Index: llvm/lib/Transforms/Utils/LoopPeel.cpp
===================================================================
--- llvm/lib/Transforms/Utils/LoopPeel.cpp
+++ llvm/lib/Transforms/Utils/LoopPeel.cpp
@@ -13,6 +13,7 @@
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/IVDescriptors.h"
 #include "llvm/Analysis/Loads.h"
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/LoopIterator.h"
@@ -467,6 +468,101 @@
     });
 }
 
+// When a loop contains an accumulator, an initial identity operation
+// may be avoided by peeling a single time.  For example, consider this loop
+// int Total = 0;
+// int Product = 1;
+// for (I = 0; I < 100000; ++I) {
+//   Total += foo(I);
+//   Product *= bar(I);
+// }
+// Peeling a single time will avoid the initial addtion and multiplication:
+// int Total = foo(I);
+// int Product = bar(I);
+// for (I = 1; I < 100000; ++I) {
+//   Total += foo(I);
+//   Product *= bar(I);
+// }
+// This may work for +=, *=, &&= and ||= depending on initial value.
+//
+class IdentityOpPeeler {
+public:
+  IdentityOpPeeler(Loop &L, ScalarEvolution &SE) : L(L), SE(SE) {
+    assert(canPeel(&L) && L.getHeader() && "expected peelable loop");
+  }
+  bool shouldPeelOnce() {
+    return any_of(L.getHeader()->phis(),
+                  [&](PHINode &Phi) { return isAccumulatorPhi(Phi); });
+  }
+
+protected:
+  // Return true if \p Phi in not an induction variable and is an accumulator
+  // that starts with an identity operation
+  bool isAccumulatorPhi(PHINode &Phi) const {
+    if (&Phi == L.getInductionVariable(SE))
+      return false;
+
+    // Return the incoming constant value from \p BB or nullptr
+    auto constIn = [&](BasicBlock *BB, bool) -> Constant * {
+      if (L.contains(BB))
+        // not a value coming from outside the loop
+        return nullptr;
+      return dyn_cast<Constant>(Phi.getIncomingValueForBlock(BB));
+    };
+
+    // find a single constant value coming from outside the loop
+    if (Constant *C = find_singleton<Constant>(Phi.blocks(), constIn, true)) {
+      if (ConstantFP *CFP = dyn_cast<ConstantFP>(C))
+        return CFP->isZeroValue() && any_of(Phi.users(), [&](User *U) -> bool {
+                 if (beneficial(*U, Phi, Instruction::FAdd))
+                   return true;
+                 // M += <exp> may be expressed using the FMulAdd
+                 // intrinsic with arguments (M, M, 0)
+                 Instruction *I = dyn_cast<Instruction>(U);
+                 return I && RecurrenceDescriptor::isFMulAddIntrinsic(I) &&
+                        I->getOperand(2) == &Phi;
+               });
+
+      if (ConstantInt *CI = dyn_cast<ConstantInt>(C)) {
+        BinaryOperator::BinaryOps Op;
+        if (CI->isZeroValue())
+          Op = (CI->getBitWidth() == 1) ? Instruction::Or : Instruction::Add;
+        else if (CI->isOneValue())
+          Op = (CI->getBitWidth() == 1) ? Instruction::And : Instruction::Mul;
+        else
+          return false;
+
+        return any_of(Phi.users(), [&](const User *U) -> bool {
+          return beneficial(*U, Phi, Op);
+        });
+      }
+    }
+    return false;
+  }
+
+  // Peeling may be beneficial for a use in the loop with operator \p Op.
+  bool beneficial(const User &U, const PHINode &Phi,
+                  const BinaryOperator::BinaryOps Op) const {
+    if (const Instruction *I = dyn_cast<const Instruction>(&U))
+      if (L.contains(I->getParent()))
+        if (const BinaryOperator *BO = dyn_cast<const BinaryOperator>(I))
+          return (BO->getOpcode() == Op) &&
+                 // SCEV might not recognize an induction variable so assume it
+                 // is only beneficial if the other operand is not a constant
+                 (!isa<Constant>(
+                     BO->getOperand(BO->getOperand(0) == &Phi ? 1 : 0))) &&
+                 // try not to get in the way of the vectorizer by seeing if the
+                 // count of the loop multiplied by the size is divisible by 128
+                 (SE.getSmallConstantMaxTripCount(&L) == 0 ||
+                  SE.getSmallConstantMaxTripCount(&L) *
+                          Phi.getType()->getScalarSizeInBits() % 128 !=
+                      0);
+    return false;
+  }
+
+  const Loop &L;
+  ScalarEvolution &SE;
+};
 
 // Return the number of iterations we want to peel off.
 void llvm::computePeelCount(Loop *L, unsigned LoopSize,
@@ -539,6 +635,9 @@
   if (DesiredPeelCount == 0)
     DesiredPeelCount = peelToTurnInvariantLoadsDerefencebale(*L, DT, AC);
 
+  if (DesiredPeelCount == 0 && MaxPeelCount)
+    DesiredPeelCount = IdentityOpPeeler(*L, SE).shouldPeelOnce() ? 1 : 0;
+
   if (DesiredPeelCount > 0) {
     DesiredPeelCount = std::min(DesiredPeelCount, MaxPeelCount);
     // Consider max peel count limitation.
Index: llvm/test/Transforms/LoopUnroll/AArch64/runtime-loop.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/AArch64/runtime-loop.ll
+++ llvm/test/Transforms/LoopUnroll/AArch64/runtime-loop.ll
@@ -24,7 +24,7 @@
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
-  %sum.02 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+  %sum.02 = phi i32 [ %add, %for.body ], [ 1, %entry ]
   %arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
   %0 = load i32, ptr %arrayidx, align 4
   %add = add nsw i32 %0, %sum.02
Index: llvm/test/Transforms/LoopUnroll/ARM/multi-blocks.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/ARM/multi-blocks.ll
+++ llvm/test/Transforms/LoopUnroll/ARM/multi-blocks.ll
@@ -23,7 +23,7 @@
 ; CHECK:       for.cond.cleanup.loopexit.unr-lcssa:
 ; CHECK-NEXT:    [[TEMP_1_LCSSA_PH:%.*]] = phi i32 [ undef, [[FOR_BODY_PREHEADER]] ], [ [[TEMP_1_LCSSA_PH_PH]], [[FOR_COND_CLEANUP_LOOPEXIT_UNR_LCSSA_LOOPEXIT:%.*]] ]
 ; CHECK-NEXT:    [[J_010_UNR:%.*]] = phi i32 [ 0, [[FOR_BODY_PREHEADER]] ], [ [[J_010_UNR_PH]], [[FOR_COND_CLEANUP_LOOPEXIT_UNR_LCSSA_LOOPEXIT]] ]
-; CHECK-NEXT:    [[TEMP_09_UNR:%.*]] = phi i32 [ 0, [[FOR_BODY_PREHEADER]] ], [ [[TEMP_09_UNR_PH]], [[FOR_COND_CLEANUP_LOOPEXIT_UNR_LCSSA_LOOPEXIT]] ]
+; CHECK-NEXT:    [[TEMP_09_UNR:%.*]] = phi i32 [ 1, [[FOR_BODY_PREHEADER]] ], [ [[TEMP_09_UNR_PH]], [[FOR_COND_CLEANUP_LOOPEXIT_UNR_LCSSA_LOOPEXIT]] ]
 ; CHECK-NEXT:    [[LCMP_MOD:%.*]] = icmp ne i32 [[XTRAITER]], 0
 ; CHECK-NEXT:    br i1 [[LCMP_MOD]], label [[FOR_BODY_EPIL_PREHEADER:%.*]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]]
 ; CHECK:       for.body.epil.preheader:
@@ -83,7 +83,7 @@
 ; CHECK-NEXT:    ret void
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[J_010:%.*]] = phi i32 [ 0, [[FOR_BODY_PREHEADER_NEW]] ], [ [[INC_3]], [[FOR_INC_3]] ]
-; CHECK-NEXT:    [[TEMP_09:%.*]] = phi i32 [ 0, [[FOR_BODY_PREHEADER_NEW]] ], [ [[TEMP_1_3]], [[FOR_INC_3]] ]
+; CHECK-NEXT:    [[TEMP_09:%.*]] = phi i32 [ 1, [[FOR_BODY_PREHEADER_NEW]] ], [ [[TEMP_1_3]], [[FOR_INC_3]] ]
 ; CHECK-NEXT:    [[NITER:%.*]] = phi i32 [ 0, [[FOR_BODY_PREHEADER_NEW]] ], [ [[NITER_NEXT_3:%.*]], [[FOR_INC_3]] ]
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[CONDITION]], i32 [[J_010]]
 ; CHECK-NEXT:    [[I:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
@@ -154,7 +154,7 @@
 
