diff --git a/llvm/lib/Transforms/Utils/LoopUnrollPeel.cpp b/llvm/lib/Transforms/Utils/LoopUnrollPeel.cpp
--- a/llvm/lib/Transforms/Utils/LoopUnrollPeel.cpp
+++ b/llvm/lib/Transforms/Utils/LoopUnrollPeel.cpp
@@ -215,11 +215,10 @@
     // consider AddRecs of the loop we are trying to peel and avoid
     // non-monotonic predicates, as we will not be able to simplify the loop
     // body.
-    // FIXME: For the non-monotonic predicates ICMP_EQ and ICMP_NE we can
-    //        simplify the loop, if we peel 1 additional iteration, if there
-    //        is no wrapping.
+    if (!LeftAR->isAffine() || LeftAR->getLoop() != &L)
+      continue;
     bool Increasing;
-    if (!LeftAR->isAffine() || LeftAR->getLoop() != &L ||
+    if (!(ICmpInst::isEquality(Pred) && LeftAR->hasNoSelfWrap()) &&
         !SE.isMonotonicPredicate(LeftAR, Pred, Increasing))
       continue;
     (void)Increasing;
@@ -238,18 +237,41 @@
       Pred = ICmpInst::getInversePredicate(Pred);
 
     const SCEV *Step = LeftAR->getStepRecurrence(SE);
-    while (NewPeelCount < MaxPeelCount &&
-           SE.isKnownPredicate(Pred, IterVal, RightSCEV)) {
-      IterVal = SE.getAddExpr(IterVal, Step);
+    const SCEV *NextIterVal = SE.getAddExpr(IterVal, Step);
+    auto PeelOneMoreIteration = [&]() {
+      IterVal = NextIterVal;
+      NextIterVal = SE.getAddExpr(IterVal, Step);
       NewPeelCount++;
+    };
+
+    auto CanPeelOneMoreIteration = [&]() {
+      return NewPeelCount < MaxPeelCount;
+    };
+
+    while (CanPeelOneMoreIteration() &&
+           SE.isKnownPredicate(Pred, IterVal, RightSCEV))
+      PeelOneMoreIteration();
+
+    // With *that* peel count, does the predicate !Pred becomes known in the
+    // first iteration of the loop body after peeling?
+    if (!SE.isKnownPredicate(ICmpInst::getInversePredicate(Pred), IterVal,
+                             RightSCEV))
+      continue; // If not, we're done here.
+
+    // However, for equality comparisons, that isn't always sufficient to
+    // eliminate the comparsion in loop body, we may need to peel one more
+    // iteration. See if Pred then becomes known again, and !Pred unknown.
+    if (ICmpInst::isEquality(Pred) &&
+        !SE.isKnownPredicate(Pred, IterVal, RightSCEV) &&
+        SE.isKnownPredicate(Pred, NextIterVal, RightSCEV) &&
+        !SE.isKnownPredicate(ICmpInst::getInversePredicate(Pred), NextIterVal,
+                             RightSCEV)) {
+      if (!CanPeelOneMoreIteration())
+        continue; // Need to peel one more iteration, but can't. Give up.
+      PeelOneMoreIteration(); // Great!
     }
 
-    // Only peel the loop if the monotonic predicate !Pred becomes known in the
-    // first iteration of the loop body after peeling.
