diff --git a/llvm/lib/Transforms/Scalar/LoopFlatten.cpp b/llvm/lib/Transforms/Scalar/LoopFlatten.cpp
index 04039b885f3c5..5d98bcd4927f6 100644
--- a/llvm/lib/Transforms/Scalar/LoopFlatten.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopFlatten.cpp
@@ -835,9 +835,39 @@ static bool DoFlattenLoopPair(FlattenInfo &FI, DominatorTree *DT, LoopInfo *LI,
   return true;
 }
 
+static bool VersionLoop(FlattenInfo &FI, DominatorTree *DT, LoopInfo *LI,
+                        ScalarEvolution *SE, const LoopAccessInfo &LAI) {
+
+  // Version the loop. The overflow check isn't a runtime pointer check, so we
+  // pass an empty list of runtime pointer checks, causing LoopVersioning to
+  // emit 'false' as the branch condition, and add our own check afterwards.
+  BasicBlock *CheckBlock = FI.OuterLoop->getLoopPreheader();
+  ArrayRef<RuntimePointerCheck> Checks(nullptr, nullptr);
+  LoopVersioning LVer(LAI, Checks, FI.OuterLoop, LI, DT, SE);
+  LVer.versionLoop();
+
+  // Check for overflow by calculating the new tripcount using
+  // umul_with_overflow and then checking if it overflowed.
+  BranchInst *Br = dyn_cast<BranchInst>(CheckBlock->getTerminator());
+  if (!Br || !Br->isConditional())
+    return false;
+  if (!match(Br->getCondition(), m_Zero()))
+    return false;
+  IRBuilder<> Builder(Br);
+  Value *Call = Builder.CreateIntrinsic(Intrinsic::umul_with_overflow,
+                                        FI.OuterTripCount->getType(),
+                                        {FI.OuterTripCount, FI.InnerTripCount},
+                                        /*FMFSource=*/nullptr, "flatten.mul");
+  FI.NewTripCount = Builder.CreateExtractValue(Call, 0, "flatten.tripcount");
+  Value *Overflow = Builder.CreateExtractValue(Call, 1, "flatten.overflow");
+  Br->setCondition(Overflow);
+  return true;
+}
+
 static bool CanWidenIV(FlattenInfo &FI, DominatorTree *DT, LoopInfo *LI,
                        ScalarEvolution *SE, AssumptionCache *AC,
-                       const TargetTransformInfo *TTI) {
+                       const TargetTransformInfo *TTI,
+                       const LoopAccessInfo &LAI) {
   if (!WidenIV) {
     LLVM_DEBUG(dbgs() << "Widening the IVs is disabled\n");
     return false;
@@ -916,7 +946,7 @@ static bool FlattenLoopPair(FlattenInfo &FI, DominatorTree *DT, LoopInfo *LI,
     return false;
 
   // Check if we can widen the induction variables to avoid overflow checks.
-  bool CanFlatten = CanWidenIV(FI, DT, LI, SE, AC, TTI);
+  bool CanFlatten = CanWidenIV(FI, DT, LI, SE, AC, TTI, LAI);
 
   // It can happen that after widening of the IV, flattening may not be
   // possible/happening, e.g. when it is deemed unprofitable. So bail here if
@@ -961,30 +991,8 @@ static bool FlattenLoopPair(FlattenInfo &FI, DominatorTree *DT, LoopInfo *LI,
       return false;
     }
     LLVM_DEBUG(dbgs() << "Multiply might overflow, versioning loop\n");
-
-    // Version the loop. The overflow check isn't a runtime pointer check, so we
-    // pass an empty list of runtime pointer checks, causing LoopVersioning to
-    // emit 'false' as the branch condition, and add our own check afterwards.
-    BasicBlock *CheckBlock = FI.OuterLoop->getLoopPreheader();
-    ArrayRef<RuntimePointerCheck> Checks(nullptr, nullptr);
-    LoopVersioning LVer(LAI, Checks, FI.OuterLoop, LI, DT, SE);
-    LVer.versionLoop();
-
-    // Check for overflow by calculating the new tripcount using
-    // umul_with_overflow and then checking if it overflowed.
