Reapply r233062: "float2int": Add a new pass to demote from float to int where possible.

Now with a fix for PR23008 and extra regression test.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@233175 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/InitializePasses.h

@@ -294,6 +294,7 @@ void initializeWinEHPreparePass(PassRegistry&);
 void initializePlaceBackedgeSafepointsImplPass(PassRegistry&);
 void initializePlaceSafepointsPass(PassRegistry&);
 void initializeDwarfEHPreparePass(PassRegistry&);
+void initializeFloat2IntPass(PassRegistry&);
 }
 
 #endif

include/llvm/LinkAllPasses.h

@@ -169,6 +169,7 @@ namespace {
       (void) llvm::createRewriteSymbolsPass();
       (void) llvm::createStraightLineStrengthReducePass();
       (void) llvm::createMemDerefPrinter();
+      (void) llvm::createFloat2IntPass();
 
       (void)new llvm::IntervalPartition();
       (void)new llvm::ScalarEvolution();

include/llvm/Transforms/Scalar.h

@@ -429,7 +429,6 @@ BasicBlockPass *createLoadCombinePass();
 
 FunctionPass *createStraightLineStrengthReducePass();
 
-
 //===----------------------------------------------------------------------===//
 //
 // PlaceSafepoints - Rewrite any IR calls to gc.statepoints and insert any
@@ -447,6 +446,12 @@ ModulePass *createPlaceSafepointsPass();
 //
 FunctionPass *createRewriteStatepointsForGCPass();
 
+//===----------------------------------------------------------------------===//
+//
+// Float2Int - Demote floats to ints where possible.
+//
+FunctionPass *createFloat2IntPass();
+
 } // End llvm namespace
 
 #endif

lib/Transforms/IPO/PassManagerBuilder.cpp

@@ -59,6 +59,10 @@ static cl::opt<bool>
 RunLoopRerolling("reroll-loops", cl::Hidden,
                  cl::desc("Run the loop rerolling pass"));
 
+static cl::opt<bool>
+RunFloat2Int("float-to-int", cl::Hidden, cl::init(true),
+             cl::desc("Run the float2int (float demotion) pass"));
+
 static cl::opt<bool> RunLoadCombine("combine-loads", cl::init(false),
                                     cl::Hidden,
                                     cl::desc("Run the load combining pass"));
@@ -307,6 +311,9 @@ void PassManagerBuilder::populateModulePassManager(
   // we must insert a no-op module pass to reset the pass manager.
   MPM.add(createBarrierNoopPass());
 
+  if (RunFloat2Int)
+    MPM.add(createFloat2IntPass());
+
   // Re-rotate loops in all our loop nests. These may have fallout out of
   // rotated form due to GVN or other transformations, and the vectorizer relies
   // on the rotated form.

lib/Transforms/Scalar/CMakeLists.txt

@@ -9,6 +9,7 @@ add_llvm_library(LLVMScalarOpts
   DeadStoreElimination.cpp
   EarlyCSE.cpp
   FlattenCFGPass.cpp
+  Float2Int.cpp
   GVN.cpp
   InductiveRangeCheckElimination.cpp
   IndVarSimplify.cpp