 for.body:                                         ; preds = %for.inc, %for.body.preheader
   %j.010 = phi i32 [ %inc, %for.inc ], [ 0, %for.body.preheader ]
-  %temp.09 = phi i32 [ %temp.1, %for.inc ], [ 0, %for.body.preheader ]
+  %temp.09 = phi i32 [ %temp.1, %for.inc ], [ 1, %for.body.preheader ]
   %arrayidx = getelementptr inbounds i32, ptr %Condition, i32 %j.010
   %i = load i32, ptr %arrayidx, align 4
   %tobool = icmp eq i32 %i, 0
@@ -182,7 +182,7 @@
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[J_016:%.*]] = phi i32 [ 0, [[FOR_BODY_PREHEADER]] ], [ [[INC_3:%.*]], [[IF_END_3:%.*]] ]
-; CHECK-NEXT:    [[TEMP_015:%.*]] = phi i32 [ 0, [[FOR_BODY_PREHEADER]] ], [ [[TEMP_0_ADD_3:%.*]], [[IF_END_3]] ]
+; CHECK-NEXT:    [[TEMP_015:%.*]] = phi i32 [ 1, [[FOR_BODY_PREHEADER]] ], [ [[TEMP_0_ADD_3:%.*]], [[IF_END_3]] ]
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[INPUT:%.*]], i32 [[J_016]]
 ; CHECK-NEXT:    [[I:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
 ; CHECK-NEXT:    [[CMP1:%.*]] = icmp ugt i32 [[I]], 65535
@@ -255,7 +255,7 @@
 
 for.body:                                         ; preds = %if.end, %for.body.preheader
   %j.016 = phi i32 [ %inc, %if.end ], [ 0, %for.body.preheader ]
-  %temp.015 = phi i32 [ %temp.0.add, %if.end ], [ 0, %for.body.preheader ]
+  %temp.015 = phi i32 [ %temp.0.add, %if.end ], [ 1, %for.body.preheader ]
   %arrayidx = getelementptr inbounds i32, ptr %Input, i32 %j.016
   %i = load i32, ptr %arrayidx, align 4
   %cmp1 = icmp ugt i32 %i, 65535
@@ -286,7 +286,7 @@
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[J_022:%.*]] = phi i32 [ [[INC:%.*]], [[IF_END5:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
-; CHECK-NEXT:    [[TEMP_021:%.*]] = phi i32 [ [[TEMP_0_ADD:%.*]], [[IF_END5]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
+; CHECK-NEXT:    [[TEMP_021:%.*]] = phi i32 [ [[TEMP_0_ADD:%.*]], [[IF_END5]] ], [ 1, [[FOR_BODY_PREHEADER]] ]
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[CONDITION:%.*]], i32 [[J_022]]
 ; CHECK-NEXT:    [[I:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
 ; CHECK-NEXT:    [[CMP1:%.*]] = icmp ugt i32 [[I]], 65535
@@ -320,7 +320,7 @@
 
 for.body:                                         ; preds = %if.end5, %for.body.preheader
   %j.022 = phi i32 [ %inc, %if.end5 ], [ 0, %for.body.preheader ]
-  %temp.021 = phi i32 [ %temp.0.add, %if.end5 ], [ 0, %for.body.preheader ]
+  %temp.021 = phi i32 [ %temp.0.add, %if.end5 ], [ 1, %for.body.preheader ]
   %arrayidx = getelementptr inbounds i32, ptr %Condition, i32 %j.022
   %i = load i32, ptr %arrayidx, align 4
   %cmp1 = icmp ugt i32 %i, 65535
@@ -371,7 +371,7 @@
 ; CHECK-NEXT:    [[TEMP_1_LCSSA_PH:%.*]] = phi i32 [ undef, [[FOR_BODY_LR_PH]] ], [ [[TEMP_1_LCSSA_PH_PH]], [[FOR_COND_CLEANUP_LOOPEXIT_UNR_LCSSA_LOOPEXIT:%.*]] ]
 ; CHECK-NEXT:    [[I_UNR:%.*]] = phi i32 [ [[DOTPRE]], [[FOR_BODY_LR_PH]] ], [ [[I_UNR_PH]], [[FOR_COND_CLEANUP_LOOPEXIT_UNR_LCSSA_LOOPEXIT]] ]
 ; CHECK-NEXT:    [[J_027_UNR:%.*]] = phi i32 [ 1, [[FOR_BODY_LR_PH]] ], [ [[J_027_UNR_PH]], [[FOR_COND_CLEANUP_LOOPEXIT_UNR_LCSSA_LOOPEXIT]] ]
-; CHECK-NEXT:    [[TEMP_026_UNR:%.*]] = phi i32 [ 0, [[FOR_BODY_LR_PH]] ], [ [[TEMP_026_UNR_PH]], [[FOR_COND_CLEANUP_LOOPEXIT_UNR_LCSSA_LOOPEXIT]] ]
+; CHECK-NEXT:    [[TEMP_026_UNR:%.*]] = phi i32 [ 1, [[FOR_BODY_LR_PH]] ], [ [[TEMP_026_UNR_PH]], [[FOR_COND_CLEANUP_LOOPEXIT_UNR_LCSSA_LOOPEXIT]] ]
 ; CHECK-NEXT:    [[LCMP_MOD:%.*]] = icmp ne i32 [[XTRAITER]], 0
 ; CHECK-NEXT:    br i1 [[LCMP_MOD]], label [[FOR_BODY_EPIL_PREHEADER:%.*]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]]
 ; CHECK:       for.body.epil.preheader:
@@ -462,7 +462,7 @@
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[DOTPRE]], [[FOR_BODY_LR_PH_NEW]] ], [ [[I2_3]], [[FOR_INC_3]] ]
 ; CHECK-NEXT:    [[J_027:%.*]] = phi i32 [ 1, [[FOR_BODY_LR_PH_NEW]] ], [ [[INC_3]], [[FOR_INC_3]] ]
-; CHECK-NEXT:    [[TEMP_026:%.*]] = phi i32 [ 0, [[FOR_BODY_LR_PH_NEW]] ], [ [[TEMP_1_3]], [[FOR_INC_3]] ]
+; CHECK-NEXT:    [[TEMP_026:%.*]] = phi i32 [ 1, [[FOR_BODY_LR_PH_NEW]] ], [ [[TEMP_1_3]], [[FOR_INC_3]] ]
 ; CHECK-NEXT:    [[NITER:%.*]] = phi i32 [ 0, [[FOR_BODY_LR_PH_NEW]] ], [ [[NITER_NEXT_3:%.*]], [[FOR_INC_3]] ]
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[CONDITION]], i32 [[J_027]]
 ; CHECK-NEXT:    [[I1:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
@@ -575,7 +575,7 @@
 for.body:                                         ; preds = %for.inc, %for.body.lr.ph
   %i = phi i32 [ %.pre, %for.body.lr.ph ], [ %i2, %for.inc ]
   %j.027 = phi i32 [ 1, %for.body.lr.ph ], [ %inc, %for.inc ]
-  %temp.026 = phi i32 [ 0, %for.body.lr.ph ], [ %temp.1, %for.inc ]
+  %temp.026 = phi i32 [ 1, %for.body.lr.ph ], [ %temp.1, %for.inc ]
   %arrayidx = getelementptr inbounds i32, ptr %Condition, i32 %j.027
   %i1 = load i32, ptr %arrayidx, align 4
   %cmp1 = icmp ugt i32 %i1, 65535
@@ -614,7 +614,7 @@
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[J_026:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_INC:%.*]] ], [ 1, [[FOR_BODY_PREHEADER]] ]
-; CHECK-NEXT:    [[TEMP_025:%.*]] = phi i32 [ [[TEMP_1:%.*]], [[FOR_INC]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
+; CHECK-NEXT:    [[TEMP_025:%.*]] = phi i32 [ [[TEMP_1:%.*]], [[FOR_INC]] ], [ 1, [[FOR_BODY_PREHEADER]] ]
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[INPUT:%.*]], i32 [[J_026]]
 ; CHECK-NEXT:    [[I:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
 ; CHECK-NEXT:    [[ADD:%.*]] = add i32 [[I]], [[TEMP_025]]
@@ -658,7 +658,7 @@
 