-    BranchInst *Br = cast<BranchInst>(CheckBlock->getTerminator());
-    assert(Br->isConditional() &&
-           "Expected LoopVersioning to generate a conditional branch");
-    assert(match(Br->getCondition(), m_Zero()) &&
-           "Expected branch condition to be false");
-    IRBuilder<> Builder(Br);
-    Value *Call = Builder.CreateIntrinsic(
-        Intrinsic::umul_with_overflow, FI.OuterTripCount->getType(),
-        {FI.OuterTripCount, FI.InnerTripCount},
-        /*FMFSource=*/nullptr, "flatten.mul");
-    FI.NewTripCount = Builder.CreateExtractValue(Call, 0, "flatten.tripcount");
-    Value *Overflow = Builder.CreateExtractValue(Call, 1, "flatten.overflow");
-    Br->setCondition(Overflow);
+    bool LoopIsVersioned = VersionLoop(FI, DT, LI, SE, LAI);
+    assert(LoopIsVersioned && "Failed to version loop");
   } else {
     LLVM_DEBUG(dbgs() << "Multiply cannot overflow, modifying loop in-place\n");
   }
diff --git a/llvm/test/Transforms/LoopFlatten/loop-flatten-version.ll b/llvm/test/Transforms/LoopFlatten/loop-flatten-version.ll
index 85072bf3a43f4..0842f049feb11 100644
--- a/llvm/test/Transforms/LoopFlatten/loop-flatten-version.ll
+++ b/llvm/test/Transforms/LoopFlatten/loop-flatten-version.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
 ; RUN: opt %s -S -passes='loop(loop-flatten),verify' -verify-loop-info -verify-dom-info -verify-scev -o - | FileCheck %s
+; RUN: opt %s -S -passes='loop(loop-flatten),verify' -loop-flatten-widen-iv=false -loop-flatten-version-loops=true -verify-loop-info -verify-dom-info -verify-scev -o - | FileCheck %s --check-prefix=CHECK-VERSION-OVER-WIDEN
 
 target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
 
@@ -61,6 +62,62 @@ define void @noinbounds_gep(i32 %N, ptr %A) {
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret void
 ;
+; CHECK-VERSION-OVER-WIDEN-LABEL: define void @noinbounds_gep(
+; CHECK-VERSION-OVER-WIDEN-SAME: i32 [[N:%.*]], ptr [[A:%.*]]) {
+; CHECK-VERSION-OVER-WIDEN-NEXT:  entry:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP3:%.*]] = icmp ult i32 0, [[N]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[CMP3]], label [[FOR_INNER_PREHEADER_LVER_CHECK:%.*]], label [[FOR_END:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.inner.preheader.lver.check:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[FLATTEN_MUL:%.*]] = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 [[N]], i32 [[N]])
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[FLATTEN_TRIPCOUNT:%.*]] = extractvalue { i32, i1 } [[FLATTEN_MUL]], 0
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[FLATTEN_OVERFLOW:%.*]] = extractvalue { i32, i1 } [[FLATTEN_MUL]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[FLATTEN_OVERFLOW]], label [[FOR_INNER_PREHEADER_PH_LVER_ORIG:%.*]], label [[FOR_INNER_PREHEADER_PH:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.inner.preheader.ph.lver.orig:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_INNER_PREHEADER_LVER_ORIG:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.inner.preheader.lver.orig:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[I_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_INNER_PREHEADER_PH_LVER_ORIG]] ], [ [[INC2_LVER_ORIG:%.*]], [[FOR_OUTER_LVER_ORIG:%.*]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_INNER_LVER_ORIG:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.inner.lver.orig:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[J_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_INNER_PREHEADER_LVER_ORIG]] ], [ [[INC1_LVER_ORIG:%.*]], [[FOR_INNER_LVER_ORIG]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[MUL_LVER_ORIG:%.*]] = mul i32 [[I_LVER_ORIG]], [[N]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[GEP_LVER_ORIG:%.*]] = getelementptr i32, ptr [[A]], i32 [[MUL_LVER_ORIG]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[ARRAYIDX_LVER_ORIG:%.*]] = getelementptr i32, ptr [[GEP_LVER_ORIG]], i32 [[J_LVER_ORIG]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    store i32 0, ptr [[ARRAYIDX_LVER_ORIG]], align 4
