-NEXT:    br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[N_VEC:%.*]] = and i64 [[SMAX]], 9223372036854775744
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <16 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP10:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI5:%.*]] = phi <16 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP11:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI6:%.*]] = phi <16 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP12:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI7:%.*]] = phi <16 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP13:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <16 x i32>*
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i32>, <16 x i32>* [[TMP3]], align 8, !alias.scope !0
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[TMP2]], i64 16
+; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i32* [[TMP4]] to <16 x i32>*
+; CHECK-NEXT:    [[WIDE_LOAD8:%.*]] = load <16 x i32>, <16 x i32>* [[TMP5]], align 8, !alias.scope !0
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TMP2]], i64 32
+; CHECK-NEXT:    [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <16 x i32>*
+; CHECK-NEXT:    [[WIDE_LOAD9:%.*]] = load <16 x i32>, <16 x i32>* [[TMP7]], align 8, !alias.scope !0
+; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[TMP2]], i64 48
+; CHECK-NEXT:    [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <16 x i32>*
+; CHECK-NEXT:    [[WIDE_LOAD10:%.*]] = load <16 x i32>, <16 x i32>* [[TMP9]], align 8, !alias.scope !0
+; CHECK-NEXT:    [[TMP10]] = add <16 x i32> [[VEC_PHI]], [[WIDE_LOAD]]
+; CHECK-NEXT:    [[TMP11]] = add <16 x i32> [[VEC_PHI5]], [[WIDE_LOAD8]]
+; CHECK-NEXT:    [[TMP12]] = add <16 x i32> [[VEC_PHI6]], [[WIDE_LOAD9]]
+; CHECK-NEXT:    [[TMP13]] = add <16 x i32> [[VEC_PHI7]], [[WIDE_LOAD10]]
+; CHECK-NEXT:    store i32 [[NTRUNC]], i32* [[A]], align 4, !alias.scope !3, !noalias !0
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 64
+; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !5
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[BIN_RDX:%.*]] = add <16 x i32> [[TMP11]], [[TMP10]]
+; CHECK-NEXT:    [[BIN_RDX11:%.*]] = add <16 x i32> [[TMP12]], [[BIN_RDX]]
+; CHECK-NEXT:    [[BIN_RDX12:%.*]] = add <16 x i32> [[TMP13]], [[BIN_RDX11]]
+; CHECK-NEXT:    [[RDX_SHUF:%.*]] = shufflevector <16 x i32> [[BIN_RDX12]], <16 x i32> undef, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT:    [[BIN_RDX13:%.*]] = add <16 x i32> [[BIN_RDX12]], [[RDX_SHUF]]
+; CHECK-NEXT:    [[RDX_SHUF14:%.*]] = shufflevector <16 x i32> [[BIN_RDX13]], <16 x i32> undef, <16 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT:    [[BIN_RDX15:%.*]] = add <16 x i32> [[BIN_RDX13]], [[RDX_SHUF14]]
+; CHECK-NEXT:    [[RDX_SHUF16:%.*]] = shufflevector <16 x i32> [[BIN_RDX15]], <16 x i32> undef, <16 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT:    [[BIN_RDX17:%.*]] = add <16 x i32> [[BIN_RDX15]], [[RDX_SHUF16]]
+; CHECK-NEXT:    [[RDX_SHUF18:%.*]] = shufflevector <16 x i32> [[BIN_RDX17]], <16 x i32> undef, <16 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT:    [[BIN_RDX19:%.*]] = add <16 x i32> [[BIN_RDX17]], [[RDX_SHUF18]]
+; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <16 x i32> [[BIN_RDX19]], i32 0
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[SMAX]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_MEMCHECK]] ]
+; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP15]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ], [ 0, [[VECTOR_MEMCHECK]] ]
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[I_NEXT:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[T0:%.*]] = phi i32 [ [[T3:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[T1:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[I]]
+; CHECK-NEXT:    [[T2:%.*]] = load i32, i32* [[T1]], align 8
+; CHECK-NEXT:    [[T3]] = add i32 [[T0]], [[T2]]
+; CHECK-NEXT:    store i32 [[NTRUNC]], i32* [[A]], align 4
+; CHECK-NEXT:    [[I_NEXT]] = add nuw nsw i64 [[I]], 1
+; CHECK-NEXT:    [[COND:%.*]] = icmp slt i64 [[I_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[COND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop !7
+; CHECK:       for.end:
+; CHECK-NEXT:    [[T4:%.*]] = phi i32 [ [[T3]], [[FOR_BODY]] ], [ [[TMP15]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    ret i32 [[T4]]
+;
 entry:
   %ntrunc = trunc i64 %n to i32
   br label %for.body
 