-    if (NewPeelCount > DesiredPeelCount &&
-        SE.isKnownPredicate(ICmpInst::getInversePredicate(Pred), IterVal,
-                            RightSCEV))
-      DesiredPeelCount = NewPeelCount;
+    DesiredPeelCount = std::max(DesiredPeelCount, NewPeelCount);
   }
 
   return DesiredPeelCount;
diff --git a/llvm/test/Transforms/LoopUnroll/peel-loop-conditions.ll b/llvm/test/Transforms/LoopUnroll/peel-loop-conditions.ll
--- a/llvm/test/Transforms/LoopUnroll/peel-loop-conditions.ll
+++ b/llvm/test/Transforms/LoopUnroll/peel-loop-conditions.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s -S -loop-unroll -verify-dom-info | FileCheck %s
+; RUN: opt < %s -S -loop-unroll -unroll-peel-max-count=4 -verify-dom-info | FileCheck %s
 
 declare void @f1()
 declare void @f2()
@@ -522,22 +522,75 @@
 }
 
 define void @test7(i32 %k) {
-; FIXME: Could simplify loop body by peeling one additional iteration after
-;        i != 3 becomes false
 ; CHECK-LABEL: @test7(
 ; CHECK-NEXT:  for.body.lr.ph:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL_BEGIN:%.*]]
+; CHECK:       for.body.peel.begin:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL:%.*]]
+; CHECK:       for.body.peel:
+; CHECK-NEXT:    [[CMP1_PEEL:%.*]] = icmp ne i32 0, 3
+; CHECK-NEXT:    br i1 [[CMP1_PEEL]], label [[IF_THEN_PEEL:%.*]], label [[FOR_INC_PEEL:%.*]]
+; CHECK:       if.then.peel:
+; CHECK-NEXT:    call void @f1()
+; CHECK-NEXT:    br label [[FOR_INC_PEEL]]
+; CHECK:       for.inc.peel:
+; CHECK-NEXT:    [[INC_PEEL:%.*]] = add nsw i32 0, 1
+; CHECK-NEXT:    [[CMP_PEEL:%.*]] = icmp slt i32 [[INC_PEEL]], [[K:%.*]]
+; CHECK-NEXT:    br i1 [[CMP_PEEL]], label [[FOR_BODY_PEEL_NEXT:%.*]], label [[FOR_END:%.*]]
+; CHECK:       for.body.peel.next:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL2:%.*]]
+; CHECK:       for.body.peel2:
+; CHECK-NEXT:    [[CMP1_PEEL3:%.*]] = icmp ne i32 [[INC_PEEL]], 3
+; CHECK-NEXT:    br i1 [[CMP1_PEEL3]], label [[IF_THEN_PEEL4:%.*]], label [[FOR_INC_PEEL5:%.*]]
+; CHECK:       if.then.peel4:
+; CHECK-NEXT:    call void @f1()
+; CHECK-NEXT:    br label [[FOR_INC_PEEL5]]
+; CHECK:       for.inc.peel5:
+; CHECK-NEXT:    [[INC_PEEL6:%.*]] = add nsw i32 [[INC_PEEL]], 1
+; CHECK-NEXT:    [[CMP_PEEL7:%.*]] = icmp slt i32 [[INC_PEEL6]], [[K]]
+; CHECK-NEXT:    br i1 [[CMP_PEEL7]], label [[FOR_BODY_PEEL_NEXT1:%.*]], label [[FOR_END]]
+; CHECK:       for.body.peel.next1:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL9:%.*]]
+; CHECK:       for.body.peel9:
+; CHECK-NEXT:    [[CMP1_PEEL10:%.*]] = icmp ne i32 [[INC_PEEL6]], 3
+; CHECK-NEXT:    br i1 [[CMP1_PEEL10]], label [[IF_THEN_PEEL11:%.*]], label [[FOR_INC_PEEL12:%.*]]
+; CHECK:       if.then.peel11:
+; CHECK-NEXT:    call void @f1()
+; CHECK-NEXT:    br label [[FOR_INC_PEEL12]]
+; CHECK:       for.inc.peel12:
+; CHECK-NEXT:    [[INC_PEEL13:%.*]] = add nsw i32 [[INC_PEEL6]], 1
+; CHECK-NEXT:    [[CMP_PEEL14:%.*]] = icmp slt i32 [[INC_PEEL13]], [[K]]
+; CHECK-NEXT:    br i1 [[CMP_PEEL14]], label [[FOR_BODY_PEEL_NEXT8:%.*]], label [[FOR_END]]
+; CHECK:       for.body.peel.next8:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL16:%.*]]
+; CHECK:       for.body.peel16:
+; CHECK-NEXT:    [[CMP1_PEEL17:%.*]] = icmp ne i32 [[INC_PEEL13]], 3
+; CHECK-NEXT:    br i1 [[CMP1_PEEL17]], label [[IF_THEN_PEEL18:%.*]], label [[FOR_INC_PEEL19:%.*]]