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC1_LVER_ORIG]] = add nuw i32 [[J_LVER_ORIG]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP2_LVER_ORIG:%.*]] = icmp ult i32 [[INC1_LVER_ORIG]], [[N]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[CMP2_LVER_ORIG]], label [[FOR_INNER_LVER_ORIG]], label [[FOR_OUTER_LVER_ORIG]]
+; CHECK-VERSION-OVER-WIDEN:       for.outer.lver.orig:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC2_LVER_ORIG]] = add i32 [[I_LVER_ORIG]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP1_LVER_ORIG:%.*]] = icmp ult i32 [[INC2_LVER_ORIG]], [[N]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[CMP1_LVER_ORIG]], label [[FOR_INNER_PREHEADER_LVER_ORIG]], label [[FOR_END_LOOPEXIT_LOOPEXIT:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.inner.preheader.ph:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_INNER_PREHEADER:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.inner.preheader:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[I:%.*]] = phi i32 [ 0, [[FOR_INNER_PREHEADER_PH]] ], [ [[INC2:%.*]], [[FOR_OUTER:%.*]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[FLATTEN_ARRAYIDX:%.*]] = getelementptr i32, ptr [[A]], i32 [[I]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_INNER:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.inner:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[J:%.*]] = phi i32 [ 0, [[FOR_INNER_PREHEADER]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[MUL:%.*]] = mul i32 [[I]], [[N]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[GEP:%.*]] = getelementptr i32, ptr [[A]], i32 [[MUL]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[ARRAYIDX:%.*]] = getelementptr i32, ptr [[GEP]], i32 [[J]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    store i32 0, ptr [[FLATTEN_ARRAYIDX]], align 4
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC1:%.*]] = add nuw i32 [[J]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP2:%.*]] = icmp ult i32 [[INC1]], [[N]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_OUTER]]
+; CHECK-VERSION-OVER-WIDEN:       for.outer:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC2]] = add i32 [[I]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP1:%.*]] = icmp ult i32 [[INC2]], [[FLATTEN_TRIPCOUNT]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[CMP1]], label [[FOR_INNER_PREHEADER]], label [[FOR_END_LOOPEXIT_LOOPEXIT1:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.end.loopexit.loopexit:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_END_LOOPEXIT:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.end.loopexit.loopexit1:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_END_LOOPEXIT]]
+; CHECK-VERSION-OVER-WIDEN:       for.end.loopexit:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_END]]
+; CHECK-VERSION-OVER-WIDEN:       for.end:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    ret void
+;
 entry:
   %cmp3 = icmp ult i32 0, %N
   br i1 %cmp3, label %for.outer.preheader, label %for.end
@@ -124,6 +181,34 @@ define void @noinbounds_gep_too_large_mul(i64 %N, ptr %A) {
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret void
 ;
+; CHECK-VERSION-OVER-WIDEN-LABEL: define void @noinbounds_gep_too_large_mul(
+; CHECK-VERSION-OVER-WIDEN-SAME: i64 [[N:%.*]], ptr [[A:%.*]]) {
+; CHECK-VERSION-OVER-WIDEN-NEXT:  entry:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP3:%.*]] = icmp ult i64 0, [[N]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[CMP3]], label [[FOR_INNER_PREHEADER_PH:%.*]], label [[FOR_END:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.outer.preheader:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_INNER_PREHEADER:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.inner.preheader:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[I:%.*]] = phi i64 [ 0, [[FOR_INNER_PREHEADER_PH]] ], [ [[INC2:%.*]], [[FOR_OUTER:%.*]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_INNER:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.inner:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[J:%.*]] = phi i64 [ 0, [[FOR_INNER_PREHEADER]] ], [ [[INC1:%.*]], [[FOR_INNER]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[MUL:%.*]] = mul i64 [[I]], [[N]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[GEP:%.*]] = getelementptr i32, ptr [[A]], i64 [[MUL]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[ARRAYIDX:%.*]] = getelementptr i32, ptr [[GEP]], i64 [[J]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    store i32 0, ptr [[ARRAYIDX]], align 4