 for.body:                                         ; preds = %for.body, %entry
   %i = phi i64 [ %i.next, %for.body ], [ 0, %entry ]
-  %tmp0 = phi i32 [ %tmp3, %for.body ], [ 0, %entry ]
-  %tmp1 = getelementptr inbounds i32, i32* %b, i64 %i
-  %tmp2 = load i32, i32* %tmp1, align 8
-  %tmp3 = add i32 %tmp0, %tmp2
+  %t0 = phi i32 [ %t3, %for.body ], [ 0, %entry ]
+  %t1 = getelementptr inbounds i32, i32* %b, i64 %i
+  %t2 = load i32, i32* %t1, align 8
+  %t3 = add i32 %t0, %t2
   store i32 %ntrunc, i32* %a
   %i.next = add nuw nsw i64 %i, 1
   %cond = icmp slt i64 %i.next, %n
   br i1 %cond, label %for.body, label %for.end
 
 for.end:                                          ; preds = %for.body
-  %tmp4 = phi i32 [ %tmp3, %for.body ]
-  ret i32 %tmp4
+  %t4 = phi i32 [ %t3, %for.body ]
+  ret i32 %t4
 }
 
 ; Conditional store
@@ -64,22 +131,22 @@ define void @inv_val_store_to_inv_address_conditional(i32* %a, i64 %n, i32* %b,
 ; CHECK-NEXT:    br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[N_VEC:%.*]] = and i64 [[SMAX]], 9223372036854775792
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <16 x i32> undef, i32 [[K:%.*]], i32 0
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <16 x i32> undef, i32 [[K:%.*]], i32 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x i32> [[BROADCAST_SPLATINSERT]], <16 x i32> undef, <16 x i32> zeroinitializer
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <16 x i32> undef, i32 [[NTRUNC]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT6:%.*]] = shufflevector <16 x i32> [[BROADCAST_SPLATINSERT5]], <16 x i32> undef, <16 x i32> zeroinitializer
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT7:%.*]] = insertelement <16 x i32> undef, i32 [[NTRUNC]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT8:%.*]] = shufflevector <16 x i32> [[BROADCAST_SPLATINSERT7]], <16 x i32> undef, <16 x i32> zeroinitializer
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT9:%.*]] = insertelement <16 x i32*> undef, i32* [[A]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT10:%.*]] = shufflevector <16 x i32*> [[BROADCAST_SPLATINSERT9]], <16 x i32*> undef, <16 x i32> zeroinitializer
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT7:%.*]] = insertelement <16 x i32*> undef, i32* [[A]], i32 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT8:%.*]] = shufflevector <16 x i32*> [[BROADCAST_SPLATINSERT7]], <16 x i32*> undef, <16 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDEX]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <16 x i32>*
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i32>, <16 x i32>* [[TMP3]], align 8, !alias.scope !8, !noalias !11
-; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq <16 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT6]]
+; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq <16 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i32* [[TMP2]] to <16 x i32>*
-; CHECK-NEXT:    store <16 x i32> [[BROADCAST_SPLAT8]], <16 x i32>* [[TMP5]], align 4, !alias.scope !8, !noalias !11
-; CHECK-NEXT:    call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> [[BROADCAST_SPLAT8]], <16 x i32*> [[BROADCAST_SPLAT10]], i32 4, <16 x i1> [[TMP4]]), !alias.scope !11
+; CHECK-NEXT:    store <16 x i32> [[BROADCAST_SPLAT6]], <16 x i32>* [[TMP5]], align 4, !alias.scope !8, !noalias !11
+; CHECK-NEXT:    call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> [[BROADCAST_SPLAT6]], <16 x i32*> [[BROADCAST_SPLAT8]], i32 4, <16 x i1> [[TMP4]]), !alias.scope !11
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 16
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !13
@@ -91,10 +158,10 @@ define void @inv_val_store_to_inv_address_conditional(i32* %a, i64 %n, i32* %b,
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[I_NEXT:%.*]], [[LATCH:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
-; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[I]]
-; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[TMP1]], align 8
-; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[TMP2]], [[K]]
-; CHECK-NEXT:    store i32 [[NTRUNC]], i32* [[TMP1]], align 4
+; CHECK-NEXT:    [[T1:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[I]]
+; CHECK-NEXT:    [[T2:%.*]] = load i32, i32* [[T1]], align 8
+; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[T2]], [[K]]
+; CHECK-NEXT:    store i32 [[NTRUNC]], i32* [[T1]], align 4
 ; CHECK-NEXT:    br i1 [[CMP]], label [[COND_STORE:%.*]], label [[LATCH]]
 ; CHECK:       cond_store:
 ; CHECK-NEXT:    store i32 [[NTRUNC]], i32* [[A]], align 4
@@ -112,10 +179,10 @@ entry:
 