+; CHECK:       if.then.peel18:
+; CHECK-NEXT:    call void @f1()
+; CHECK-NEXT:    br label [[FOR_INC_PEEL19]]
+; CHECK:       for.inc.peel19:
+; CHECK-NEXT:    [[INC_PEEL20:%.*]] = add nsw i32 [[INC_PEEL13]], 1
+; CHECK-NEXT:    [[CMP_PEEL21:%.*]] = icmp slt i32 [[INC_PEEL20]], [[K]]
+; CHECK-NEXT:    br i1 [[CMP_PEEL21]], label [[FOR_BODY_PEEL_NEXT15:%.*]], label [[FOR_END]]
+; CHECK:       for.body.peel.next15:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL_NEXT22:%.*]]
+; CHECK:       for.body.peel.next22:
+; CHECK-NEXT:    br label [[FOR_BODY_LR_PH_PEEL_NEWPH:%.*]]
+; CHECK:       for.body.lr.ph.peel.newph:
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
-; CHECK-NEXT:    [[I_05:%.*]] = phi i32 [ 0, [[FOR_BODY_LR_PH:%.*]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ]
-; CHECK-NEXT:    [[CMP1:%.*]] = icmp ne i32 [[I_05]], 3
-; CHECK-NEXT:    br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
+; CHECK-NEXT:    [[I_05:%.*]] = phi i32 [ [[INC_PEEL20]], [[FOR_BODY_LR_PH_PEEL_NEWPH]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ]
+; CHECK-NEXT:    br i1 true, label [[IF_THEN:%.*]], label [[FOR_INC]]
 ; CHECK:       if.then:
 ; CHECK-NEXT:    call void @f1()
 ; CHECK-NEXT:    br label [[FOR_INC]]
 ; CHECK:       for.inc:
-; CHECK-NEXT:    [[INC]] = add nsw i32 [[I_05]], 1
-; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[INC]], [[K:%.*]]
-; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_END:%.*]]
+; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_05]], 1
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[INC]], [[K]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_END_LOOPEXIT:%.*]], !llvm.loop !6
+; CHECK:       for.end.loopexit:
+; CHECK-NEXT:    br label [[FOR_END]]
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret void
 ;
@@ -563,22 +616,75 @@
 }
 
 define void @test8(i32 %k) {
-; FIXME: Could simplify loop body by peeling one additional iteration after
-;        i == 3 becomes true.
 ; CHECK-LABEL: @test8(
 ; CHECK-NEXT:  for.body.lr.ph:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL_BEGIN:%.*]]
+; CHECK:       for.body.peel.begin:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL:%.*]]
+; CHECK:       for.body.peel:
+; CHECK-NEXT:    [[CMP1_PEEL:%.*]] = icmp eq i32 0, 3
+; CHECK-NEXT:    br i1 [[CMP1_PEEL]], label [[IF_THEN_PEEL:%.*]], label [[FOR_INC_PEEL:%.*]]
+; CHECK:       if.then.peel:
+; CHECK-NEXT:    call void @f1()
+; CHECK-NEXT:    br label [[FOR_INC_PEEL]]
+; CHECK:       for.inc.peel:
+; CHECK-NEXT:    [[INC_PEEL:%.*]] = add nsw i32 0, 1
+; CHECK-NEXT:    [[CMP_PEEL:%.*]] = icmp slt i32 [[INC_PEEL]], [[K:%.*]]
+; CHECK-NEXT:    br i1 [[CMP_PEEL]], label [[FOR_BODY_PEEL_NEXT:%.*]], label [[FOR_END:%.*]]
+; CHECK:       for.body.peel.next:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL2:%.*]]
+; CHECK:       for.body.peel2:
+; CHECK-NEXT:    [[CMP1_PEEL3:%.*]] = icmp eq i32 [[INC_PEEL]], 3
+; CHECK-NEXT:    br i1 [[CMP1_PEEL3]], label [[IF_THEN_PEEL4:%.*]], label [[FOR_INC_PEEL5:%.*]]
+; CHECK:       if.then.peel4:
+; CHECK-NEXT:    call void @f1()
+; CHECK-NEXT:    br label [[FOR_INC_PEEL5]]
+; CHECK:       for.inc.peel5:
+; CHECK-NEXT:    [[INC_PEEL6:%.*]] = add nsw i32 [[INC_PEEL]], 1
+; CHECK-NEXT:    [[CMP_PEEL7:%.*]] = icmp slt i32 [[INC_PEEL6]], [[K]]
+; CHECK-NEXT:    br i1 [[CMP_PEEL7]], label [[FOR_BODY_PEEL_NEXT1:%.*]], label [[FOR_END]]