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC1]] = add nuw i64 [[J]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP2:%.*]] = icmp ult i64 [[INC1]], [[N]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[CMP2]], label [[FOR_INNER]], label [[FOR_OUTER]]
+; CHECK-VERSION-OVER-WIDEN:       for.outer:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC2]] = add i64 [[I]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP1:%.*]] = icmp ult i64 [[INC2]], [[N]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[CMP1]], label [[FOR_INNER_PREHEADER]], label [[FOR_END_LOOPEXIT_LOOPEXIT1:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.end.loopexit:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_END]]
+; CHECK-VERSION-OVER-WIDEN:       for.end:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    ret void
+;
 entry:
   %cmp3 = icmp ult i64 0, %N
   br i1 %cmp3, label %for.outer.preheader, label %for.end
@@ -238,6 +323,79 @@ define void @d3_2(ptr %A, i32 %N, i32 %M) {
 ; CHECK:       for.cond.cleanup:
 ; CHECK-NEXT:    ret void
 ;
+; CHECK-VERSION-OVER-WIDEN-LABEL: define void @d3_2(
+; CHECK-VERSION-OVER-WIDEN-SAME: ptr [[A:%.*]], i32 [[N:%.*]], i32 [[M:%.*]]) {
+; CHECK-VERSION-OVER-WIDEN-NEXT:  entry:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP30:%.*]] = icmp sgt i32 [[N]], 0
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[CMP30]], label [[FOR_COND1_PREHEADER_LR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond1.preheader.lr.ph:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP625:%.*]] = icmp sgt i32 [[M]], 0
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND1_PREHEADER_US:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond1.preheader.us:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[K_031_US:%.*]] = phi i32 [ 0, [[FOR_COND1_PREHEADER_LR_PH]] ], [ [[INC13_US:%.*]], [[FOR_COND1_FOR_COND_CLEANUP3_CRIT_EDGE_US:%.*]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[CMP625]], label [[FOR_COND5_PREHEADER_US_US_LVER_CHECK:%.*]], label [[FOR_COND5_PREHEADER_US43_PREHEADER:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond5.preheader.us43.preheader:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND1_FOR_COND_CLEANUP3_CRIT_EDGE_US_LOOPEXIT50:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond5.preheader.us.us.lver.check:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[FLATTEN_MUL:%.*]] = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 [[N]], i32 [[M]])
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[FLATTEN_TRIPCOUNT:%.*]] = extractvalue { i32, i1 } [[FLATTEN_MUL]], 0
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[FLATTEN_OVERFLOW:%.*]] = extractvalue { i32, i1 } [[FLATTEN_MUL]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[FLATTEN_OVERFLOW]], label [[FOR_COND5_PREHEADER_US_US_PH_LVER_ORIG:%.*]], label [[FOR_COND5_PREHEADER_US_US_PH:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond5.preheader.us.us.ph.lver.orig:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND5_PREHEADER_US_US_LVER_ORIG:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond5.preheader.us.us.lver.orig:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[I_028_US_US_LVER_ORIG:%.*]] = phi i32 [ [[INC10_US_US_LVER_ORIG:%.*]], [[FOR_COND5_FOR_COND_CLEANUP7_CRIT_EDGE_US_US_LVER_ORIG:%.*]] ], [ 0, [[FOR_COND5_PREHEADER_US_US_PH_LVER_ORIG]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[MUL_US_US_LVER_ORIG:%.*]] = mul nsw i32 [[I_028_US_US_LVER_ORIG]], [[M]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_BODY8_US_US_LVER_ORIG:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.body8.us.us.lver.orig:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[J_026_US_US_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_COND5_PREHEADER_US_US_LVER_ORIG]] ], [ [[INC_US_US_LVER_ORIG:%.*]], [[FOR_BODY8_US_US_LVER_ORIG]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[ADD_US_US_LVER_ORIG:%.*]] = add nsw i32 [[J_026_US_US_LVER_ORIG]], [[MUL_US_US_LVER_ORIG]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[IDXPROM_US_US_LVER_ORIG:%.*]] = sext i32 [[ADD_US_US_LVER_ORIG]] to i64