lib/Transforms/Scalar/Float2Int.cpp

@@ -0,0 +1,537 @@
+//===- Float2Int.cpp - Demote floating point ops to work on integers ------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the Float2Int pass, which aims to demote floating
+// point operations to work on integers, where that is losslessly possible.
+//
+//===----------------------------------------------------------------------===//
+
+#define DEBUG_TYPE "float2int"
+#include "llvm/ADT/APInt.h"
+#include "llvm/ADT/APSInt.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/EquivalenceClasses.h"
+#include "llvm/ADT/MapVector.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/IR/ConstantRange.h"
+#include "llvm/IR/Constants.h"
+#include "llvm/IR/IRBuilder.h"
+#include "llvm/IR/InstIterator.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/IR/Module.h"
+#include "llvm/Pass.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/raw_ostream.h"
+#include "llvm/Transforms/Scalar.h"
+#include <deque>
+#include <functional> // For std::function
+using namespace llvm;
+
+// The algorithm is simple. Start at instructions that convert from the
+// float to the int domain: fptoui, fptosi and fcmp. Walk up the def-use
+// graph, using an equivalence datastructure to unify graphs that interfere.
+//
+// Mappable instructions are those with an integer corrollary that, given
+// integer domain inputs, produce an integer output; fadd, for example.
+//
+// If a non-mappable instruction is seen, this entire def-use graph is marked
+// as non-transformable. If we see an instruction that converts from the 
+// integer domain to FP domain (uitofp,sitofp), we terminate our walk.
+
+/// The largest integer type worth dealing with.
+static cl::opt<unsigned>
+MaxIntegerBW("float2int-max-integer-bw", cl::init(64), cl::Hidden,
+             cl::desc("Max integer bitwidth to consider in float2int"
+                      "(default=64)"));
+
+namespace {
+  struct Float2Int : public FunctionPass {
+    static char ID; // Pass identification, replacement for typeid
+    Float2Int() : FunctionPass(ID) {
+      initializeFloat2IntPass(*PassRegistry::getPassRegistry());
+    }
+
+    bool runOnFunction(Function &F) override;
+    void getAnalysisUsage(AnalysisUsage &AU) const override {
+      AU.setPreservesCFG();
+    }
+
+    void findRoots(Function &F, SmallPtrSet<Instruction*,8> &Roots);
+    ConstantRange seen(Instruction *I, ConstantRange R);
+    ConstantRange badRange();
+    ConstantRange unknownRange();
+    ConstantRange validateRange(ConstantRange R);
+    void walkBackwards(const SmallPtrSetImpl<Instruction*> &Roots);
+    void walkForwards();
+    bool validateAndTransform();
+    Value *convert(Instruction *I, Type *ToTy);
+    void cleanup();
+
+    MapVector<Instruction*, ConstantRange > SeenInsts;
+    SmallPtrSet<Instruction*,8> Roots;
+    EquivalenceClasses<Instruction*> ECs;
+    MapVector<Instruction*, Value*> ConvertedInsts;
+    LLVMContext *Ctx;
+  };
+}
+
+char Float2Int::ID = 0;
+INITIALIZE_PASS(Float2Int, "float2int", "Float to int", false, false)
+
+// Given a FCmp predicate, return a matching ICmp predicate if one
+// exists, otherwise return BAD_ICMP_PREDICATE.
+static CmpInst::Predicate mapFCmpPred(CmpInst::Predicate P) {
+  switch (P) {
+  case CmpInst::FCMP_OEQ:
+  case CmpInst::FCMP_UEQ:
+    return CmpInst::ICMP_EQ;
+  case CmpInst::FCMP_OGT:
+  case CmpInst::FCMP_UGT:
+    return CmpInst::ICMP_SGT;
+  case CmpInst::FCMP_OGE:
+  case CmpInst::FCMP_UGE:
+    return CmpInst::ICMP_SGE;
+  case CmpInst::FCMP_OLT:
+  case CmpInst::FCMP_ULT:
+    return CmpInst::ICMP_SLT;
+  case CmpInst::FCMP_OLE:
+  case CmpInst::FCMP_ULE:
+    return CmpInst::ICMP_SLE;
+  case CmpInst::FCMP_ONE:
+  case CmpInst::FCMP_UNE:
+    return CmpInst::ICMP_NE;
+  default:
+    return CmpInst::BAD_ICMP_PREDICATE;
+  }
+}
+
+// Given a floating point binary operator, return the matching
+// integer version.
+static Instruction::BinaryOps mapBinOpcode(unsigned Opcode) {
+  switch (Opcode) {
+  default: llvm_unreachable("Unhandled opcode!");
+  case Instruction::FAdd: return Instruction::Add;
+  case Instruction::FSub: return Instruction::Sub;
+  case Instruction::FMul: return Instruction::Mul;
+  }
+}
+
+// Find the roots - instructions that convert from the FP domain to