+; CHECK:       for.body.peel.next1:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL9:%.*]]
+; CHECK:       for.body.peel9:
+; CHECK-NEXT:    [[CMP1_PEEL10:%.*]] = icmp eq i32 [[INC_PEEL6]], 3
+; CHECK-NEXT:    br i1 [[CMP1_PEEL10]], label [[IF_THEN_PEEL11:%.*]], label [[FOR_INC_PEEL12:%.*]]
+; CHECK:       if.then.peel11:
+; CHECK-NEXT:    call void @f1()
+; CHECK-NEXT:    br label [[FOR_INC_PEEL12]]
+; CHECK:       for.inc.peel12:
+; CHECK-NEXT:    [[INC_PEEL13:%.*]] = add nsw i32 [[INC_PEEL6]], 1
+; CHECK-NEXT:    [[CMP_PEEL14:%.*]] = icmp slt i32 [[INC_PEEL13]], [[K]]
+; CHECK-NEXT:    br i1 [[CMP_PEEL14]], label [[FOR_BODY_PEEL_NEXT8:%.*]], label [[FOR_END]]
+; CHECK:       for.body.peel.next8:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL16:%.*]]
+; CHECK:       for.body.peel16:
+; CHECK-NEXT:    [[CMP1_PEEL17:%.*]] = icmp eq i32 [[INC_PEEL13]], 3
+; CHECK-NEXT:    br i1 [[CMP1_PEEL17]], label [[IF_THEN_PEEL18:%.*]], label [[FOR_INC_PEEL19:%.*]]
+; CHECK:       if.then.peel18:
+; CHECK-NEXT:    call void @f1()
+; CHECK-NEXT:    br label [[FOR_INC_PEEL19]]
+; CHECK:       for.inc.peel19:
+; CHECK-NEXT:    [[INC_PEEL20:%.*]] = add nsw i32 [[INC_PEEL13]], 1
+; CHECK-NEXT:    [[CMP_PEEL21:%.*]] = icmp slt i32 [[INC_PEEL20]], [[K]]
+; CHECK-NEXT:    br i1 [[CMP_PEEL21]], label [[FOR_BODY_PEEL_NEXT15:%.*]], label [[FOR_END]]
+; CHECK:       for.body.peel.next15:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL_NEXT22:%.*]]
+; CHECK:       for.body.peel.next22:
+; CHECK-NEXT:    br label [[FOR_BODY_LR_PH_PEEL_NEWPH:%.*]]
+; CHECK:       for.body.lr.ph.peel.newph:
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
-; CHECK-NEXT:    [[I_05:%.*]] = phi i32 [ 0, [[FOR_BODY_LR_PH:%.*]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ]
-; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i32 [[I_05]], 3
-; CHECK-NEXT:    br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
+; CHECK-NEXT:    [[I_05:%.*]] = phi i32 [ [[INC_PEEL20]], [[FOR_BODY_LR_PH_PEEL_NEWPH]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ]
+; CHECK-NEXT:    br i1 false, label [[IF_THEN:%.*]], label [[FOR_INC]]
 ; CHECK:       if.then:
 ; CHECK-NEXT:    call void @f1()
 ; CHECK-NEXT:    br label [[FOR_INC]]
 ; CHECK:       for.inc:
-; CHECK-NEXT:    [[INC]] = add nsw i32 [[I_05]], 1
-; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[INC]], [[K:%.*]]
-; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_END:%.*]]
+; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_05]], 1
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[INC]], [[K]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_END_LOOPEXIT:%.*]], !llvm.loop !7
+; CHECK:       for.end.loopexit:
+; CHECK-NEXT:    br label [[FOR_END]]
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret void
 ;
@@ -687,7 +793,7 @@
 ; CHECK-NEXT:    call void @sink()
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_06]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[LEN]]
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT_LOOPEXIT:%.*]], label [[FOR_BODY]], !llvm.loop !6
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT_LOOPEXIT:%.*]], label [[FOR_BODY]], !llvm.loop !8
 ;
 entry:
   %cmp5 = icmp sgt i32 %len, 0
@@ -754,7 +860,7 @@
 ; CHECK-NEXT:    call void @sink()