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[ARRAYIDX_US_US_LVER_ORIG:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IDXPROM_US_US_LVER_ORIG]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    tail call void @f(ptr [[ARRAYIDX_US_US_LVER_ORIG]])
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC_US_US_LVER_ORIG]] = add nuw nsw i32 [[J_026_US_US_LVER_ORIG]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[EXITCOND_LVER_ORIG:%.*]] = icmp ne i32 [[INC_US_US_LVER_ORIG]], [[M]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[EXITCOND_LVER_ORIG]], label [[FOR_BODY8_US_US_LVER_ORIG]], label [[FOR_COND5_FOR_COND_CLEANUP7_CRIT_EDGE_US_US_LVER_ORIG]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond5.for.cond.cleanup7_crit_edge.us.us.lver.orig:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC10_US_US_LVER_ORIG]] = add nuw nsw i32 [[I_028_US_US_LVER_ORIG]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[EXITCOND51_LVER_ORIG:%.*]] = icmp ne i32 [[INC10_US_US_LVER_ORIG]], [[N]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[EXITCOND51_LVER_ORIG]], label [[FOR_COND5_PREHEADER_US_US_LVER_ORIG]], label [[FOR_COND1_FOR_COND_CLEANUP3_CRIT_EDGE_US_LOOPEXIT_LOOPEXIT:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond5.preheader.us.us.ph:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND5_PREHEADER_US_US:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond1.for.cond.cleanup3_crit_edge.us.loopexit.loopexit:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND1_FOR_COND_CLEANUP3_CRIT_EDGE_US_LOOPEXIT:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond1.for.cond.cleanup3_crit_edge.us.loopexit.loopexit1:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND1_FOR_COND_CLEANUP3_CRIT_EDGE_US_LOOPEXIT]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond1.for.cond.cleanup3_crit_edge.us.loopexit:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND1_FOR_COND_CLEANUP3_CRIT_EDGE_US]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond1.for.cond.cleanup3_crit_edge.us.loopexit50:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND1_FOR_COND_CLEANUP3_CRIT_EDGE_US]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond1.for.cond.cleanup3_crit_edge.us:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC13_US]] = add nuw nsw i32 [[K_031_US]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[EXITCOND52:%.*]] = icmp ne i32 [[INC13_US]], [[N]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[EXITCOND52]], label [[FOR_COND1_PREHEADER_US]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond5.preheader.us.us:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[I_028_US_US:%.*]] = phi i32 [ [[INC10_US_US:%.*]], [[FOR_COND5_FOR_COND_CLEANUP7_CRIT_EDGE_US_US:%.*]] ], [ 0, [[FOR_COND5_PREHEADER_US_US_PH]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[MUL_US_US:%.*]] = mul nsw i32 [[I_028_US_US]], [[M]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_BODY8_US_US:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond5.for.cond.cleanup7_crit_edge.us.us:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC10_US_US]] = add nuw nsw i32 [[I_028_US_US]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[EXITCOND51:%.*]] = icmp ne i32 [[INC10_US_US]], [[FLATTEN_TRIPCOUNT]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[EXITCOND51]], label [[FOR_COND5_PREHEADER_US_US]], label [[FOR_COND1_FOR_COND_CLEANUP3_CRIT_EDGE_US_LOOPEXIT_LOOPEXIT1:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.body8.us.us:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[J_026_US_US:%.*]] = phi i32 [ 0, [[FOR_COND5_PREHEADER_US_US]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[ADD_US_US:%.*]] = add nsw i32 [[J_026_US_US]], [[MUL_US_US]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[IDXPROM_US_US:%.*]] = sext i32 [[I_028_US_US]] to i64