 for.body:                                         ; preds = %for.inc, %for.body.preheader
   %j.026 = phi i32 [ %inc, %for.inc ], [ 1, %for.body.preheader ]
-  %temp.025 = phi i32 [ %temp.1, %for.inc ], [ 0, %for.body.preheader ]
+  %temp.025 = phi i32 [ %temp.1, %for.inc ], [ 1, %for.body.preheader ]
   %arrayidx = getelementptr inbounds i32, ptr %Input, i32 %j.026
   %i = load i32, ptr %arrayidx, align 4
   %add = add i32 %i, %temp.025
Index: llvm/test/Transforms/LoopUnroll/ARM/v6munroll.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/ARM/v6munroll.ll
+++ llvm/test/Transforms/LoopUnroll/ARM/v6munroll.ll
@@ -86,10 +86,10 @@
   %x.addr.062 = phi ptr [ %incdec.ptr, %for.inc ], [ %x, %for.body.preheader ]
   %y.addr.061 = phi ptr [ %incdec.ptr19, %for.inc ], [ %y, %for.body.preheader ]
   %rhs_cols_idx.060 = phi i32 [ %dec, %for.inc ], [ %n, %for.body.preheader ]
-  %res11.059 = phi i32 [ %add18, %for.inc ], [ 0, %for.body.preheader ]
-  %res10.058 = phi i32 [ %add16, %for.inc ], [ 0, %for.body.preheader ]
-  %res01.057 = phi i32 [ %add8, %for.inc ], [ 0, %for.body.preheader ]
-  %res00.056 = phi i32 [ %add, %for.inc ], [ 0, %for.body.preheader ]
+  %res11.059 = phi i32 [ %add18, %for.inc ], [ 1, %for.body.preheader ]
+  %res10.058 = phi i32 [ %add16, %for.inc ], [ 1, %for.body.preheader ]
+  %res01.057 = phi i32 [ %add8, %for.inc ], [ 1, %for.body.preheader ]
+  %res00.056 = phi i32 [ %add, %for.inc ], [ 1, %for.body.preheader ]
   %0 = load i32, ptr %x.addr.062, align 4
   %1 = load i32, ptr %y.addr.061, align 4
   %conv5 = and i32 %1, 255
Index: llvm/test/Transforms/LoopUnroll/PowerPC/a2-unrolling.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/PowerPC/a2-unrolling.ll
+++ llvm/test/Transforms/LoopUnroll/PowerPC/a2-unrolling.ll
@@ -8,7 +8,7 @@
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
-  %sum.02 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+  %sum.02 = phi i32 [ %add, %for.body ], [ 1, %entry ]
   %arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
   %0 = load i32, ptr %arrayidx, align 4
   %add = add nsw i32 %0, %sum.02
Index: llvm/test/Transforms/LoopUnroll/X86/partial.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/X86/partial.ll
+++ llvm/test/Transforms/LoopUnroll/X86/partial.ll
@@ -77,7 +77,7 @@
 
 for.body:                                         ; preds = %entry, %for.body
   %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
-  %reduction.026 = phi i16 [ %add14, %for.body ], [ 0, %entry ]
+  %reduction.026 = phi i16 [ %add14, %for.body ], [ 1, %entry ]
   %arrayidx = getelementptr inbounds i16, ptr %arr, i64 %indvars.iv
   %0 = load i16, ptr %arrayidx, align 2
   %mul = shl i16 %0, 1
Index: llvm/test/Transforms/LoopUnroll/followup.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/followup.ll
+++ llvm/test/Transforms/LoopUnroll/followup.ll
@@ -13,7 +13,7 @@
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
-  %sum.02 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+  %sum.02 = phi i32 [ %add, %for.body ], [ 1, %entry ]
   %arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
   %0 = load i32, ptr %arrayidx, align 4
   %add = add nsw i32 %0, %sum.02
Index: llvm/test/Transforms/LoopUnroll/partially-unroll-unconditional-latch.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/partially-unroll-unconditional-latch.ll
+++ llvm/test/Transforms/LoopUnroll/partially-unroll-unconditional-latch.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -passes=loop-unroll -unroll-allow-partial -S %s -verify-loop-info -verify-dom-info -verify-loop-lcssa | FileCheck %s
+; RUN: opt -passes=loop-unroll -unroll-allow-partial -S %s -verify-loop-info -verify-dom-info -verify-loop-lcssa -unroll-allow-peeling=false | FileCheck %s
 
 @table = internal unnamed_addr global [344 x i32] zeroinitializer, align 16
 
Index: llvm/test/Transforms/LoopUnroll/peel-loop-identity-op.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/LoopUnroll/peel-loop-identity-op.ll
@@ -0,0 +1,57 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -S -passes=loop-unroll -unroll-allow-peeling | FileCheck %s
+
+declare i32 @g()
+
+define i32 @f() {
+; Preheader:
+; CHECK-LABEL: @f(
+; CHECK-NEXT:  entry:
+; 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:    [[CALL_PEEL:%.*]] = tail call signext i32 @g(i32 noundef signext 0)
+; CHECK-NEXT:    [[ADD_PEEL:%.*]] = add nsw i32 [[CALL_PEEL]], 0
+; CHECK-NEXT:    [[INC_PEEL:%.*]] = add nuw nsw i32 0, 1
+; CHECK-NEXT:    [[EXITCOND_PEEL:%.*]] = icmp ne i32 [[INC_PEEL]], 999
+; CHECK-NEXT:    br i1 [[EXITCOND_PEEL]], label [[FOR_BODY_PEEL_NEXT:%.*]], label [[FOR_COND_CLEANUP:%.*]]
+; CHECK:       for.body.peel.next:
+; CHECK-NEXT:    br label [[FOR_BODY_PEEL_NEXT1:%.*]]
+; CHECK:       for.body.peel.next1:
+; CHECK-NEXT:    br label [[ENTRY_PEEL_NEWPH:%.*]]
+; CHECK:       entry.peel.newph:
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[J_05:%.*]] = phi i32 [ [[INC_PEEL]], [[ENTRY_PEEL_NEWPH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[TOTAL_04:%.*]] = phi i32 [ [[ADD_PEEL]], [[ENTRY_PEEL_NEWPH]] ], [ [[ADD:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[CALL:%.*]] = tail call signext i32 @g(i32 noundef signext [[J_05]])
+; CHECK-NEXT:    [[ADD]] = add nsw i32 [[CALL]], [[TOTAL_04]]
+; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[J_05]], 1
+; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[INC]], 999
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       for.cond.cleanup.loopexit:
+; CHECK-NEXT:    [[ADD_LCSSA_PH:%.*]] = phi i32 [ [[ADD]], [[FOR_BODY]] ]
+; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
+; CHECK:       for.cond.cleanup:
+; CHECK-NEXT:    [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD_PEEL]], [[FOR_BODY_PEEL]] ], [ [[ADD_LCSSA_PH]], [[FOR_COND_CLEANUP_LOOPEXIT]] ]
+; CHECK-NEXT:    ret i32 [[ADD_LCSSA]]
+;
+entry:
+  br label %for.body
+
+; Loop:
+for.body:                                         ; preds = %entry, %for.body
+  %j.05 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
+  %total.04 = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %call = tail call signext i32 @g(i32 noundef signext %j.05)
+  %add = add nsw i32 %call, %total.04
+  %inc = add nuw nsw i32 %j.05, 1
+  %exitcond = icmp ne i32 %inc, 999
+  br i1 %exitcond, label %for.body, label %for.cond.cleanup
+
+; Exit blocks
+for.cond.cleanup:                                 ; preds = %for.body
+  %add.lcssa = phi i32 [ %add, %for.body ]
+  ret i32 %add.lcssa
+}
Index: llvm/test/Transforms/LoopUnroll/peel-loop-not-forced.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/peel-loop-not-forced.ll
+++ llvm/test/Transforms/LoopUnroll/peel-loop-not-forced.ll
@@ -187,7 +187,7 @@
   %i = phi i32 [ 0, %entry ], [ %inc, %loop ]
   %phi.a = phi i32 [ %a, %entry ], [ %phi.b, %loop ]
   %phi.b = phi i32 [ %b, %entry ], [ %phi.a, %loop ]
-  %sum = phi i32 [ 0, %entry], [ %incsum, %loop ]
+  %sum = phi i32 [ 2, %entry], [ %incsum, %loop ]
   %incsum = add i32 %sum, %phi.a
   %inc = add i32 %i, 1
   %cmp = icmp slt i32 %i, 1000
Index: llvm/test/Transforms/LoopUnroll/peel-to-turn-invariant-accesses-dereferenceable.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/peel-to-turn-invariant-accesses-dereferenceable.ll
+++ llvm/test/Transforms/LoopUnroll/peel-to-turn-invariant-accesses-dereferenceable.ll
@@ -90,7 +90,7 @@
 ; CHECK-NEXT:    br label [[LOOP_HEADER:%.*]]
 ; CHECK:       loop.header:
 ; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 1, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
-; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
+; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
 ; CHECK-NEXT:    br i1 [[C_1:%.*]], label [[THEN:%.*]], label [[EXIT_2:%.*]]
 ; CHECK:       then:
 ; CHECK-NEXT:    [[I:%.*]] = load i32, ptr [[INV:%.*]], align 4
@@ -122,7 +122,7 @@
 
 loop.header:
   %iv = phi i32 [ 1, %entry ], [ %iv.next, %loop.latch ]
-  %sum = phi i32 [ 0, %entry ], [ %sum.next, %loop.latch ]
+  %sum = phi i32 [ 1, %entry ], [ %sum.next, %loop.latch ]
   br i1 %c.1, label %then, label %exit.2
 