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_06]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[LEN]]
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT_LOOPEXIT:%.*]], label [[FOR_BODY]], !llvm.loop !8
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT_LOOPEXIT:%.*]], label [[FOR_BODY]], !llvm.loop !10
 ;
 entry:
   %cmp5 = icmp sgt i32 %len, 0
@@ -779,21 +885,43 @@
   br i1 %exitcond, label %for.cond.cleanup, label %for.body
 }
 
+; NOTE: here we should only peel the first iteration,
+;       i.e. all calls to sink() must stay in loop.
 define void @test12__peel_first_iter_via_eq_pred(i32 %len) {
 ; CHECK-LABEL: @test12__peel_first_iter_via_eq_pred(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[CMP5:%.*]] = icmp sgt i32 [[LEN:%.*]], 0
 ; CHECK-NEXT:    br i1 [[CMP5]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
 ; CHECK:       for.body.preheader:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL_BEGIN:%.*]]
+; CHECK:       for.body.peel.begin:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL:%.*]]
+; CHECK:       for.body.peel:
+; CHECK-NEXT:    [[CMP1_PEEL:%.*]] = icmp eq i32 0, 0
+; CHECK-NEXT:    br i1 [[CMP1_PEEL]], label [[IF_THEN_PEEL:%.*]], label [[IF_END_PEEL:%.*]]
+; CHECK:       if.then.peel:
+; CHECK-NEXT:    call void @init()
+; CHECK-NEXT:    br label [[IF_END_PEEL]]
+; CHECK:       if.end.peel:
+; CHECK-NEXT:    call void @sink()
+; CHECK-NEXT:    [[INC_PEEL:%.*]] = add nuw nsw i32 0, 1
+; CHECK-NEXT:    [[EXITCOND_PEEL:%.*]] = icmp eq i32 [[INC_PEEL]], [[LEN]]
+; CHECK-NEXT:    br i1 [[EXITCOND_PEEL]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[FOR_BODY_PEEL_NEXT:%.*]]
+; CHECK:       for.body.peel.next:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL_NEXT1:%.*]]
+; CHECK:       for.body.peel.next1:
+; CHECK-NEXT:    br label [[FOR_BODY_PREHEADER_PEEL_NEWPH:%.*]]
+; CHECK:       for.body.preheader.peel.newph:
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.cond.cleanup.loopexit.loopexit:
+; CHECK-NEXT:    br label [[FOR_COND_CLEANUP_LOOPEXIT]]
 ; CHECK:       for.cond.cleanup.loopexit:
 ; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
 ; CHECK:       for.cond.cleanup:
 ; CHECK-NEXT:    ret void
 ; CHECK:       for.body:
-; CHECK-NEXT:    [[I_06:%.*]] = phi i32 [ [[INC:%.*]], [[IF_END:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
-; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i32 [[I_06]], 0
-; CHECK-NEXT:    br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[IF_END]]
+; CHECK-NEXT:    [[I_06:%.*]] = phi i32 [ [[INC:%.*]], [[IF_END:%.*]] ], [ [[INC_PEEL]], [[FOR_BODY_PREHEADER_PEEL_NEWPH]] ]
+; CHECK-NEXT:    br i1 false, label [[IF_THEN:%.*]], label [[IF_END]]
 ; CHECK:       if.then:
 ; CHECK-NEXT:    call void @init()
 ; CHECK-NEXT:    br label [[IF_END]]
@@ -801,7 +929,7 @@
 ; CHECK-NEXT:    call void @sink()
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_06]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[LEN]]
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[FOR_BODY]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT_LOOPEXIT:%.*]], label [[FOR_BODY]], !llvm.loop !11
 ;
 entry:
   %cmp5 = icmp sgt i32 %len, 0
@@ -826,21 +954,43 @@
   br i1 %exitcond, label %for.cond.cleanup, label %for.body
 }
 
+; NOTE: here we should only peel the first iteration,
+;       i.e. all calls to sink() must stay in loop.