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[ARRAYIDX_US_US:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IDXPROM_US_US]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    tail call void @f(ptr [[ARRAYIDX_US_US]])
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC_US_US:%.*]] = add nuw nsw i32 [[J_026_US_US]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[INC_US_US]], [[M]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND5_FOR_COND_CLEANUP7_CRIT_EDGE_US_US]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond.cleanup.loopexit:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND_CLEANUP]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond.cleanup:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    ret void
+;
 entry:
   %cmp30 = icmp sgt i32 %N, 0
   br i1 %cmp30, label %for.cond1.preheader.lr.ph, label %for.cond.cleanup
@@ -371,6 +529,79 @@ define void @overflow(i32 %lim, ptr %a) {
 ; CHECK-NEXT:    [[CMP2:%.*]] = icmp ult i32 [[J_016]], 99999
 ; CHECK-NEXT:    br label [[FOR_COND_CLEANUP3]]
 ;
+; CHECK-VERSION-OVER-WIDEN-LABEL: define void @overflow(
+; CHECK-VERSION-OVER-WIDEN-SAME: i32 [[LIM:%.*]], ptr [[A:%.*]]) {
+; CHECK-VERSION-OVER-WIDEN-NEXT:  entry:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP17_NOT:%.*]] = icmp eq i32 [[LIM]], 0
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[CMP17_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_COND1_PREHEADER_LVER_CHECK:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond1.preheader.lver.check:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[FLATTEN_MUL:%.*]] = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 [[LIM]], i32 100000)
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[FLATTEN_TRIPCOUNT:%.*]] = extractvalue { i32, i1 } [[FLATTEN_MUL]], 0
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[FLATTEN_OVERFLOW:%.*]] = extractvalue { i32, i1 } [[FLATTEN_MUL]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[FLATTEN_OVERFLOW]], label [[FOR_COND1_PREHEADER_PH_LVER_ORIG:%.*]], label [[FOR_COND1_PREHEADER_PH:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond1.preheader.ph.lver.orig:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND1_PREHEADER_LVER_ORIG:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond1.preheader.lver.orig:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[I_018_LVER_ORIG:%.*]] = phi i32 [ [[INC6_LVER_ORIG:%.*]], [[FOR_COND_CLEANUP3_LVER_ORIG:%.*]] ], [ 0, [[FOR_COND1_PREHEADER_PH_LVER_ORIG]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[MUL_LVER_ORIG:%.*]] = mul i32 [[I_018_LVER_ORIG]], 100000
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_BODY4_LVER_ORIG:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.body4.lver.orig:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[J_016_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_COND1_PREHEADER_LVER_ORIG]] ], [ [[INC_LVER_ORIG:%.*]], [[IF_END_LVER_ORIG:%.*]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[ADD_LVER_ORIG:%.*]] = add i32 [[J_016_LVER_ORIG]], [[MUL_LVER_ORIG]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[TMP0:%.*]] = load i32, ptr @first, align 4
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[TOBOOL_NOT_LVER_ORIG:%.*]] = icmp eq i32 [[TMP0]], 0
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[TOBOOL_NOT_LVER_ORIG]], label [[IF_END_LVER_ORIG]], label [[IF_THEN_LVER_ORIG:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       if.then.lver.orig:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[ARRAYIDX_LVER_ORIG:%.*]] = getelementptr inbounds [0 x i8], ptr @a, i32 0, i32 [[ADD_LVER_ORIG]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[TMP1:%.*]] = load i8, ptr [[ARRAYIDX_LVER_ORIG]], align 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    tail call void asm sideeffect "", "r"(i8 [[TMP1]])
+; CHECK-VERSION-OVER-WIDEN-NEXT:    store i32 0, ptr @first, align 4
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[IF_END_LVER_ORIG]]
+; CHECK-VERSION-OVER-WIDEN:       if.end.lver.orig:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    tail call void asm sideeffect "", "r"(i32 [[ADD_LVER_ORIG]])
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC_LVER_ORIG]] = add nuw nsw i32 [[J_016_LVER_ORIG]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP2_LVER_ORIG:%.*]] = icmp ult i32 [[J_016_LVER_ORIG]], 99999
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[CMP2_LVER_ORIG]], label [[FOR_BODY4_LVER_ORIG]], label [[FOR_COND_CLEANUP3_LVER_ORIG]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond.cleanup3.lver.orig:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC6_LVER_ORIG]] = add i32 [[I_018_LVER_ORIG]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP_LVER_ORIG:%.*]] = icmp ult i32 [[INC6_LVER_ORIG]], [[LIM]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[CMP_LVER_ORIG]], label [[FOR_COND1_PREHEADER_LVER_ORIG]], label [[FOR_COND_CLEANUP_LOOPEXIT_LOOPEXIT:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond1.preheader.ph:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND1_PREHEADER:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond1.preheader:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[I_018:%.*]] = phi i32 [ [[INC6:%.*]], [[FOR_COND_CLEANUP3:%.*]] ], [ 0, [[FOR_COND1_PREHEADER_PH]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[MUL:%.*]] = mul i32 [[I_018]], 100000
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_BODY4:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond.cleanup.loopexit.loopexit:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond.cleanup.loopexit.loopexit1:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND_CLEANUP_LOOPEXIT]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond.cleanup.loopexit:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND_CLEANUP]]
+; CHECK-VERSION-OVER-WIDEN:       for.cond.cleanup:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    ret void
+; CHECK-VERSION-OVER-WIDEN:       for.cond.cleanup3:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC6]] = add i32 [[I_018]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP:%.*]] = icmp ult i32 [[INC6]], [[FLATTEN_TRIPCOUNT]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[CMP]], label [[FOR_COND1_PREHEADER]], label [[FOR_COND_CLEANUP_LOOPEXIT_LOOPEXIT1:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       for.body4:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[J_016:%.*]] = phi i32 [ 0, [[FOR_COND1_PREHEADER]] ]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[ADD:%.*]] = add i32 [[J_016]], [[MUL]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[TMP2:%.*]] = load i32, ptr @first, align 4
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[TOBOOL_NOT:%.*]] = icmp eq i32 [[TMP2]], 0
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br i1 [[TOBOOL_NOT]], label [[IF_END:%.*]], label [[IF_THEN:%.*]]
+; CHECK-VERSION-OVER-WIDEN:       if.then:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [0 x i8], ptr @a, i32 0, i32 [[I_018]]
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[TMP3:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    tail call void asm sideeffect "", "r"(i8 [[TMP3]])
+; CHECK-VERSION-OVER-WIDEN-NEXT:    store i32 0, ptr @first, align 4
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[IF_END]]
+; CHECK-VERSION-OVER-WIDEN:       if.end:
+; CHECK-VERSION-OVER-WIDEN-NEXT:    tail call void asm sideeffect "", "r"(i32 [[I_018]])
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[INC:%.*]] = add nuw nsw i32 [[J_016]], 1
+; CHECK-VERSION-OVER-WIDEN-NEXT:    [[CMP2:%.*]] = icmp ult i32 [[J_016]], 99999
+; CHECK-VERSION-OVER-WIDEN-NEXT:    br label [[FOR_COND_CLEANUP3]]
+;
 entry:
   %cmp17.not = icmp eq i32 %lim, 0
   br i1 %cmp17.not, label %for.cond.cleanup, label %for.cond1.preheader.preheader