 then:
@@ -162,7 +162,7 @@
 ; CHECK-NEXT:    br label [[LOOP_HEADER:%.*]]
 ; CHECK:       loop.header:
 ; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 1, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
-; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
+; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
 ; CHECK-NEXT:    [[I:%.*]] = load i32, ptr [[INV:%.*]], align 4
 ; CHECK-NEXT:    [[C_2:%.*]] = icmp ult i32 [[I]], 2
 ; CHECK-NEXT:    br i1 [[C_2]], label [[THEN:%.*]], label [[UNREACHABLE_EXIT:%.*]]
@@ -187,7 +187,7 @@
 
 loop.header:
   %iv = phi i32 [ 1, %entry ], [ %iv.next, %loop.latch ]
-  %sum = phi i32 [ 0, %entry ], [ %sum.next, %loop.latch ]
+  %sum = phi i32 [ 1, %entry ], [ %sum.next, %loop.latch ]
   %i = load i32, ptr %inv
   %c.2 = icmp ult i32 %i, 2
   br i1 %c.2, label %then, label %unreachable.exit
@@ -217,7 +217,7 @@
 ; CHECK-NEXT:    br label [[LOOP_HEADER:%.*]]
 ; CHECK:       loop.header:
 ; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 1, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
-; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
+; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
 ; CHECK-NEXT:    [[C_1:%.*]] = icmp eq i32 [[IV]], [[X:%.*]]
 ; CHECK-NEXT:    br i1 [[C_1]], label [[THEN:%.*]], label [[ELSE:%.*]]
 ; CHECK:       then:
@@ -247,7 +247,7 @@
 
 loop.header:
   %iv = phi i32 [ 1, %entry ], [ %iv.next, %loop.latch ]
-  %sum = phi i32 [ 0, %entry ], [ %sum.next, %loop.latch ]
+  %sum = phi i32 [ 1, %entry ], [ %sum.next, %loop.latch ]
   %c.1 = icmp eq i32 %iv, %x
   br i1 %c.1, label %then, label %else
 
@@ -283,7 +283,7 @@
 ; CHECK-NEXT:    br label [[LOOP_HEADER:%.*]]
 ; CHECK:       loop.header:
 ; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 1, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
-; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
+; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
 ; CHECK-NEXT:    br i1 [[C_1:%.*]], label [[THEN:%.*]], label [[UNREACHABLE_EXIT:%.*]]
 ; CHECK:       then:
 ; CHECK-NEXT:    [[I:%.*]] = load i32, ptr [[INV:%.*]], align 4
@@ -309,7 +309,7 @@
 
 loop.header:
   %iv = phi i32 [ 1, %entry ], [ %iv.next, %loop.latch ]
-  %sum = phi i32 [ 0, %entry ], [ %sum.next, %loop.latch ]
+  %sum = phi i32 [ 1, %entry ], [ %sum.next, %loop.latch ]
   br i1 %c.1, label %then, label %unreachable.exit
 
 then:
@@ -340,7 +340,7 @@
 ; CHECK-NEXT:    br label [[LOOP_HEADER:%.*]]
 ; CHECK:       loop.header:
 ; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 1, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
-; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
+; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
 ; CHECK-NEXT:    [[I:%.*]] = load i32, ptr [[INV:%.*]], align 4
 ; CHECK-NEXT:    [[C_1:%.*]] = icmp eq i32 [[I]], 20
 ; CHECK-NEXT:    br i1 [[C_1]], label [[THEN:%.*]], label [[ELSE:%.*]]
@@ -369,7 +369,7 @@
 
 loop.header:
   %iv = phi i32 [ 1, %entry ], [ %iv.next, %loop.latch ]
-  %sum = phi i32 [ 0, %entry ], [ %sum.next, %loop.latch ]
+  %sum = phi i32 [ 1, %entry ], [ %sum.next, %loop.latch ]
   %i = load i32, ptr %inv
   %c.1 = icmp eq i32 %i, 20
   br i1 %c.1, label %then, label %else
@@ -406,7 +406,7 @@
 ; CHECK-NEXT:    br label [[LOOP_HEADER:%.*]]
 ; CHECK:       loop.header:
 ; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 1, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
-; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
+; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
 ; CHECK-NEXT:    br i1 [[C_1:%.*]], label [[THEN:%.*]], label [[DEOPT_EXIT:%.*]]
 ; CHECK:       then:
 ; CHECK-NEXT:    [[I:%.*]] = load i32, ptr [[INV:%.*]], align 4
@@ -432,7 +432,7 @@
 
 loop.header:
   %iv = phi i32 [ 1, %entry ], [ %iv.next, %loop.latch ]
-  %sum = phi i32 [ 0, %entry ], [ %sum.next, %loop.latch ]
+  %sum = phi i32 [ 1, %entry ], [ %sum.next, %loop.latch ]
   br i1 %c.1, label %then, label %deopt.exit
 
 then:
@@ -462,7 +462,7 @@
 ; CHECK-NEXT:    br label [[LOOP_HEADER:%.*]]
 ; CHECK:       loop.header:
 ; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 1, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
-; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
+; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
 ; CHECK-NEXT:    [[C_1:%.*]] = icmp ult i32 [[IV]], 1000
 ; CHECK-NEXT:    br i1 [[C_1]], label [[THEN:%.*]], label [[EXIT:%.*]]
 ; CHECK:       then:
@@ -487,7 +487,7 @@
 
 loop.header:
   %iv = phi i32 [ 1, %entry ], [ %iv.next, %loop.latch ]
-  %sum = phi i32 [ 0, %entry ], [ %sum.next, %loop.latch ]
+  %sum = phi i32 [ 1, %entry ], [ %sum.next, %loop.latch ]
   %c.1 = icmp ult i32 %iv, 1000
   br i1 %c.1, label %then, label %exit
 
@@ -517,7 +517,7 @@
 ; CHECK-NEXT:    br label [[LOOP_HEADER:%.*]]
 ; CHECK:       loop.header:
 ; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 1, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
-; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
+; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
 ; CHECK-NEXT:    br i1 [[C_1:%.*]], label [[THEN:%.*]], label [[UNREACHABLE_EXIT:%.*]]
 ; CHECK:       then:
 ; CHECK-NEXT:    [[I:%.*]] = load i32, ptr [[INV:%.*]], align 4
@@ -542,7 +542,7 @@
 
 loop.header:
   %iv = phi i32 [ 1, %entry ], [ %iv.next, %loop.latch ]
-  %sum = phi i32 [ 0, %entry ], [ %sum.next, %loop.latch ]
+  %sum = phi i32 [ 1, %entry ], [ %sum.next, %loop.latch ]
   br i1 %c.1, label %then, label %unreachable.exit
 
 then:
@@ -574,7 +574,7 @@
 ; CHECK-NEXT:    br label [[LOOP_HEADER:%.*]]
 ; CHECK:       loop.header:
 ; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 1, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
-; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
+; CHECK-NEXT:    [[SUM:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[LOOP_LATCH]] ]
 ; CHECK-NEXT:    br i1 [[C_1:%.*]], label [[THEN:%.*]], label [[UNREACHABLE_EXIT:%.*]]
 ; CHECK:       then:
 ; CHECK-NEXT:    [[I:%.*]] = load i32, ptr @glob, align 4
@@ -599,7 +599,7 @@
 
 loop.header:
   %iv = phi i32 [ 1, %entry ], [ %iv.next, %loop.latch ]
-  %sum = phi i32 [ 0, %entry ], [ %sum.next, %loop.latch ]
+  %sum = phi i32 [ 1, %entry ], [ %sum.next, %loop.latch ]
   br i1 %c.1, label %then, label %unreachable.exit
 
 then:
Index: llvm/test/Transforms/LoopUnroll/runtime-epilog-debuginfo.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/runtime-epilog-debuginfo.ll
+++ llvm/test/Transforms/LoopUnroll/runtime-epilog-debuginfo.ll
@@ -1,4 +1,4 @@
-; RUN: opt -passes=loop-unroll -unroll-runtime -unroll-runtime-epilog -S %s | FileCheck %s
+; RUN: opt -passes=loop-unroll -unroll-runtime -unroll-runtime-epilog -unroll-allow-peeling=false -S %s | FileCheck %s
 
 ; Test that epilogue is tagged with the same debug information as original loop body rather than original loop exit.
 
Index: llvm/test/Transforms/LoopUnroll/runtime-loop-at-most-two-exits.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/runtime-loop-at-most-two-exits.ll
+++ llvm/test/Transforms/LoopUnroll/runtime-loop-at-most-two-exits.ll
@@ -15,7 +15,7 @@
 ; ENABLED-NEXT:    br label [[HEADER:%.*]]
 ; ENABLED:       header:
 ; ENABLED-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY_NEW]] ], [ [[INDVARS_IV_NEXT_7:%.*]], [[FOR_BODY_7:%.*]] ]
-; ENABLED-NEXT:    [[SUM_02:%.*]] = phi i32 [ 0, [[ENTRY_NEW]] ], [ [[ADD_7:%.*]], [[FOR_BODY_7]] ]
+; ENABLED-NEXT:    [[SUM_02:%.*]] = phi i32 [ 1, [[ENTRY_NEW]] ], [ [[ADD_7:%.*]], [[FOR_BODY_7]] ]
 ; ENABLED-NEXT:    [[NITER:%.*]] = phi i64 [ 0, [[ENTRY_NEW]] ], [ [[NITER_NEXT_7:%.*]], [[FOR_BODY_7]] ]
 ; ENABLED-NEXT:    [[CMP:%.*]] = icmp eq i64 [[N]], 42
 ; ENABLED-NEXT:    br i1 [[CMP]], label [[FOR_EXIT2_LOOPEXIT:%.*]], label [[FOR_BODY:%.*]]
@@ -91,7 +91,7 @@
 ; ENABLED:       for.end.unr-lcssa:
 ; ENABLED-NEXT:    [[SUM_0_LCSSA_PH:%.*]] = phi i32 [ undef, [[ENTRY:%.*]] ], [ [[SUM_0_LCSSA_PH_PH]], [[FOR_END_UNR_LCSSA_LOOPEXIT]] ]
 ; ENABLED-NEXT:    [[INDVARS_IV_UNR:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[INDVARS_IV_UNR_PH]], [[FOR_END_UNR_LCSSA_LOOPEXIT]] ]
-; ENABLED-NEXT:    [[SUM_02_UNR:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[SUM_02_UNR_PH]], [[FOR_END_UNR_LCSSA_LOOPEXIT]] ]
+; ENABLED-NEXT:    [[SUM_02_UNR:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[SUM_02_UNR_PH]], [[FOR_END_UNR_LCSSA_LOOPEXIT]] ]
 ; ENABLED-NEXT:    [[LCMP_MOD:%.*]] = icmp ne i64 [[XTRAITER]], 0
 ; ENABLED-NEXT:    br i1 [[LCMP_MOD]], label [[HEADER_EPIL_PREHEADER:%.*]], label [[FOR_END:%.*]]
 ; ENABLED:       header.epil.preheader:
@@ -132,7 +132,7 @@
 ; DISABLED-NEXT:    br label [[HEADER:%.*]]
 ; DISABLED:       header:
 ; DISABLED-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY:%.*]] ], [ 0, [[ENTRY:%.*]] ]
-; DISABLED-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY]] ]
+; DISABLED-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[FOR_BODY]] ], [ 1, [[ENTRY]] ]
 ; DISABLED-NEXT:    [[CMP:%.*]] = icmp eq i64 [[N:%.*]], 42
 ; DISABLED-NEXT:    br i1 [[CMP]], label [[FOR_EXIT2:%.*]], label [[FOR_BODY]]
 ; DISABLED:       for.body:
@@ -154,7 +154,7 @@
 
 header:
   %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
-  %sum.02 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+  %sum.02 = phi i32 [ %add, %for.body ], [ 1, %entry ]
   %cmp = icmp eq i64 %n, 42
   br i1 %cmp, label %for.exit2, label %for.body
 
Index: llvm/test/Transforms/LoopUnroll/runtime-loop-multiple-exits.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/runtime-loop-multiple-exits.ll
+++ llvm/test/Transforms/LoopUnroll/runtime-loop-multiple-exits.ll
@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: -p
-; RUN: opt < %s -passes=loop-unroll -unroll-runtime=true -unroll-runtime-epilog=true -unroll-runtime-multi-exit=true -verify-loop-lcssa -verify-dom-info -verify-loop-info -S | FileCheck %s -check-prefixes=CHECK,EPILOG
-; RUN: opt < %s -passes=loop-unroll -unroll-runtime -unroll-count=2 -unroll-runtime-epilog=true -unroll-runtime-multi-exit=true -verify-loop-lcssa -verify-dom-info -verify-loop-info -S | FileCheck %s -check-prefixes=CHECK,EPILOG-BLOCK
-; RUN: opt < %s -passes=loop-unroll -unroll-runtime=true -unroll-runtime-epilog=false -unroll-runtime-multi-exit=true -verify-loop-lcssa -verify-dom-info -verify-loop-info -S | FileCheck %s -check-prefixes=CHECK,PROLOG
-; RUN: opt < %s -passes=loop-unroll -unroll-runtime -unroll-runtime-epilog=false -unroll-count=2 -unroll-runtime-multi-exit=true -verify-loop-lcssa -verify-dom-info -verify-loop-info -S | FileCheck %s -check-prefixes=CHECK,PROLOG-BLOCK
+; RUN: opt < %s -passes=loop-unroll -unroll-runtime=true -unroll-runtime-epilog=true -unroll-runtime-multi-exit=true -verify-loop-lcssa -verify-dom-info -verify-loop-info -S -unroll-allow-peeling=false | FileCheck %s -check-prefixes=CHECK,EPILOG
+; RUN: opt < %s -passes=loop-unroll -unroll-runtime -unroll-count=2 -unroll-runtime-epilog=true -unroll-runtime-multi-exit=true -verify-loop-lcssa -verify-dom-info -verify-loop-info -S -unroll-allow-peeling=false | FileCheck %s -check-prefixes=CHECK,EPILOG-BLOCK
+; RUN: opt < %s -passes=loop-unroll -unroll-runtime=true -unroll-runtime-epilog=false -unroll-runtime-multi-exit=true -verify-loop-lcssa -verify-dom-info -verify-loop-info -S -unroll-allow-peeling=false | FileCheck %s -check-prefixes=CHECK,PROLOG
+; RUN: opt < %s -passes=loop-unroll -unroll-runtime -unroll-runtime-epilog=false -unroll-count=2 -unroll-runtime-multi-exit=true -verify-loop-lcssa -verify-dom-info -verify-loop-info -S -unroll-allow-peeling=false | FileCheck %s -check-prefixes=CHECK,PROLOG-BLOCK
 
 ; REQUIRES: asserts
 
Index: llvm/test/Transforms/LoopUnroll/runtime-loop.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/runtime-loop.ll
+++ llvm/test/Transforms/LoopUnroll/runtime-loop.ll
@@ -56,7 +56,7 @@
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
-  %sum.02 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+  %sum.02 = phi i32 [ %add, %for.body ], [ 1, %entry ]
   %arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
   %0 = load i32, ptr %arrayidx, align 4
   %add = add nsw i32 %0, %sum.02
@@ -66,7 +66,7 @@
   br i1 %exitcond, label %for.end, label %for.body
 
 for.end:                                          ; preds = %for.body, %entry
-  %sum.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %sum.0.lcssa = phi i32 [ 1, %entry ], [ %add, %for.body ]
   ret i32 %sum.0.lcssa
 }
 
@@ -85,7 +85,7 @@
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
-  %sum.01 = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %sum.01 = phi i32 [ 1, %entry ], [ %add, %for.body ]
   %arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
   %0 = load i32, ptr %arrayidx, align 4
   %add = add nsw i32 %0, %sum.01
@@ -148,7 +148,7 @@
 for.body:                                         ; preds = %for.body, %entry
   %p.addr.05 = phi ptr [ %incdec.ptr, %for.body ], [ %p, %entry ]
   %len.addr.04 = phi i32 [ %sub, %for.body ], [ %len, %entry ]
-  %res.03 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+  %res.03 = phi i32 [ %add, %for.body ], [ 1, %entry ]
   %incdec.ptr = getelementptr inbounds i16, ptr %p.addr.05, i64 1
   %0 = load i16, ptr %p.addr.05, align 2
   %conv = zext i16 %0 to i32
@@ -189,7 +189,7 @@
 for.body:                                         ; preds = %for.body, %entry
   %p.addr.05 = phi ptr [ %incdec.ptr, %for.body ], [ %p, %entry ]
   %len.addr.04 = phi i32 [ %sub, %for.body ], [ %len, %entry ]
-  %res.03 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+  %res.03 = phi i32 [ %add, %for.body ], [ 1, %entry ]
   %incdec.ptr = getelementptr inbounds i16, ptr %p.addr.05, i64 1
   %0 = load i16, ptr %p.addr.05, align 2
   %conv = zext i16 %0 to i32
Index: llvm/test/Transforms/LoopUnroll/runtime-loop2.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/runtime-loop2.ll
+++ llvm/test/Transforms/LoopUnroll/runtime-loop2.ll
@@ -24,7 +24,7 @@
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
-  %sum.02 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+  %sum.02 = phi i32 [ %add, %for.body ], [ 1, %entry ]
   %arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
   %0 = load i32, ptr %arrayidx, align 4
   %add = add nsw i32 %0, %sum.02
Index: llvm/test/Transforms/LoopUnroll/runtime-loop3.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/runtime-loop3.ll
+++ llvm/test/Transforms/LoopUnroll/runtime-loop3.ll
@@ -21,7 +21,7 @@
   br i1 %cmp28, label %for.body3, label %for.inc5
 