 define void @test13__peel_first_iter_via_ne_pred(i32 %len) {
 ; CHECK-LABEL: @test13__peel_first_iter_via_ne_pred(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[CMP5:%.*]] = icmp sgt i32 [[LEN:%.*]], 0
 ; CHECK-NEXT:    br i1 [[CMP5]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
 ; CHECK:       for.body.preheader:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL_BEGIN:%.*]]
+; CHECK:       for.body.peel.begin:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL:%.*]]
+; CHECK:       for.body.peel:
+; CHECK-NEXT:    [[CMP1_PEEL:%.*]] = icmp ne i32 0, 0
+; CHECK-NEXT:    br i1 [[CMP1_PEEL]], label [[IF_END_PEEL:%.*]], label [[IF_THEN_PEEL:%.*]]
+; CHECK:       if.then.peel:
+; CHECK-NEXT:    call void @init()
+; CHECK-NEXT:    br label [[IF_END_PEEL]]
+; CHECK:       if.end.peel:
+; CHECK-NEXT:    call void @sink()
+; CHECK-NEXT:    [[INC_PEEL:%.*]] = add nuw nsw i32 0, 1
+; CHECK-NEXT:    [[EXITCOND_PEEL:%.*]] = icmp eq i32 [[INC_PEEL]], [[LEN]]
+; CHECK-NEXT:    br i1 [[EXITCOND_PEEL]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[FOR_BODY_PEEL_NEXT:%.*]]
+; CHECK:       for.body.peel.next:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL_NEXT1:%.*]]
+; CHECK:       for.body.peel.next1:
+; CHECK-NEXT:    br label [[FOR_BODY_PREHEADER_PEEL_NEWPH:%.*]]
+; CHECK:       for.body.preheader.peel.newph:
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.cond.cleanup.loopexit.loopexit:
+; CHECK-NEXT:    br label [[FOR_COND_CLEANUP_LOOPEXIT]]
 ; CHECK:       for.cond.cleanup.loopexit:
 ; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
 ; CHECK:       for.cond.cleanup:
 ; CHECK-NEXT:    ret void
 ; CHECK:       for.body:
-; CHECK-NEXT:    [[I_06:%.*]] = phi i32 [ [[INC:%.*]], [[IF_END:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
-; CHECK-NEXT:    [[CMP1:%.*]] = icmp ne i32 [[I_06]], 0
-; CHECK-NEXT:    br i1 [[CMP1]], label [[IF_END]], label [[IF_THEN:%.*]]
+; CHECK-NEXT:    [[I_06:%.*]] = phi i32 [ [[INC:%.*]], [[IF_END:%.*]] ], [ [[INC_PEEL]], [[FOR_BODY_PREHEADER_PEEL_NEWPH]] ]
+; CHECK-NEXT:    br i1 true, label [[IF_END]], label [[IF_THEN:%.*]]
 ; CHECK:       if.then:
 ; CHECK-NEXT:    call void @init()
 ; CHECK-NEXT:    br label [[IF_END]]
@@ -848,7 +998,7 @@
 ; CHECK-NEXT:    call void @sink()
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_06]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[LEN]]
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[FOR_BODY]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT_LOOPEXIT:%.*]], label [[FOR_BODY]], !llvm.loop !12
 ;
 entry:
   %cmp5 = icmp sgt i32 %len, 0
@@ -873,6 +1023,7 @@
   br i1 %exitcond, label %for.cond.cleanup, label %for.body
 }
 
+; No peeling is profitable here.