 for.body:                                         ; preds = %for.body, %entry
   %i = phi i64 [ %i.next, %latch ], [ 0, %entry ]
-  %tmp1 = getelementptr inbounds i32, i32* %b, i64 %i
-  %tmp2 = load i32, i32* %tmp1, align 8
-  %cmp = icmp eq i32 %tmp2, %k
-  store i32 %ntrunc, i32* %tmp1
+  %t1 = getelementptr inbounds i32, i32* %b, i64 %i
+  %t2 = load i32, i32* %t1, align 8
+  %cmp = icmp eq i32 %t2, %k
+  store i32 %ntrunc, i32* %t1
   br i1 %cmp, label %cond_store, label %latch
 
 cond_store:
@@ -162,25 +229,25 @@ define void @variant_val_store_to_inv_address_conditional(i32* %a, i64 %n, i32*
 ; CHECK-NEXT:    br i1 [[CONFLICT_RDX15]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[N_VEC:%.*]] = and i64 [[SMAX]], 9223372036854775792
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT16:%.*]] = insertelement <16 x i32> undef, i32 [[K:%.*]], i32 0
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <16 x i32> undef, i32 [[K:%.*]], i32 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x i32> [[BROADCAST_SPLATINSERT]], <16 x i32> undef, <16 x i32> zeroinitializer
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT16:%.*]] = insertelement <16 x i32> undef, i32 [[NTRUNC]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT17:%.*]] = shufflevector <16 x i32> [[BROADCAST_SPLATINSERT16]], <16 x i32> undef, <16 x i32> zeroinitializer
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT18:%.*]] = insertelement <16 x i32> undef, i32 [[NTRUNC]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT19:%.*]] = shufflevector <16 x i32> [[BROADCAST_SPLATINSERT18]], <16 x i32> undef, <16 x i32> zeroinitializer
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT20:%.*]] = insertelement <16 x i32*> undef, i32* [[A]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT21:%.*]] = shufflevector <16 x i32*> [[BROADCAST_SPLATINSERT20]], <16 x i32*> undef, <16 x i32> zeroinitializer
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT18:%.*]] = insertelement <16 x i32*> undef, i32* [[A]], i32 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT19:%.*]] = shufflevector <16 x i32*> [[BROADCAST_SPLATINSERT18]], <16 x i32*> undef, <16 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDEX]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <16 x i32>*
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i32>, <16 x i32>* [[TMP3]], align 8, !alias.scope !15, !noalias !18
-; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq <16 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT17]]
+; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq <16 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i32* [[TMP2]] to <16 x i32>*
-; CHECK-NEXT:    store <16 x i32> [[BROADCAST_SPLAT19]], <16 x i32>* [[TMP5]], align 4, !alias.scope !15, !noalias !18
+; CHECK-NEXT:    store <16 x i32> [[BROADCAST_SPLAT17]], <16 x i32>* [[TMP5]], align 4, !alias.scope !15, !noalias !18
 ; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 [[INDEX]]
 ; CHECK-NEXT:    [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <16 x i32>*
 ; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* [[TMP7]], i32 8, <16 x i1> [[TMP4]], <16 x i32> undef), !alias.scope !21
-; CHECK-NEXT:    call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> [[WIDE_MASKED_LOAD]], <16 x i32*> [[BROADCAST_SPLAT21]], i32 4, <16 x i1> [[TMP4]]), !alias.scope !22, !noalias !21
+; CHECK-NEXT:    call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> [[WIDE_MASKED_LOAD]], <16 x i32*> [[BROADCAST_SPLAT19]], i32 4, <16 x i1> [[TMP4]]), !alias.scope !22, !noalias !21
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 16
 ; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !23
@@ -192,15 +259,15 @@ define void @variant_val_store_to_inv_address_conditional(i32* %a, i64 %n, i32*
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[I_NEXT:%.*]], [[LATCH:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
-; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[I]]
-; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[TMP1]], align 8
-; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[TMP2]], [[K]]
-; CHECK-NEXT:    store i32 [[NTRUNC]], i32* [[TMP1]], align 4
+; CHECK-NEXT:    [[T1:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[I]]
+; CHECK-NEXT:    [[T2:%.*]] = load i32, i32* [[T1]], align 8
+; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[T2]], [[K]]
+; CHECK-NEXT:    store i32 [[NTRUNC]], i32* [[T1]], align 4
 ; CHECK-NEXT:    br i1 [[CMP]], label [[COND_STORE:%.*]], label [[LATCH]]
 ; CHECK:       cond_store:
-; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 [[I]]
-; CHECK-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP3]], align 8
-; CHECK-NEXT:    store i32 [[TMP4]], i32* [[A]], align 4
+; CHECK-NEXT:    [[T3:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 [[I]]
+; CHECK-NEXT:    [[T4:%.*]] = load i32, i32* [[T3]], align 8
+; CHECK-NEXT:    store i32 [[T4]], i32* [[A]], align 4
 ; CHECK-NEXT:    br label [[LATCH]]
 ; CHECK:       latch:
 ; CHECK-NEXT:    [[I_NEXT]] = add nuw nsw i64 [[I]], 1
@@ -215,16 +282,16 @@ entry:
 
 for.body:                                         ; preds = %for.body, %entry
   %i = phi i64 [ %i.next, %latch ], [ 0, %entry ]
-  %tmp1 = getelementptr inbounds i32, i32* %b, i64 %i
-  %tmp2 = load i32, i32* %tmp1, align 8
-  %cmp = icmp eq i32 %tmp2, %k
-  store i32 %ntrunc, i32* %tmp1
+  %t1 = getelementptr inbounds i32, i32* %b, i64 %i
+  %t2 = load i32, i32* %t1, align 8
+  %cmp = icmp eq i32 %t2, %k
+  store i32 %ntrunc, i32* %t1
   br i1 %cmp, label %cond_store, label %latch
 
 cond_store:
-  %tmp3 = getelementptr inbounds i32, i32* %c, i64 %i
-  %tmp4 = load i32, i32* %tmp3, align 8
-  store i32 %tmp4, i32* %a
+  %t3 = getelementptr inbounds i32, i32* %c, i64 %i
+  %t4 = load i32, i32* %t3, align 8
+  store i32 %t4, i32* %a
   br label %latch
 
 latch: