[LoopPred/WC] Use a dominating widenable condition to remove analyze loop exits

This implements a version of the predicateLoopExits transform from IndVarSimplify extended to exploit widenable conditions - and thus be much wider in scope of legality. The code structure ends up being almost entirely different, so I chose to duplicate this into the LoopPredication pass instead of trying to reuse the code in the IndVars.

The core notions of the transform are as follows:

    If we have a widenable condition which controls entry into the loop, we're allowed to widen it arbitrarily. Given that, it's simply a *profitability* question as to what conditions to fold into the widenable branch.
    To avoid pass ordering issues, we want to avoid widening cases that would otherwise be dischargeable. Or... widen in a form which can still be discharged. Thus, we phrase the transform as selecting one analyzeable exit from the set of analyzeable exits to keep. This avoids creating pass ordering complexities.
    Since none of the above proves that we actually exit through our analyzeable exits - we might exit through something else entirely - we limit ourselves to cases where a) the latch is analyzeable and b) the latch is predicted taken, and c) the exit being removed is statically cold.

Differential Revision: https://reviews.llvm.org/D69830

diff --git a/llvm/lib/Transforms/Scalar/LoopPredication.cpp b/llvm/lib/Transforms/Scalar/LoopPredication.cpp
index a877225..9abf6de 100644 (file)
--- a/llvm/lib/Transforms/Scalar/LoopPredication.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopPredication.cpp
@@ -250,7 +250,9 @@ struct LoopICmp {
 
 class LoopPredication {
   AliasAnalysis *AA;
+  DominatorTree *DT;
   ScalarEvolution *SE;
+  LoopInfo *LI;
   BranchProbabilityInfo *BPI;
 
   Loop *L;
@@ -302,10 +304,13 @@ class LoopPredication {
   // within the loop. We identify such unprofitable loops through BPI.
   bool isLoopProfitableToPredicate();
 
+  bool predicateLoopExits(Loop *L, SCEVExpander &Rewriter);
+
 public:
-  LoopPredication(AliasAnalysis *AA, ScalarEvolution *SE,
+  LoopPredication(AliasAnalysis *AA, DominatorTree *DT,
+                  ScalarEvolution *SE, LoopInfo *LI,
                   BranchProbabilityInfo *BPI)
-    : AA(AA), SE(SE), BPI(BPI){};
+    : AA(AA), DT(DT), SE(SE), LI(LI), BPI(BPI) {};
   bool runOnLoop(Loop *L);
 };
 
@@ -325,10 +330,12 @@ public:
     if (skipLoop(L))
       return false;
     auto *SE = &getAnalysis<ScalarEvolutionWrapperPass>().getSE();
+    auto *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
+    auto *DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
     BranchProbabilityInfo &BPI =
         getAnalysis<BranchProbabilityInfoWrapperPass>().getBPI();
     auto *AA = &getAnalysis<AAResultsWrapperPass>().getAAResults();
-    LoopPredication LP(AA, SE, &BPI);
+    LoopPredication LP(AA, DT, SE, LI, &BPI);
     return LP.runOnLoop(L);
   }
 };
@@ -354,7 +361,7 @@ PreservedAnalyses LoopPredicationPass::run(Loop &L, LoopAnalysisManager &AM,
       AM.getResult<FunctionAnalysisManagerLoopProxy>(L, AR).getManager();
   Function *F = L.getHeader()->getParent();
   auto *BPI = FAM.getCachedResult<BranchProbabilityAnalysis>(*F);
-  LoopPredication LP(&AR.AA, &AR.SE, BPI);
+  LoopPredication LP(&AR.AA, &AR.DT, &AR.SE, &AR.LI, BPI);
   if (!LP.runOnLoop(&L))
     return PreservedAnalyses::all();
 
@@ -955,6 +962,200 @@ bool LoopPredication::isLoopProfitableToPredicate() {
   return true;
 }
 
+/// If we can (cheaply) find a widenable branch which controls entry into the
+/// loop, return it.
+static BranchInst *FindWidenableTerminatorAboveLoop(Loop *L, LoopInfo &LI) {
+  // Walk back through any unconditional executed blocks and see if we can find
+  // a widenable condition which seems to control execution of this loop.  Note
+  // that we predict that maythrow calls are likely untaken and thus that it's
+  // profitable to widen a branch before a maythrow call with a condition
+  // afterwards even though that may cause the slow path to run in a case where
+  // it wouldn't have otherwise.
+  BasicBlock *BB = L->getLoopPreheader();
+  if (!BB)
+    return nullptr;
+  do {
+    if (BasicBlock *Pred = BB->getSinglePredecessor())
+      if (BB == Pred->getSingleSuccessor()) {
+        BB = Pred;
+        continue;
+      }
+    break;
+  } while (true);
+
+  if (BasicBlock *Pred = BB->getSinglePredecessor()) {
+    auto *Term = Pred->getTerminator();
+
+    Value *Cond, *WC;
+    BasicBlock *IfTrueBB, *IfFalseBB;
+    if (parseWidenableBranch(Term, Cond, WC, IfTrueBB, IfFalseBB) &&
+        IfTrueBB == BB)
+      return cast<BranchInst>(Term);
+  }
+  return nullptr;
+}
+
+/// Return the minimum of all analyzeable exit counts.  This is an upper bound
+/// on the actual exit count.  If there are not at least two analyzeable exits,
+/// returns SCEVCouldNotCompute.
+static const SCEV *getMinAnalyzeableBackedgeTakenCount(ScalarEvolution &SE,
+                                                       DominatorTree &DT,
+                                                       Loop *L) {
+  SmallVector<BasicBlock *, 16> ExitingBlocks;
+  L->getExitingBlocks(ExitingBlocks);
+
+  SmallVector<const SCEV *, 4> ExitCounts;
+  for (BasicBlock *ExitingBB : ExitingBlocks) {
+    const SCEV *ExitCount = SE.getExitCount(L, ExitingBB);
+    if (isa<SCEVCouldNotCompute>(ExitCount))
+      continue;
+    assert(DT.dominates(ExitingBB, L->getLoopLatch()) &&
+           "We should only have known counts for exiting blocks that "
+           "dominate latch!");
+    ExitCounts.push_back(ExitCount);
+  }
+  if (ExitCounts.size() < 2)
+    return SE.getCouldNotCompute();
+  return SE.getUMinFromMismatchedTypes(ExitCounts);
+}
+
+/// This implements an analogous, but entirely distinct transform from the main
+/// loop predication transform.  This one is phrased in terms of using a
+/// widenable branch *outside* the loop to allow us to simplify loop exits in a
+/// following loop.  This is close in spirit to the IndVarSimplify transform
+/// of the same name, but is materially different widening loosens legality
+/// sharply.
+bool LoopPredication::predicateLoopExits(Loop *L, SCEVExpander &Rewriter) {
+  // The transformation performed here aims to widen a widenable condition
+  // above the loop such that all analyzeable exit leading to deopt are dead.
+  // It assumes that the latch is the dominant exit for profitability and that
+  // exits branching to deoptimizing blocks are rarely taken. It relies on the
+  // semantics of widenable expressions for legality. (i.e. being able to fall
+  // down the widenable path spuriously allows us to ignore exit order,
+  // unanalyzeable exits, side effects, exceptional exits, and other challenges
+  // which restrict the applicability of the non-WC based version of this
+  // transform in IndVarSimplify.)
+  //
+  // NOTE ON POISON/UNDEF - We're hoisting an expression above guards which may
+  // imply flags on the expression being hoisted and inserting new uses (flags
+  // are only correct for current uses).  The result is that we may be
+  // inserting a branch on the value which can be either poison or undef.  In
+  // this case, the branch can legally go either way; we just need to avoid
+  // introducing UB.  This is achieved through the use of the freeze
+  // instruction.  
+
+  SmallVector<BasicBlock *, 16> ExitingBlocks;
+  L->getExitingBlocks(ExitingBlocks);
+
+  if (ExitingBlocks.empty())
+    return false; // Nothing to do.
+
+  auto *Latch = L->getLoopLatch();
+  if (!Latch)
+    return false;
+
+  auto *WidenableBR = FindWidenableTerminatorAboveLoop(L, *LI);
+  if (!WidenableBR)
+    return false;
+
+  const SCEV *LatchEC = SE->getExitCount(L, Latch);
+  if (isa<SCEVCouldNotCompute>(LatchEC))
+    return false; // profitability - want hot exit in analyzeable set
+
+  // The use of umin(all analyzeable exits) instead of latch is subtle, but
+  // important for profitability.  We may have a loop which hasn't been fully
+  // canonicalized just yet.  If the exit we chose to widen is provably never
+  // taken, we want the widened form to *also* be provably never taken.  We
+  // can't guarantee this as a current unanalyzeable exit may later become
+  // analyzeable, but we can at least avoid the obvious cases.
+  const SCEV *MinEC = getMinAnalyzeableBackedgeTakenCount(*SE, *DT, L);
+  if (isa<SCEVCouldNotCompute>(MinEC) || MinEC->getType()->isPointerTy() ||
+      !SE->isLoopInvariant(MinEC, L) ||
+      !isSafeToExpandAt(MinEC, WidenableBR, *SE))
+    return false;
+
+  // Subtlety: We need to avoid inserting additional uses of the WC.  We know
+  // that it can only have one transitive use at the moment, and thus moving
+  // that use to just before the branch and inserting code before it and then
+  // modifying the operand is legal.
+  auto *IP = cast<Instruction>(WidenableBR->getCondition());
+  IP->moveBefore(WidenableBR);
+  Rewriter.setInsertPoint(IP);
+  IRBuilder<> B(IP);
+
+  bool Changed = false;
+  Value *MinECV = nullptr; // lazily generated if needed
+  for (BasicBlock *ExitingBB : ExitingBlocks) {
+    // If our exiting block exits multiple loops, we can only rewrite the
+    // innermost one.  Otherwise, we're changing how many times the innermost
+    // loop runs before it exits.
+    if (LI->getLoopFor(ExitingBB) != L)
+      continue;
+
+    // Can't rewrite non-branch yet.
+    auto *BI = dyn_cast<BranchInst>(ExitingBB->getTerminator());
+    if (!BI)
+      continue;
+
+    // If already constant, nothing to do.
+    if (isa<Constant>(BI->getCondition()))
+      continue;
+
+    const SCEV *ExitCount = SE->getExitCount(L, ExitingBB);
+    if (isa<SCEVCouldNotCompute>(ExitCount) ||
+        ExitCount->getType()->isPointerTy() ||
+        !isSafeToExpandAt(ExitCount, WidenableBR, *SE))
+      continue;
+
+    const bool ExitIfTrue = !L->contains(*succ_begin(ExitingBB));
+    BasicBlock *ExitBB = BI->getSuccessor(ExitIfTrue ? 0 : 1);
+    if (!ExitBB->getTerminatingDeoptimizeCall())
+      // Profitability: indicator of rarely/never taken exit
+      continue;
+
+    // If we found a widenable exit condition, do two things:
+    // 1) fold the widened exit test into the widenable condition
+    // 2) fold the branch to untaken - avoids infinite looping
+
+    Value *ECV = Rewriter.expandCodeFor(ExitCount);
+    if (!MinECV)
+      MinECV = Rewriter.expandCodeFor(MinEC);
+    Value *RHS = MinECV;
+    if (ECV->getType() != RHS->getType()) {
+      Type *WiderTy = SE->getWiderType(ECV->getType(), RHS->getType());
+      ECV = B.CreateZExt(ECV, WiderTy);
+      RHS = B.CreateZExt(RHS, WiderTy);
+    }
+    assert(!Latch || DT->dominates(ExitingBB, Latch));
+    Value *NewCond = B.CreateICmp(ICmpInst::ICMP_UGT, ECV, RHS);
+    // Freeze poison or undef to an arbitrary bit pattern to ensure we can
+    // branch without introducing UB.  See NOTE ON POISON/UNDEF above for
+    // context.
+    NewCond = B.CreateFreeze(NewCond);
+
+    Value *Cond, *WC;
+    BasicBlock *IfTrueBB, *IfFalseBB;
+    bool Success =
+        parseWidenableBranch(WidenableBR, Cond, WC, IfTrueBB, IfFalseBB);
+    assert(Success && "implied from above");
+    (void)Success;
+    Instruction *WCAnd = cast<Instruction>(WidenableBR->getCondition());
+    WCAnd->setOperand(0, B.CreateAnd(NewCond, Cond));
+
+    Value *OldCond = BI->getCondition();
+    BI->setCondition(ConstantInt::get(OldCond->getType(), !ExitIfTrue));
+    Changed = true;
+  }
+
+  if (Changed)
+    // We just mutated a bunch of loop exits changing there exit counts
+    // widely.  We need to force recomputation of the exit counts given these
+    // changes.  Note that all of the inserted exits are never taken, and
+    // should be removed next time the CFG is modified.
+    SE->forgetLoop(L);
+  return Changed;
+}
+
 bool LoopPredication::runOnLoop(Loop *Loop) {
   L = Loop;
 
@@ -1006,16 +1207,12 @@ bool LoopPredication::runOnLoop(Loop *Loop) {
           cast<BranchInst>(BB->getTerminator()));
   }
 
-  if (Guards.empty() && GuardsAsWidenableBranches.empty())
-    return false;
-
   SCEVExpander Expander(*SE, *DL, "loop-predication");
-
   bool Changed = false;
   for (auto *Guard : Guards)
     Changed |= widenGuardConditions(Guard, Expander);
   for (auto *Guard : GuardsAsWidenableBranches)
     Changed |= widenWidenableBranchGuardConditions(Guard, Expander);
-
+  Changed |= predicateLoopExits(L, Expander);
   return Changed;
 }

diff --git a/llvm/test/Transforms/LoopPredication/predicate-exits.ll b/llvm/test/Transforms/LoopPredication/predicate-exits.ll
new file mode 100644 (file)
index 0000000..b71ac8c
--- /dev/null
+++ b/llvm/test/Transforms/LoopPredication/predicate-exits.ll
@@ -0,0 +1,758 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -loop-predication -S | FileCheck %s
+
+declare void @prevent_merging()
+
+; Base case - with side effects in loop
+define i32 @test1(i32* %array, i32 %length, i32 %n, i1 %cond_0) {
+; CHECK-LABEL: @test1(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
+; CHECK-NEXT:    [[TMP0:%.*]] = icmp ugt i32 [[N:%.*]], 1
+; CHECK-NEXT:    [[UMAX:%.*]] = select i1 [[TMP0]], i32 [[N]], i32 1
+; CHECK-NEXT:    [[TMP1:%.*]] = add i32 [[UMAX]], -1
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp ult i32 [[LENGTH:%.*]], [[TMP1]]
+; CHECK-NEXT:    [[UMIN:%.*]] = select i1 [[TMP2]], i32 [[LENGTH]], i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]]
+; CHECK-NEXT:    [[TMP4:%.*]] = freeze i1 [[TMP3]]
+; CHECK-NEXT:    [[TMP5:%.*]] = and i1 [[TMP4]], [[COND_0:%.*]]
+; CHECK-NEXT:    [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP5]], [[WIDENABLE_COND]]
+; CHECK-NEXT:    br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
+; CHECK:       deopt:
+; CHECK-NEXT:    [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET]]
+; CHECK:       loop.preheader:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]]
+; CHECK-NEXT:    br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0
+; CHECK:       deopt2:
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET2]]
+; CHECK:       guarded:
+; CHECK-NEXT:    [[I_I64:%.*]] = zext i32 [[I]] to i64
+; CHECK-NEXT:    [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
+; CHECK-NEXT:    [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
+; CHECK-NEXT:    store i32 0, i32* [[ARRAY_I_PTR]]
+; CHECK-NEXT:    [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
+; CHECK-NEXT:    [[I_NEXT]] = add nuw i32 [[I]], 1
+; CHECK-NEXT:    [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK:       exit:
+; CHECK-NEXT:    [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ]
+; CHECK-NEXT:    ret i32 [[RESULT]]
+;
+entry:
+  %widenable_cond = call i1 @llvm.experimental.widenable.condition()
+  %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
+  br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
+
+deopt:
+  %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret
+
+loop.preheader:
+  br label %loop
+
+loop:
+  %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
+  %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
+  call void @unknown()
+  %within.bounds = icmp ult i32 %i, %length
+  br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
+
+deopt2:
+  call void @unknown()
+  %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret2
+
+guarded:
+  %i.i64 = zext i32 %i to i64
+  %array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
+  %array.i = load i32, i32* %array.i.ptr, align 4
+  store i32 0, i32* %array.i.ptr
+  %loop.acc.next = add i32 %loop.acc, %array.i
+  %i.next = add nuw i32 %i, 1
+  %continue = icmp ult i32 %i.next, %n
+  br i1 %continue, label %loop, label %exit
+
+exit:
+  %result = phi i32 [ %loop.acc.next, %guarded ]
+  ret i32 %result
+}
+
+
+
+define i32 @test_non_canonical(i32* %array, i32 %length, i1 %cond_0) {
+; CHECK-LABEL: @test_non_canonical(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
+; CHECK-NEXT:    [[TMP0:%.*]] = icmp ugt i32 [[LENGTH:%.*]], 1
+; CHECK-NEXT:    [[UMAX:%.*]] = select i1 [[TMP0]], i32 [[LENGTH]], i32 1
+; CHECK-NEXT:    [[TMP1:%.*]] = add i32 [[UMAX]], -1
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp ult i32 [[LENGTH]], [[TMP1]]
+; CHECK-NEXT:    [[UMIN:%.*]] = select i1 [[TMP2]], i32 [[LENGTH]], i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]]
+; CHECK-NEXT:    [[TMP4:%.*]] = freeze i1 [[TMP3]]
+; CHECK-NEXT:    [[TMP5:%.*]] = and i1 [[TMP4]], [[COND_0:%.*]]
+; CHECK-NEXT:    [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP5]], [[WIDENABLE_COND]]
+; CHECK-NEXT:    br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
+; CHECK:       deopt:
+; CHECK-NEXT:    [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET]]
+; CHECK:       loop.preheader:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]]
+; CHECK-NEXT:    br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0
+; CHECK:       deopt2:
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET2]]
+; CHECK:       guarded:
+; CHECK-NEXT:    [[I_I64:%.*]] = zext i32 [[I]] to i64
+; CHECK-NEXT:    [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
+; CHECK-NEXT:    [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
+; CHECK-NEXT:    store i32 0, i32* [[ARRAY_I_PTR]]
+; CHECK-NEXT:    [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
+; CHECK-NEXT:    [[I_NEXT]] = add nuw i32 [[I]], 1
+; CHECK-NEXT:    [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[LENGTH]]
+; CHECK-NEXT:    br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK:       exit:
+; CHECK-NEXT:    [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ]
+; CHECK-NEXT:    ret i32 [[RESULT]]
+;
+entry:
+  %widenable_cond = call i1 @llvm.experimental.widenable.condition()
+  %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
+  br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
+
+deopt:
+  %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret
+
+loop.preheader:
+  br label %loop
+
+loop:
+  %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
+  %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
+  call void @unknown()
+  %within.bounds = icmp ult i32 %i, %length
+  br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
+
+deopt2:
+  call void @unknown()
+  %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret2
+
+guarded:
+  %i.i64 = zext i32 %i to i64
+  %array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
+  %array.i = load i32, i32* %array.i.ptr, align 4
+  store i32 0, i32* %array.i.ptr
+  %loop.acc.next = add i32 %loop.acc, %array.i
+  %i.next = add nuw i32 %i, 1
+  %continue = icmp ult i32 %i.next, %length
+  br i1 %continue, label %loop, label %exit
+
+exit:
+  %result = phi i32 [ %loop.acc.next, %guarded ]
+  ret i32 %result
+}
+
+
+define i32 @test_two_range_checks(i32* %array, i32 %length.1, i32 %length.2, i32 %n, i1 %cond_0) {
+; CHECK-LABEL: @test_two_range_checks(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
+; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult i32 [[LENGTH_2:%.*]], [[LENGTH_1:%.*]]
+; CHECK-NEXT:    [[UMIN:%.*]] = select i1 [[TMP0]], i32 [[LENGTH_2]], i32 [[LENGTH_1]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ugt i32 [[N:%.*]], 1
+; CHECK-NEXT:    [[UMAX:%.*]] = select i1 [[TMP1]], i32 [[N]], i32 1
+; CHECK-NEXT:    [[TMP2:%.*]] = add i32 [[UMAX]], -1
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i32 [[UMIN]], [[TMP2]]
+; CHECK-NEXT:    [[UMIN1:%.*]] = select i1 [[TMP3]], i32 [[UMIN]], i32 [[TMP2]]
+; CHECK-NEXT:    [[TMP4:%.*]] = icmp ugt i32 [[LENGTH_1]], [[UMIN1]]
+; CHECK-NEXT:    [[TMP5:%.*]] = freeze i1 [[TMP4]]
+; CHECK-NEXT:    [[TMP6:%.*]] = and i1 [[TMP5]], [[COND_0:%.*]]
+; CHECK-NEXT:    [[TMP7:%.*]] = icmp ugt i32 [[LENGTH_2]], [[UMIN1]]
+; CHECK-NEXT:    [[TMP8:%.*]] = freeze i1 [[TMP7]]
+; CHECK-NEXT:    [[TMP9:%.*]] = and i1 [[TMP8]], [[TMP6]]
+; CHECK-NEXT:    [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP9]], [[WIDENABLE_COND]]
+; CHECK-NEXT:    br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
+; CHECK:       deopt:
+; CHECK-NEXT:    [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET]]
+; CHECK:       loop.preheader:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED2:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED2]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH_1]]
+; CHECK-NEXT:    br i1 true, label [[GUARDED:%.*]], label [[DEOPT2:%.*]], !prof !0
+; CHECK:       deopt2:
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET2]]
+; CHECK:       guarded:
+; CHECK-NEXT:    [[WITHIN_BOUNDS2:%.*]] = icmp ult i32 [[I]], [[LENGTH_2]]
+; CHECK-NEXT:    br i1 true, label [[GUARDED2]], label [[DEOPT3:%.*]], !prof !0
+; CHECK:       deopt3:
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[DEOPTRET3:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET3]]
+; CHECK:       guarded2:
+; CHECK-NEXT:    [[I_I64:%.*]] = zext i32 [[I]] to i64
+; CHECK-NEXT:    [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
+; CHECK-NEXT:    [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
+; CHECK-NEXT:    store i32 0, i32* [[ARRAY_I_PTR]]
+; CHECK-NEXT:    [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
+; CHECK-NEXT:    [[I_NEXT]] = add nuw i32 [[I]], 1
+; CHECK-NEXT:    [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK:       exit:
+; CHECK-NEXT:    [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED2]] ]
+; CHECK-NEXT:    ret i32 [[RESULT]]
+;
+entry:
+  %widenable_cond = call i1 @llvm.experimental.widenable.condition()
+  %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
+  br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
+
+deopt:
+  %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret
+
+loop.preheader:
+  br label %loop
+
+loop:
+  %loop.acc = phi i32 [ %loop.acc.next, %guarded2 ], [ 0, %loop.preheader ]
+  %i = phi i32 [ %i.next, %guarded2 ], [ 0, %loop.preheader ]
+  call void @unknown()
+  %within.bounds = icmp ult i32 %i, %length.1
+  br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
+
+deopt2:
+  call void @unknown()
+  %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret2
+
+guarded:
+  %within.bounds2 = icmp ult i32 %i, %length.2
+  br i1 %within.bounds2, label %guarded2, label %deopt3, !prof !0
+
+deopt3:
+  call void @unknown()
+  %deoptret3 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret3
+
+guarded2:
+  %i.i64 = zext i32 %i to i64
+  %array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
+  %array.i = load i32, i32* %array.i.ptr, align 4
+  store i32 0, i32* %array.i.ptr
+  %loop.acc.next = add i32 %loop.acc, %array.i
+  %i.next = add nuw i32 %i, 1
+  %continue = icmp ult i32 %i.next, %n
+  br i1 %continue, label %loop, label %exit
+
+exit:
+  %result = phi i32 [ %loop.acc.next, %guarded2 ]
+  ret i32 %result
+}
+
+@G = external global i32
+
+define i32 @test_unanalyzeable_exit(i32* %array, i32 %length, i32 %n, i1 %cond_0) {
+; CHECK-LABEL: @test_unanalyzeable_exit(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
+; CHECK-NEXT:    [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[COND_0:%.*]], [[WIDENABLE_COND]]
+; CHECK-NEXT:    br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
+; CHECK:       deopt:
+; CHECK-NEXT:    [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET]]
+; CHECK:       loop.preheader:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED2:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED2]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[VOL:%.*]] = load volatile i32, i32* @G
+; CHECK-NEXT:    [[UNKNOWN:%.*]] = icmp eq i32 [[VOL]], 0
+; CHECK-NEXT:    br i1 [[UNKNOWN]], label [[GUARDED2]], label [[DEOPT3:%.*]], !prof !0
+; CHECK:       deopt3:
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[DEOPTRET3:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET3]]
+; CHECK:       guarded2:
+; CHECK-NEXT:    [[I_I64:%.*]] = zext i32 [[I]] to i64
+; CHECK-NEXT:    [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
+; CHECK-NEXT:    [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
+; CHECK-NEXT:    store i32 0, i32* [[ARRAY_I_PTR]]
+; CHECK-NEXT:    [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
+; CHECK-NEXT:    [[I_NEXT]] = add nuw i32 [[I]], 1
+; CHECK-NEXT:    [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N:%.*]]
+; CHECK-NEXT:    br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK:       exit:
+; CHECK-NEXT:    [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED2]] ]
+; CHECK-NEXT:    ret i32 [[RESULT]]
+;
+entry:
+  %widenable_cond = call i1 @llvm.experimental.widenable.condition()
+  %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
+  br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
+
+deopt:
+  %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret
+
+loop.preheader:
+  br label %loop
+
+loop:
+  %loop.acc = phi i32 [ %loop.acc.next, %guarded2 ], [ 0, %loop.preheader ]
+  %i = phi i32 [ %i.next, %guarded2 ], [ 0, %loop.preheader ]
+  call void @unknown()
+  %vol = load volatile i32, i32* @G
+  %unknown = icmp eq i32 %vol, 0
+  br i1 %unknown, label %guarded2, label %deopt3, !prof !0
+
+deopt3:
+  call void @unknown()
+  %deoptret3 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret3
+
+guarded2:
+  %i.i64 = zext i32 %i to i64
+  %array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
+  %array.i = load i32, i32* %array.i.ptr, align 4
+  store i32 0, i32* %array.i.ptr
+  %loop.acc.next = add i32 %loop.acc, %array.i
+  %i.next = add nuw i32 %i, 1
+  %continue = icmp ult i32 %i.next, %n
+  br i1 %continue, label %loop, label %exit
+
+exit:
+  %result = phi i32 [ %loop.acc.next, %guarded2 ]
+  ret i32 %result
+}
+
+define i32 @test_unanalyzeable_exit2(i32* %array, i32 %length, i32 %n, i1 %cond_0) {
+; CHECK-LABEL: @test_unanalyzeable_exit2(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
+; CHECK-NEXT:    [[TMP0:%.*]] = icmp ugt i32 [[N:%.*]], 1
+; CHECK-NEXT:    [[UMAX:%.*]] = select i1 [[TMP0]], i32 [[N]], i32 1
+; CHECK-NEXT:    [[TMP1:%.*]] = add i32 [[UMAX]], -1
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp ult i32 [[LENGTH:%.*]], [[TMP1]]
+; CHECK-NEXT:    [[UMIN:%.*]] = select i1 [[TMP2]], i32 [[LENGTH]], i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]]
+; CHECK-NEXT:    [[TMP4:%.*]] = freeze i1 [[TMP3]]
+; CHECK-NEXT:    [[TMP5:%.*]] = and i1 [[TMP4]], [[COND_0:%.*]]
+; CHECK-NEXT:    [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP5]], [[WIDENABLE_COND]]
+; CHECK-NEXT:    br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
+; CHECK:       deopt:
+; CHECK-NEXT:    [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET]]
+; CHECK:       loop.preheader:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED2:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED2]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]]
+; CHECK-NEXT:    br i1 true, label [[GUARDED:%.*]], label [[DEOPT2:%.*]], !prof !0
+; CHECK:       deopt2:
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET2]]
+; CHECK:       guarded:
+; CHECK-NEXT:    [[VOL:%.*]] = load volatile i32, i32* @G
+; CHECK-NEXT:    [[UNKNOWN:%.*]] = icmp eq i32 [[VOL]], 0
+; CHECK-NEXT:    br i1 [[UNKNOWN]], label [[GUARDED2]], label [[DEOPT3:%.*]], !prof !0
+; CHECK:       deopt3:
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[DEOPTRET3:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET3]]
+; CHECK:       guarded2:
+; CHECK-NEXT:    [[I_I64:%.*]] = zext i32 [[I]] to i64
+; CHECK-NEXT:    [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
+; CHECK-NEXT:    [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
+; CHECK-NEXT:    store i32 0, i32* [[ARRAY_I_PTR]]
+; CHECK-NEXT:    [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
+; CHECK-NEXT:    [[I_NEXT]] = add nuw i32 [[I]], 1
+; CHECK-NEXT:    [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK:       exit:
+; CHECK-NEXT:    [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED2]] ]
+; CHECK-NEXT:    ret i32 [[RESULT]]
+;
+entry:
+  %widenable_cond = call i1 @llvm.experimental.widenable.condition()
+  %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
+  br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
+
+deopt:
+  %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret
+
+loop.preheader:
+  br label %loop
+
+loop:
+  %loop.acc = phi i32 [ %loop.acc.next, %guarded2 ], [ 0, %loop.preheader ]
+  %i = phi i32 [ %i.next, %guarded2 ], [ 0, %loop.preheader ]
+  call void @unknown()
+  %within.bounds = icmp ult i32 %i, %length
+  br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
+
+deopt2:
+  call void @unknown()
+  %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret2
+
+guarded:
+  %vol = load volatile i32, i32* @G
+  %unknown = icmp eq i32 %vol, 0
+  br i1 %unknown, label %guarded2, label %deopt3, !prof !0
+
+deopt3:
+  call void @unknown()
+  %deoptret3 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret3
+
+guarded2:
+  %i.i64 = zext i32 %i to i64
+  %array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
+  %array.i = load i32, i32* %array.i.ptr, align 4
+  store i32 0, i32* %array.i.ptr
+  %loop.acc.next = add i32 %loop.acc, %array.i
+  %i.next = add nuw i32 %i, 1
+  %continue = icmp ult i32 %i.next, %n
+  br i1 %continue, label %loop, label %exit
+
+exit:
+  %result = phi i32 [ %loop.acc.next, %guarded2 ]
+  ret i32 %result
+}
+
+
+define i32 @test_unanalyzeable_latch(i32* %array, i32 %length, i32 %n, i1 %cond_0) {
+; CHECK-LABEL: @test_unanalyzeable_latch(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
+; CHECK-NEXT:    [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[COND_0:%.*]], [[WIDENABLE_COND]]
+; CHECK-NEXT:    br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
+; CHECK:       deopt:
+; CHECK-NEXT:    [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET]]
+; CHECK:       loop.preheader:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH:%.*]]
+; CHECK-NEXT:    br i1 [[WITHIN_BOUNDS]], label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0
+; CHECK:       deopt2:
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET2]]
+; CHECK:       guarded:
+; CHECK-NEXT:    [[I_I64:%.*]] = zext i32 [[I]] to i64
+; CHECK-NEXT:    [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
+; CHECK-NEXT:    [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
+; CHECK-NEXT:    store i32 0, i32* [[ARRAY_I_PTR]]
+; CHECK-NEXT:    [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
+; CHECK-NEXT:    [[I_NEXT]] = add nuw i32 [[I]], 1
+; CHECK-NEXT:    [[VOL:%.*]] = load volatile i32, i32* @G
+; CHECK-NEXT:    [[UNKNOWN:%.*]] = icmp eq i32 [[VOL]], 0
+; CHECK-NEXT:    br i1 [[UNKNOWN]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK:       exit:
+; CHECK-NEXT:    [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ]
+; CHECK-NEXT:    ret i32 [[RESULT]]
+;
+entry:
+  %widenable_cond = call i1 @llvm.experimental.widenable.condition()
+  %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
+  br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
+
+deopt:
+  %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret
+
+loop.preheader:
+  br label %loop
+
+loop:
+  %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
+  %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
+  call void @unknown()
+  %within.bounds = icmp ult i32 %i, %length
+  br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
+
+deopt2:
+  call void @unknown()
+  %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret2
+
+guarded:
+  %i.i64 = zext i32 %i to i64
+  %array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
+  %array.i = load i32, i32* %array.i.ptr, align 4
+  store i32 0, i32* %array.i.ptr
+  %loop.acc.next = add i32 %loop.acc, %array.i
+  %i.next = add nuw i32 %i, 1
+  %vol = load volatile i32, i32* @G
+  %unknown = icmp eq i32 %vol, 0
+  br i1 %unknown, label %loop, label %exit
+
+exit:
+  %result = phi i32 [ %loop.acc.next, %guarded ]
+  ret i32 %result
+}
+
+
+define i32 @provably_taken(i32* %array, i1 %cond_0) {
+; CHECK-LABEL: @provably_taken(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
+; CHECK-NEXT:    [[TMP0:%.*]] = freeze i1 false
+; CHECK-NEXT:    [[TMP1:%.*]] = and i1 [[TMP0]], [[COND_0:%.*]]
+; CHECK-NEXT:    [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP1]], [[WIDENABLE_COND]]
+; CHECK-NEXT:    br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
+; CHECK:       deopt:
+; CHECK-NEXT:    [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET]]
+; CHECK:       loop.preheader:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], 198
+; CHECK-NEXT:    br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0
+; CHECK:       deopt2:
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET2]]
+; CHECK:       guarded:
+; CHECK-NEXT:    [[I_I64:%.*]] = zext i32 [[I]] to i64
+; CHECK-NEXT:    [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
+; CHECK-NEXT:    [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
+; CHECK-NEXT:    store i32 0, i32* [[ARRAY_I_PTR]]
+; CHECK-NEXT:    [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
+; CHECK-NEXT:    [[I_NEXT]] = add nuw i32 [[I]], 1
+; CHECK-NEXT:    [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], 200
+; CHECK-NEXT:    br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK:       exit:
+; CHECK-NEXT:    [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ]
+; CHECK-NEXT:    ret i32 [[RESULT]]
+;
+entry:
+  %widenable_cond = call i1 @llvm.experimental.widenable.condition()
+  %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
+  br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
+
+deopt:
+  %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret
+
+loop.preheader:
+  br label %loop
+
+loop:
+  %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
+  %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
+  call void @unknown()
+  %within.bounds = icmp ult i32 %i, 198
+  br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
+
+deopt2:
+  call void @unknown()
+  %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret2
+
+guarded:
+  %i.i64 = zext i32 %i to i64
+  %array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
+  %array.i = load i32, i32* %array.i.ptr, align 4
+  store i32 0, i32* %array.i.ptr
+  %loop.acc.next = add i32 %loop.acc, %array.i
+  %i.next = add nuw i32 %i, 1
+  %continue = icmp ult i32 %i.next, 200
+  br i1 %continue, label %loop, label %exit
+
+exit:
+  %result = phi i32 [ %loop.acc.next, %guarded ]
+  ret i32 %result
+}
+
+define i32 @provably_not_taken(i32* %array, i1 %cond_0) {
+; CHECK-LABEL: @provably_not_taken(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
+; CHECK-NEXT:    [[TMP0:%.*]] = freeze i1 true
+; CHECK-NEXT:    [[TMP1:%.*]] = and i1 [[TMP0]], [[COND_0:%.*]]
+; CHECK-NEXT:    [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP1]], [[WIDENABLE_COND]]
+; CHECK-NEXT:    br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
+; CHECK:       deopt:
+; CHECK-NEXT:    [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET]]
+; CHECK:       loop.preheader:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], 205
+; CHECK-NEXT:    br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0
+; CHECK:       deopt2:
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET2]]
+; CHECK:       guarded:
+; CHECK-NEXT:    [[I_I64:%.*]] = zext i32 [[I]] to i64
+; CHECK-NEXT:    [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
+; CHECK-NEXT:    [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
+; CHECK-NEXT:    store i32 0, i32* [[ARRAY_I_PTR]]
+; CHECK-NEXT:    [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
+; CHECK-NEXT:    [[I_NEXT]] = add nuw i32 [[I]], 1
+; CHECK-NEXT:    [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], 200
+; CHECK-NEXT:    br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK:       exit:
+; CHECK-NEXT:    [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ]
+; CHECK-NEXT:    ret i32 [[RESULT]]
+;
+entry:
+  %widenable_cond = call i1 @llvm.experimental.widenable.condition()
+  %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
+  br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
+
+deopt:
+  %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret
+
+loop.preheader:
+  br label %loop
+
+loop:
+  %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
+  %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
+  call void @unknown()
+  %within.bounds = icmp ult i32 %i, 205
+  br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
+
+deopt2:
+  call void @unknown()
+  %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret2
+
+guarded:
+  %i.i64 = zext i32 %i to i64
+  %array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
+  %array.i = load i32, i32* %array.i.ptr, align 4
+  store i32 0, i32* %array.i.ptr
+  %loop.acc.next = add i32 %loop.acc, %array.i
+  %i.next = add nuw i32 %i, 1
+  %continue = icmp ult i32 %i.next, 200
+  br i1 %continue, label %loop, label %exit
+
+exit:
+  %result = phi i32 [ %loop.acc.next, %guarded ]
+  ret i32 %result
+}
+
+
+
+
+
+
+
+
+; TODO: Non-latch exits can still be predicated
+; This is currently prevented by an overly restrictive profitability check.
+define i32 @todo_unconditional_latch(i32* %array, i32 %length, i1 %cond_0) {
+; CHECK-LABEL: @todo_unconditional_latch(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
+; CHECK-NEXT:    [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[COND_0:%.*]], [[WIDENABLE_COND]]
+; CHECK-NEXT:    br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
+; CHECK:       deopt:
+; CHECK-NEXT:    [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET]]
+; CHECK:       loop.preheader:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH:%.*]]
+; CHECK-NEXT:    br i1 [[WITHIN_BOUNDS]], label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0
+; CHECK:       deopt2:
+; CHECK-NEXT:    call void @unknown()
+; CHECK-NEXT:    [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+; CHECK-NEXT:    ret i32 [[DEOPTRET2]]
+; CHECK:       guarded:
+; CHECK-NEXT:    [[I_I64:%.*]] = zext i32 [[I]] to i64
+; CHECK-NEXT:    [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
+; CHECK-NEXT:    [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
+; CHECK-NEXT:    store i32 0, i32* [[ARRAY_I_PTR]]
+; CHECK-NEXT:    [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
+; CHECK-NEXT:    [[I_NEXT]] = add nuw i32 [[I]], 1
+; CHECK-NEXT:    br label [[LOOP]]
+;
+entry:
+  %widenable_cond = call i1 @llvm.experimental.widenable.condition()
+  %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
+  br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
+
+deopt:
+  %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret
+
+loop.preheader:
+  br label %loop
+
+loop:
+  %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
+  %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
+  call void @unknown()
+  %within.bounds = icmp ult i32 %i, %length
+  br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
+
+deopt2:
+  call void @unknown()
+  %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
+  ret i32 %deoptret2
+
+guarded:
+  %i.i64 = zext i32 %i to i64
+  %array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
+  %array.i = load i32, i32* %array.i.ptr, align 4
+  store i32 0, i32* %array.i.ptr
+  %loop.acc.next = add i32 %loop.acc, %array.i
+  %i.next = add nuw i32 %i, 1
+  br label %loop
+}
+
+
+declare void @unknown()
+
+declare i1 @llvm.experimental.widenable.condition()
+declare i32 @llvm.experimental.deoptimize.i32(...)
+
+!0 = !{!"branch_weights", i32 1048576, i32 1}
+!1 = !{i32 1, i32 -2147483648}
+!2 = !{i32 0, i32 50}