 for.body3:                                        ; preds = %for.cond1.preheader, %for.body3
-  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body3 ], [ 0, %for.cond1.preheader ]
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body3 ], [ 1, %for.cond1.preheader ]
   %sum.19 = phi i32 [ %add4, %for.body3 ], [ %sum.012, %for.cond1.preheader ]
   %0 = add nsw i64 %indvars.iv, %indvars.iv16
   %arrayidx = getelementptr inbounds i32, ptr %a, i64 %0
Index: llvm/test/Transforms/LoopUnroll/runtime-multiexit-heuristic.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/runtime-multiexit-heuristic.ll
+++ llvm/test/Transforms/LoopUnroll/runtime-multiexit-heuristic.ll
@@ -25,7 +25,7 @@
 ; CHECK-NEXT:    br label [[HEADER:%.*]]
 ; CHECK:       header:
 ; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY_NEW]] ], [ [[INDVARS_IV_NEXT_7:%.*]], [[LATCH_7:%.*]] ]
-; CHECK-NEXT:    [[SUM_02:%.*]] = phi i32 [ 0, [[ENTRY_NEW]] ], [ [[ADD_7:%.*]], [[LATCH_7]] ]
+; CHECK-NEXT:    [[SUM_02:%.*]] = phi i32 [ 1, [[ENTRY_NEW]] ], [ [[ADD_7:%.*]], [[LATCH_7]] ]
 ; CHECK-NEXT:    [[NITER:%.*]] = phi i64 [ 0, [[ENTRY_NEW]] ], [ [[NITER_NEXT_7:%.*]], [[LATCH_7]] ]
 ; CHECK-NEXT:    br label [[FOR_EXITING_BLOCK:%.*]]
 ; CHECK:       for.exiting_block:
@@ -107,7 +107,7 @@
 ; CHECK:       latchexit.unr-lcssa:
 ; CHECK-NEXT:    [[SUM_0_LCSSA_PH:%.*]] = phi i32 [ undef, [[ENTRY:%.*]] ], [ [[ADD_7]], [[LATCHEXIT_UNR_LCSSA_LOOPEXIT]] ]
 ; CHECK-NEXT:    [[INDVARS_IV_UNR:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[INDVARS_IV_NEXT_7]], [[LATCHEXIT_UNR_LCSSA_LOOPEXIT]] ]
-; CHECK-NEXT:    [[SUM_02_UNR:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[ADD_7]], [[LATCHEXIT_UNR_LCSSA_LOOPEXIT]] ]
+; CHECK-NEXT:    [[SUM_02_UNR:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[ADD_7]], [[LATCHEXIT_UNR_LCSSA_LOOPEXIT]] ]
 ; CHECK-NEXT:    [[LCMP_MOD_NOT:%.*]] = icmp eq i64 [[XTRAITER]], 0
 ; CHECK-NEXT:    br i1 [[LCMP_MOD_NOT]], label [[LATCHEXIT:%.*]], label [[HEADER_EPIL_PREHEADER:%.*]]
 ; CHECK:       header.epil.preheader:
@@ -148,7 +148,7 @@
 ; NOUNROLL-NEXT:    br label [[HEADER:%.*]]
 ; NOUNROLL:       header:
 ; NOUNROLL-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[LATCH:%.*]] ], [ 0, [[ENTRY:%.*]] ]
-; NOUNROLL-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 0, [[ENTRY]] ]
+; NOUNROLL-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 1, [[ENTRY]] ]
 ; NOUNROLL-NEXT:    br label [[FOR_EXITING_BLOCK:%.*]]
 ; NOUNROLL:       for.exiting_block:
 ; NOUNROLL-NEXT:    [[CMP:%.*]] = icmp eq i64 [[N:%.*]], 42
@@ -180,7 +180,7 @@
 ; ENABLED-NEXT:    br label [[HEADER:%.*]]
 ; ENABLED:       header:
 ; ENABLED-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY_NEW]] ], [ [[INDVARS_IV_NEXT_7:%.*]], [[LATCH_7:%.*]] ]
-; ENABLED-NEXT:    [[SUM_02:%.*]] = phi i32 [ 0, [[ENTRY_NEW]] ], [ [[ADD_7:%.*]], [[LATCH_7]] ]
+; ENABLED-NEXT:    [[SUM_02:%.*]] = phi i32 [ 1, [[ENTRY_NEW]] ], [ [[ADD_7:%.*]], [[LATCH_7]] ]
 ; ENABLED-NEXT:    [[NITER:%.*]] = phi i64 [ 0, [[ENTRY_NEW]] ], [ [[NITER_NEXT_7:%.*]], [[LATCH_7]] ]
 ; ENABLED-NEXT:    br label [[FOR_EXITING_BLOCK:%.*]]
 ; ENABLED:       for.exiting_block:
@@ -272,7 +272,7 @@
 ; ENABLED:       latchexit.unr-lcssa:
 ; ENABLED-NEXT:    [[SUM_0_LCSSA_PH:%.*]] = phi i32 [ undef, [[ENTRY:%.*]] ], [ [[SUM_0_LCSSA_PH_PH]], [[LATCHEXIT_UNR_LCSSA_LOOPEXIT]] ]
 ; ENABLED-NEXT:    [[INDVARS_IV_UNR:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[INDVARS_IV_UNR_PH]], [[LATCHEXIT_UNR_LCSSA_LOOPEXIT]] ]
-; ENABLED-NEXT:    [[SUM_02_UNR:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[SUM_02_UNR_PH]], [[LATCHEXIT_UNR_LCSSA_LOOPEXIT]] ]
+; ENABLED-NEXT:    [[SUM_02_UNR:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[SUM_02_UNR_PH]], [[LATCHEXIT_UNR_LCSSA_LOOPEXIT]] ]
 ; ENABLED-NEXT:    [[LCMP_MOD:%.*]] = icmp ne i64 [[XTRAITER]], 0
 ; ENABLED-NEXT:    br i1 [[LCMP_MOD]], label [[HEADER_EPIL_PREHEADER:%.*]], label [[LATCHEXIT:%.*]]
 ; ENABLED:       header.epil.preheader:
@@ -316,7 +316,7 @@
 
 header:
   %indvars.iv = phi i64 [ %indvars.iv.next, %latch ], [ 0, %entry ]
-  %sum.02 = phi i32 [ %add, %latch ], [ 0, %entry ]
+  %sum.02 = phi i32 [ %add, %latch ], [ 1, %entry ]
   br label %for.exiting_block
 
 for.exiting_block:
@@ -348,7 +348,7 @@
 ; CHECK-NEXT:    br label [[HEADER:%.*]]
 ; CHECK:       header:
 ; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[LATCH:%.*]] ], [ 0, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 0, [[ENTRY]] ]
+; CHECK-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 1, [[ENTRY]] ]
 ; CHECK-NEXT:    br label [[FOR_EXITING_BLOCK:%.*]]
 ; CHECK:       for.exiting_block:
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i64 [[N:%.*]], 42
@@ -370,7 +370,7 @@
 ; NOUNROLL-NEXT:    br label [[HEADER:%.*]]
 ; NOUNROLL:       header:
 ; NOUNROLL-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[LATCH:%.*]] ], [ 0, [[ENTRY:%.*]] ]
-; NOUNROLL-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 0, [[ENTRY]] ]
+; NOUNROLL-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 1, [[ENTRY]] ]
 ; NOUNROLL-NEXT:    br label [[FOR_EXITING_BLOCK:%.*]]
 ; NOUNROLL:       for.exiting_block:
 ; NOUNROLL-NEXT:    [[CMP:%.*]] = icmp eq i64 [[N:%.*]], 42
@@ -401,7 +401,7 @@
 ; ENABLED-NEXT:    br label [[HEADER:%.*]]
 ; ENABLED:       header:
 ; ENABLED-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY_NEW]] ], [ [[INDVARS_IV_NEXT_7:%.*]], [[LATCH_7:%.*]] ]
-; ENABLED-NEXT:    [[SUM_02:%.*]] = phi i32 [ 0, [[ENTRY_NEW]] ], [ [[ADD_7:%.*]], [[LATCH_7]] ]
+; ENABLED-NEXT:    [[SUM_02:%.*]] = phi i32 [ 1, [[ENTRY_NEW]] ], [ [[ADD_7:%.*]], [[LATCH_7]] ]
 ; ENABLED-NEXT:    [[NITER:%.*]] = phi i64 [ 0, [[ENTRY_NEW]] ], [ [[NITER_NEXT_7:%.*]], [[LATCH_7]] ]
 ; ENABLED-NEXT:    br label [[FOR_EXITING_BLOCK:%.*]]
 ; ENABLED:       for.exiting_block:
@@ -493,7 +493,7 @@
 ; ENABLED:       latchexit.unr-lcssa:
 ; ENABLED-NEXT:    [[SUM_0_LCSSA_PH:%.*]] = phi i32 [ undef, [[ENTRY:%.*]] ], [ [[SUM_0_LCSSA_PH_PH]], [[LATCHEXIT_UNR_LCSSA_LOOPEXIT]] ]
 ; ENABLED-NEXT:    [[INDVARS_IV_UNR:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[INDVARS_IV_UNR_PH]], [[LATCHEXIT_UNR_LCSSA_LOOPEXIT]] ]
-; ENABLED-NEXT:    [[SUM_02_UNR:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[SUM_02_UNR_PH]], [[LATCHEXIT_UNR_LCSSA_LOOPEXIT]] ]
+; ENABLED-NEXT:    [[SUM_02_UNR:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[SUM_02_UNR_PH]], [[LATCHEXIT_UNR_LCSSA_LOOPEXIT]] ]
 ; ENABLED-NEXT:    [[LCMP_MOD:%.*]] = icmp ne i64 [[XTRAITER]], 0
 ; ENABLED-NEXT:    br i1 [[LCMP_MOD]], label [[HEADER_EPIL_PREHEADER:%.*]], label [[LATCHEXIT:%.*]]
 ; ENABLED:       header.epil.preheader:
@@ -536,7 +536,7 @@
 
 header:
   %indvars.iv = phi i64 [ %indvars.iv.next, %latch ], [ 0, %entry ]
-  %sum.02 = phi i32 [ %add, %latch ], [ 0, %entry ]
+  %sum.02 = phi i32 [ %add, %latch ], [ 1, %entry ]
   br label %for.exiting_block
 
 for.exiting_block:
@@ -569,7 +569,7 @@
 ; CHECK-NEXT:    br label [[HEADER:%.*]]
 ; CHECK:       header:
 ; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[LATCH:%.*]] ], [ 0, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 0, [[ENTRY]] ]
+; CHECK-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 1, [[ENTRY]] ]
 ; CHECK-NEXT:    br label [[FOR_EXITING_BLOCK:%.*]]
 ; CHECK:       for.exiting_block:
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i64 [[N:%.*]], 42
@@ -591,7 +591,7 @@
 ; NOUNROLL-NEXT:    br label [[HEADER:%.*]]
 ; NOUNROLL:       header:
 ; NOUNROLL-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[LATCH:%.*]] ], [ 0, [[ENTRY:%.*]] ]
-; NOUNROLL-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 0, [[ENTRY]] ]
+; NOUNROLL-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 1, [[ENTRY]] ]
 ; NOUNROLL-NEXT:    br label [[FOR_EXITING_BLOCK:%.*]]
 ; NOUNROLL:       for.exiting_block:
 ; NOUNROLL-NEXT:    [[CMP:%.*]] = icmp eq i64 [[N:%.*]], 42
@@ -614,7 +614,7 @@
 ; ENABLED-NEXT:    br label [[HEADER:%.*]]
 ; ENABLED:       header:
 ; ENABLED-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[LATCH:%.*]] ], [ 0, [[ENTRY:%.*]] ]
-; ENABLED-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 0, [[ENTRY]] ]
+; ENABLED-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 1, [[ENTRY]] ]
 ; ENABLED-NEXT:    br label [[FOR_EXITING_BLOCK:%.*]]
 ; ENABLED:       for.exiting_block:
 ; ENABLED-NEXT:    [[CMP:%.*]] = icmp eq i64 [[N:%.*]], 42
@@ -637,7 +637,7 @@
 
 header:
   %indvars.iv = phi i64 [ %indvars.iv.next, %latch ], [ 0, %entry ]
-  %sum.02 = phi i32 [ %add, %latch ], [ 0, %entry ]
+  %sum.02 = phi i32 [ %add, %latch ], [ 1, %entry ]
   br label %for.exiting_block
 
 for.exiting_block:
@@ -669,7 +669,7 @@
 ; CHECK-NEXT:    br label [[HEADER:%.*]]
 ; CHECK:       header:
 ; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[LATCH:%.*]] ], [ 0, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 0, [[ENTRY]] ]
+; CHECK-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 1, [[ENTRY]] ]
 ; CHECK-NEXT:    br label [[FOR_EXITING_BLOCK:%.*]]
 ; CHECK:       for.exiting_block:
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i64 [[INDVARS_IV]], 4096
@@ -691,7 +691,7 @@
 ; NOUNROLL-NEXT:    br label [[HEADER:%.*]]
 ; NOUNROLL:       header:
 ; NOUNROLL-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[LATCH:%.*]] ], [ 0, [[ENTRY:%.*]] ]
-; NOUNROLL-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 0, [[ENTRY]] ]
+; NOUNROLL-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 1, [[ENTRY]] ]
 ; NOUNROLL-NEXT:    br label [[FOR_EXITING_BLOCK:%.*]]
 ; NOUNROLL:       for.exiting_block:
 ; NOUNROLL-NEXT:    [[CMP:%.*]] = icmp eq i64 [[INDVARS_IV]], 4096
@@ -714,7 +714,7 @@
 ; ENABLED-NEXT:    br label [[HEADER:%.*]]
 ; ENABLED:       header:
 ; ENABLED-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[LATCH:%.*]] ], [ 0, [[ENTRY:%.*]] ]
-; ENABLED-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 0, [[ENTRY]] ]
+; ENABLED-NEXT:    [[SUM_02:%.*]] = phi i32 [ [[ADD:%.*]], [[LATCH]] ], [ 1, [[ENTRY]] ]
 ; ENABLED-NEXT:    br label [[FOR_EXITING_BLOCK:%.*]]
 ; ENABLED:       for.exiting_block:
 ; ENABLED-NEXT:    [[CMP:%.*]] = icmp eq i64 [[INDVARS_IV]], 4096
@@ -737,7 +737,7 @@
 
 header:
   %indvars.iv = phi i64 [ %indvars.iv.next, %latch ], [ 0, %entry ]
-  %sum.02 = phi i32 [ %add, %latch ], [ 0, %entry ]
+  %sum.02 = phi i32 [ %add, %latch ], [ 1, %entry ]
   br label %for.exiting_block
 
 for.exiting_block:
Index: llvm/test/Transforms/LoopUnroll/unroll-cost-symbolic-execute.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/unroll-cost-symbolic-execute.ll
+++ llvm/test/Transforms/LoopUnroll/unroll-cost-symbolic-execute.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -passes=loop-unroll -S -unroll-threshold=120 -unroll-max-iteration-count-to-analyze=100 < %s | FileCheck %s
+; RUN: opt -passes=loop-unroll -S -unroll-threshold=120 -unroll-max-iteration-count-to-analyze=100 -unroll-allow-peeling=false < %s | FileCheck %s
 
 ; TODO: None of the if.false blocks are reachable, it would be nice if
 ; the output of unrolling made this obvious and didn't rely on other
Index: llvm/test/Transforms/LoopUnroll/unroll-heuristics-pgo.ll
===================================================================
--- llvm/test/Transforms/LoopUnroll/unroll-heuristics-pgo.ll
+++ llvm/test/Transforms/LoopUnroll/unroll-heuristics-pgo.ll
@@ -15,7 +15,7 @@
 
 loop:
   %iv = phi i64 [ 0, %entry ], [ %inc, %loop ]
-  %r  = phi i32 [ 0, %entry ], [ %add, %loop ]
+  %r  = phi i32 [ 1, %entry ], [ %add, %loop ]
   %arrayidx = getelementptr inbounds i32, ptr %src, i64 %iv
   %src_element = load i32, ptr %arrayidx, align 4
   %array_const_idx = getelementptr inbounds [9 x i32], ptr @known_constant, i64 0, i64 %iv
@@ -39,7 +39,7 @@
 
 loop:
   %iv = phi i64 [ 0, %entry ], [ %inc, %loop ]
-  %r  = phi i32 [ 0, %entry ], [ %add, %loop ]
+  %r  = phi i32 [ 1, %entry ], [ %add, %loop ]
   %arrayidx = getelementptr inbounds i32, ptr %src, i64 %iv
   %src_element = load i32, ptr %arrayidx, align 4
   %array_const_idx = getelementptr inbounds [9 x i32], ptr @known_constant, i64 0, i64 %iv
Index: llvm/test/Transforms/PhaseOrdering/ARM/arm_mean_q7.ll
===================================================================
--- llvm/test/Transforms/PhaseOrdering/ARM/arm_mean_q7.ll
+++ llvm/test/Transforms/PhaseOrdering/ARM/arm_mean_q7.ll
@@ -16,7 +16,7 @@
 ; CHECK-NEXT:    [[TMP0:%.*]] = and i32 [[BLOCKSIZE]], -16
 ; CHECK-NEXT:    br label [[WHILE_BODY:%.*]]
 ; CHECK:       while.body:
-; CHECK-NEXT:    [[SUM_013:%.*]] = phi i32 [ [[TMP3:%.*]], [[WHILE_BODY]] ], [ 0, [[WHILE_BODY_PREHEADER]] ]
+; CHECK-NEXT:    [[SUM_013:%.*]] = phi i32 [ [[TMP3:%.*]], [[WHILE_BODY]] ], [ 1, [[WHILE_BODY_PREHEADER]] ]
 ; CHECK-NEXT:    [[PSRC_ADDR_012:%.*]] = phi ptr [ [[ADD_PTR:%.*]], [[WHILE_BODY]] ], [ [[PSRC:%.*]], [[WHILE_BODY_PREHEADER]] ]
 ; CHECK-NEXT:    [[BLKCNT_011:%.*]] = phi i32 [ [[DEC:%.*]], [[WHILE_BODY]] ], [ [[SHR]], [[WHILE_BODY_PREHEADER]] ]
 ; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, ptr [[PSRC_ADDR_012]], align 1
@@ -31,7 +31,7 @@
 ; CHECK-NEXT:    br label [[WHILE_END]]
 ; CHECK:       while.end:
 ; CHECK-NEXT:    [[PSRC_ADDR_0_LCSSA:%.*]] = phi ptr [ [[PSRC]], [[ENTRY:%.*]] ], [ [[UGLYGEP]], [[WHILE_END_LOOPEXIT]] ]
-; CHECK-NEXT:    [[SUM_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[TMP3]], [[WHILE_END_LOOPEXIT]] ]
+; CHECK-NEXT:    [[SUM_0_LCSSA:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[TMP3]], [[WHILE_END_LOOPEXIT]] ]
 ; CHECK-NEXT:    [[AND:%.*]] = and i32 [[BLOCKSIZE]], 15
 ; CHECK-NEXT:    [[CMP2_NOT15:%.*]] = icmp eq i32 [[AND]], 0
 ; CHECK-NEXT:    br i1 [[CMP2_NOT15]], label [[WHILE_END5:%.*]], label [[VECTOR_BODY:%.*]]
@@ -63,7 +63,7 @@
   call void @llvm.lifetime.start.p0(i64 4, ptr %blkCnt) #3
   call void @llvm.lifetime.start.p0(i64 16, ptr %vecSrc) #3
   call void @llvm.lifetime.start.p0(i64 4, ptr %sum) #3
-  store i32 0, ptr %sum, align 4
+  store i32 1, ptr %sum, align 4
   %0 = load i32, ptr %blockSize.addr, align 4
   %shr = lshr i32 %0, 4
   store i32 %shr, ptr %blkCnt, align 4
Index: llvm/test/Transforms/PhaseOrdering/SystemZ/sub-xor.ll
===================================================================
--- llvm/test/Transforms/PhaseOrdering/SystemZ/sub-xor.ll
+++ llvm/test/Transforms/PhaseOrdering/SystemZ/sub-xor.ll
@@ -18,7 +18,7 @@
 ; CHECK-NEXT:    br label [[FOR_BODY4:%.*]]
 ; CHECK:       for.body4:
 ; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT_7:%.*]], [[FOR_BODY4]] ]
-; CHECK-NEXT:    [[SUM_11:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[ADD_7:%.*]], [[FOR_BODY4]] ]
+; CHECK-NEXT:    [[SUM_11:%.*]] = phi i32 [ 1, [[ENTRY]] ], [ [[ADD_7:%.*]], [[FOR_BODY4]] ]
 ; CHECK-NEXT:    [[IDX_NEG:%.*]] = sub nsw i64 0, [[INDVARS_IV]]
 ; CHECK-NEXT:    [[ADD_PTR:%.*]] = getelementptr inbounds i32, ptr getelementptr inbounds ([100 x i32], ptr @ARR, i64 0, i64 99), i64 [[IDX_NEG]]
 ; CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[ADD_PTR]], align 4, !tbaa [[TBAA3:![0-9]+]]
@@ -155,7 +155,7 @@
 
 for.cond:                                         ; preds = %for.inc5, %entry
   %j.0 = phi i32 [ 1, %entry ], [ %inc6, %for.inc5 ]
-  %sum.0 = phi i32 [ 0, %entry ], [ %sum.1, %for.inc5 ]
+  %sum.0 = phi i32 [ 1, %entry ], [ %sum.1, %for.inc5 ]
   %cmp = icmp slt i32 %j.0, 4
   br i1 %cmp, label %for.body, label %for.cond.cleanup
 
Index: llvm/test/Transforms/PhaseOrdering/X86/ctlz-loop.ll
===================================================================
--- llvm/test/Transforms/PhaseOrdering/X86/ctlz-loop.ll
+++ llvm/test/Transforms/PhaseOrdering/X86/ctlz-loop.ll
@@ -29,13 +29,13 @@
 ; CHECK-NEXT:    br label [[WHILE_BODY:%.*]]
 ; CHECK:       while.body:
 ; CHECK-NEXT:    [[N_ADDR_03:%.*]] = phi i32 [ [[TMP1:%.*]], [[WHILE_BODY]] ], [ [[TMP0]], [[WHILE_BODY_PREHEADER]] ]
-; CHECK-NEXT:    [[I_02:%.*]] = phi i32 [ [[INC:%.*]], [[WHILE_BODY]] ], [ 0, [[WHILE_BODY_PREHEADER]] ]
+; CHECK-NEXT:    [[I_02:%.*]] = phi i32 [ [[INC:%.*]], [[WHILE_BODY]] ], [ 1, [[WHILE_BODY_PREHEADER]] ]
 ; CHECK-NEXT:    [[TMP1]] = lshr i32 [[N_ADDR_03]], 1
 ; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_02]], 1
 ; CHECK-NEXT:    [[TOBOOL_NOT:%.*]] = icmp ult i32 [[N_ADDR_03]], 2
 ; CHECK-NEXT:    br i1 [[TOBOOL_NOT]], label [[WHILE_END]], label [[WHILE_BODY]]
 ; CHECK:       while.end:
-; CHECK-NEXT:    [[I_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC]], [[WHILE_BODY]] ]
+; CHECK-NEXT:    [[I_0_LCSSA:%.*]] = phi i32 [ 1, [[ENTRY:%.*]] ], [ [[INC]], [[WHILE_BODY]] ]
 ; CHECK-NEXT:    ret i32 [[I_0_LCSSA]]
 ;
 entry:
@@ -54,7 +54,7 @@
   br label %while.cond
 
 while.cond:                                       ; preds = %while.body, %cond.end
-  %i.0 = phi i32 [ 0, %cond.end ], [ %inc, %while.body ]
+  %i.0 = phi i32 [ 1, %cond.end ], [ %inc, %while.body ]
   %n.addr.0 = phi i32 [ %cond, %cond.end ], [ %shr, %while.body ]
   %tobool = icmp ne i32 %n.addr.0, 0
   br i1 %tobool, label %while.body, label %while.end
Index: llvm/test/Transforms/PhaseOrdering/pr44461-br-to-switch-rotate.ll
===================================================================
--- llvm/test/Transforms/PhaseOrdering/pr44461-br-to-switch-rotate.ll
+++ llvm/test/Transforms/PhaseOrdering/pr44461-br-to-switch-rotate.ll
@@ -11,7 +11,7 @@
 ; CHECK:       bb10:
 ; CHECK-NEXT:    [[ITER1_SROA_5_0:%.*]] = phi i64 [ 100000, [[START:%.*]] ], [ [[SPEC_SELECT:%.*]], [[BB3_I_I:%.*]] ]
 ; CHECK-NEXT:    [[ITER1_SROA_9_0:%.*]] = phi i8 [ 2, [[START]] ], [ [[TMP3:%.*]], [[BB3_I_I]] ]
-; CHECK-NEXT:    [[COUNT_1:%.*]] = phi i64 [ 0, [[START]] ], [ [[TMP4:%.*]], [[BB3_I_I]] ]
+; CHECK-NEXT:    [[COUNT_1:%.*]] = phi i64 [ 1, [[START]] ], [ [[TMP4:%.*]], [[BB3_I_I]] ]
 ; CHECK-NEXT:    switch i8 [[ITER1_SROA_9_0]], label [[BB12:%.*]] [
 ; CHECK-NEXT:    i8 2, label [[BB3_I_I]]
 ; CHECK-NEXT:    i8 0, label [[BB3_I_I]]
@@ -31,7 +31,7 @@
 bb10:                                             ; preds = %bb3.i.i, %bb6
   %iter1.sroa.5.0 = phi i64 [ 100000, %start ], [ %spec.select, %bb3.i.i ]
   %iter1.sroa.9.0 = phi i8 [ 2, %start ], [ %tmp3, %bb3.i.i ]
-  %count.1 = phi i64 [ 0, %start ], [ %tmp4, %bb3.i.i ]
+  %count.1 = phi i64 [ 1, %start ], [ %tmp4, %bb3.i.i ]
   %c1 = icmp eq i8 %iter1.sroa.9.0, 2
   %c2 = icmp eq i8 %iter1.sroa.9.0, 0
   %c3 = or i1 %c1, %c2