 define void @test15__ivar_mod2_is_1(i32 %len) {
 ; CHECK-LABEL: @test15__ivar_mod2_is_1(
 ; CHECK-NEXT:  entry:
@@ -922,6 +1073,7 @@
   br i1 %exitcond, label %for.cond.cleanup, label %for.body
 }
 
+; No peeling is profitable here.
 define void @test16__ivar_mod2_is_0(i32 %len) {
 ; CHECK-LABEL: @test16__ivar_mod2_is_0(
 ; CHECK-NEXT:  entry:
@@ -971,5 +1123,87 @@
   br i1 %exitcond, label %for.cond.cleanup, label %for.body
 }
 
+; Similar to @test7, we need to peel one extra iteration, and we can't do that
+; as per the -unroll-peel-max-count=4, so this shouldn't be peeled at all.
+define void @test17(i32 %k) {
+; CHECK-LABEL: @test17(
+; CHECK-NEXT:  for.body.lr.ph:
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I_05:%.*]] = phi i32 [ 0, [[FOR_BODY_LR_PH:%.*]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ]
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp ne i32 [[I_05]], 4
+; CHECK-NEXT:    br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
+; CHECK:       if.then:
+; CHECK-NEXT:    call void @f1()
+; CHECK-NEXT:    br label [[FOR_INC]]
+; CHECK:       for.inc:
+; CHECK-NEXT:    [[INC]] = add nsw i32 [[I_05]], 1
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[INC]], [[K:%.*]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_END:%.*]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
+;
+for.body.lr.ph:
+  br label %for.body
+
+for.body:
+  %i.05 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
+  %cmp1 = icmp ne i32 %i.05, 4
+  br i1 %cmp1, label %if.then, label %for.inc
+
+if.then:
+  call void @f1()
+  br label %for.inc
+
+for.inc:
+  %inc = add nsw i32 %i.05, 1
+  %cmp = icmp slt i32 %inc, %k
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:
+  ret void
+}
+
+; Similar to @test8, we need to peel one extra iteration, and we can't do that
+; as per the -unroll-peel-max-count=4, so this shouldn't be peeled at all.
+define void @test18(i32 %k) {
+; CHECK-LABEL: @test18(
+; CHECK-NEXT:  for.body.lr.ph:
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I_05:%.*]] = phi i32 [ 0, [[FOR_BODY_LR_PH:%.*]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ]
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i32 [[I_05]], 4
+; CHECK-NEXT:    br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
+; CHECK:       if.then:
+; CHECK-NEXT:    call void @f1()
+; CHECK-NEXT:    br label [[FOR_INC]]
+; CHECK:       for.inc:
+; CHECK-NEXT:    [[INC]] = add nsw i32 [[I_05]], 1
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[INC]], [[K:%.*]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_END:%.*]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
+;
+for.body.lr.ph:
+  br label %for.body
+
+for.body:
+  %i.05 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
+  %cmp1 = icmp eq i32 %i.05, 4
+  br i1 %cmp1, label %if.then, label %for.inc
+
+if.then:
+  call void @f1()
+  br label %for.inc
+
+for.inc:
+  %inc = add nsw i32 %i.05, 1
+  %cmp = icmp slt i32 %inc, %k
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:
+  ret void
+}
+
 declare void @init()
 declare void @sink()