+// integer domain.
+void Float2Int::findRoots(Function &F, SmallPtrSet<Instruction*,8> &Roots) {
+  for (auto &I : inst_range(F)) {
+    switch (I.getOpcode()) {
+    default: break;
+    case Instruction::FPToUI:
+    case Instruction::FPToSI:
+      Roots.insert(&I);
+      break;
+    case Instruction::FCmp:
+      if (mapFCmpPred(cast<CmpInst>(&I)->getPredicate()) != 
+          CmpInst::BAD_ICMP_PREDICATE)
+        Roots.insert(&I);
+      break;
+    }
+  }
+}
+
+// Helper - mark I as having been traversed, having range R.
+ConstantRange Float2Int::seen(Instruction *I, ConstantRange R) {
+  DEBUG(dbgs() << "F2I: " << *I << ":" << R << "\n");
+  if (SeenInsts.find(I) != SeenInsts.end())
+    SeenInsts.find(I)->second = R;
+  else
+    SeenInsts.insert(std::make_pair(I, R));
+  return R;
+}
+
+// Helper - get a range representing a poison value.
+ConstantRange Float2Int::badRange() {
+  return ConstantRange(MaxIntegerBW + 1, true);
+}
+ConstantRange Float2Int::unknownRange() {
+  return ConstantRange(MaxIntegerBW + 1, false);
+}
+ConstantRange Float2Int::validateRange(ConstantRange R) {
+  if (R.getBitWidth() > MaxIntegerBW + 1)
+    return badRange();
+  return R;
+}
+
+// The most obvious way to structure the search is a depth-first, eager
+// search from each root. However, that require direct recursion and so
+// can only handle small instruction sequences. Instead, we split the search
+// up into two phases:
+//   - walkBackwards:  A breadth-first walk of the use-def graph starting from
+//                     the roots. Populate "SeenInsts" with interesting
+//                     instructions and poison values if they're obvious and
+//                     cheap to compute. Calculate the equivalance set structure
+//                     while we're here too.
+//   - walkForwards:  Iterate over SeenInsts in reverse order, so we visit
+//                     defs before their uses. Calculate the real range info.
+
+// Breadth-first walk of the use-def graph; determine the set of nodes 
+// we care about and eagerly determine if some of them are poisonous.
+void Float2Int::walkBackwards(const SmallPtrSetImpl<Instruction*> &Roots) {
+  std::deque<Instruction*> Worklist(Roots.begin(), Roots.end());
+  while (!Worklist.empty()) {
+    Instruction *I = Worklist.back();
+    Worklist.pop_back();
+
+    if (SeenInsts.find(I) != SeenInsts.end())
+      // Seen already.
+      continue;
+
+    switch (I->getOpcode()) {
+      // FIXME: Handle select and phi nodes.
+    default:
+      // Path terminated uncleanly.
+      seen(I, badRange());
+      break;
+
+    case Instruction::UIToFP: {
+      // Path terminated cleanly.
+      unsigned BW = I->getOperand(0)->getType()->getPrimitiveSizeInBits();
+      APInt Min = APInt::getMinValue(BW).zextOrSelf(MaxIntegerBW+1);
+      APInt Max = APInt::getMaxValue(BW).zextOrSelf(MaxIntegerBW+1);
+      seen(I, validateRange(ConstantRange(Min, Max)));
+      continue;
+    }
+
+    case Instruction::SIToFP: {
+      // Path terminated cleanly.
+      unsigned BW = I->getOperand(0)->getType()->getPrimitiveSizeInBits();
+      APInt SMin = APInt::getSignedMinValue(BW).sextOrSelf(MaxIntegerBW+1);
+      APInt SMax = APInt::getSignedMaxValue(BW).sextOrSelf(MaxIntegerBW+1);
+      seen(I, validateRange(ConstantRange(SMin, SMax)));
+      continue;
+    }
+
+    case Instruction::FAdd:
+    case Instruction::FSub:
+    case Instruction::FMul:
+    case Instruction::FPToUI:
+    case Instruction::FPToSI:
+    case Instruction::FCmp:
+      seen(I, unknownRange());
+      break;
+    }
+  
+    for (Value *O : I->operands()) {
+      if (Instruction *OI = dyn_cast<Instruction>(O)) {
+        // Unify def-use chains if they interfere.
+        ECs.unionSets(I, OI);
+	if (SeenInsts.find(I)->second != badRange())
+          Worklist.push_back(OI);
+      } else if (!isa<ConstantFP>(O)) {      
+        // Not an instruction or ConstantFP? we can't do anything.
+        seen(I, badRange());
+      }
+    }
+  }
+}
+
+// Walk forwards down the list of seen instructions, so we visit defs before
+// uses.
+void Float2Int::walkForwards() {
+  for (auto It = SeenInsts.rbegin(), E = SeenInsts.rend(); It != E; ++It) {
+    if (It->second != unknownRange())
+      continue;
+
+    Instruction *I = It->first;
+    std::function<ConstantRange(ArrayRef<ConstantRange>)> Op;
+    switch (I->getOpcode()) {
+      // FIXME: Handle select and phi nodes.
+    default:
+    case Instruction::UIToFP:
+    case Instruction::SIToFP:
+      llvm_unreachable("Should have been handled in walkForwards!");
+
+    case Instruction::FAdd:
+      Op = [](ArrayRef<ConstantRange> Ops) {
+        assert(Ops.size() == 2 && "FAdd is a binary operator!");
+        return Ops[0].add(Ops[1]);
+      };
+      break;
+
+    case Instruction::FSub:
+      Op = [](ArrayRef<ConstantRange> Ops) {
+        assert(Ops.size() == 2 && "FSub is a binary operator!");
+        return Ops[0].sub(Ops[1]);
+      };
+      break;
+
+    case Instruction::FMul:
+      Op = [](ArrayRef<ConstantRange> Ops) {
+        assert(Ops.size() == 2 && "FMul is a binary operator!");
+        return Ops[0].multiply(Ops[1]);
+      };
+      break;
+
+    //
+    // Root-only instructions - we'll only see these if they're the
+    //                          first node in a walk.
+    //
+    case Instruction::FPToUI:
+    case Instruction::FPToSI:
+      Op = [](ArrayRef<ConstantRange> Ops) {
+        assert(Ops.size() == 1 && "FPTo[US]I is a unary operator!");
+        return Ops[0];
+      };
+      break;
+
+    case Instruction::FCmp:
+      Op = [](ArrayRef<ConstantRange> Ops) {
+        assert(Ops.size() == 2 && "FCmp is a binary operator!");
+        return Ops[0].unionWith(Ops[1]);
+      };
+      break;
+    }
+
+    bool Abort = false;
+    SmallVector<ConstantRange,4> OpRanges;
+    for (Value *O : I->operands()) {
+      if (Instruction *OI = dyn_cast<Instruction>(O)) {
+        assert(SeenInsts.find(OI) != SeenInsts.end() &&
+	       "def not seen before use!");
+        OpRanges.push_back(SeenInsts.find(OI)->second);
+      } else if (ConstantFP *CF = dyn_cast<ConstantFP>(O)) {
+        // Work out if the floating point number can be losslessly represented
+        // as an integer.
+        // APFloat::convertToInteger(&Exact) purports to do what we want, but
+        // the exactness can be too precise. For example, negative zero can
+        // never be exactly converted to an integer.
+        //
+        // Instead, we ask APFloat to round itself to an integral value - this
+        // preserves sign-of-zero - then compare the result with the original.
+        //
+        APFloat F = CF->getValueAPF();
+
+        // First, weed out obviously incorrect values. Non-finite numbers
+        // can't be represented and neither can negative zero, unless 
+        // we're in fast math mode.
+        if (!F.isFinite() ||
+            (F.isZero() && F.isNegative() && isa<FPMathOperator>(I) &&
+	     !I->hasNoSignedZeros())) {
+          seen(I, badRange());
+          Abort = true;
+          break;
+        }
+
+        APFloat NewF = F;
+        auto Res = NewF.roundToIntegral(APFloat::rmNearestTiesToEven);
+        if (Res != APFloat::opOK || NewF.compare(F) != APFloat::cmpEqual) {
+          seen(I, badRange());
+          Abort = true;
+          break;
+        }
+        // OK, it's representable. Now get it.
+        APSInt Int(MaxIntegerBW+1, false);
+        bool Exact;
+        CF->getValueAPF().convertToInteger(Int,
+                                           APFloat::rmNearestTiesToEven,
+                                           &Exact);
+        OpRanges.push_back(ConstantRange(Int));
+      } else {
+        llvm_unreachable("Should have already marked this as badRange!");
+      }
+    }
+
+    // Reduce the operands' ranges to a single range and return.
+    if (!Abort)
+      seen(I, Op(OpRanges));    
+  }
+}
+
+// If there is a valid transform to be done, do it.
+bool Float2Int::validateAndTransform() {
+  bool MadeChange = false;
+
+  // Iterate over every disjoint partition of the def-use graph.
+  for (auto It = ECs.begin(), E = ECs.end(); It != E; ++It) {
+    ConstantRange R(MaxIntegerBW + 1, false);
+    bool Fail = false;
+    Type *ConvertedToTy = nullptr;
+
+    // For every member of the partition, union all the ranges together.
+    for (auto MI = ECs.member_begin(It), ME = ECs.member_end();
+         MI != ME; ++MI) {
+      Instruction *I = *MI;
+      auto SeenI = SeenInsts.find(I);
+      if (SeenI == SeenInsts.end())
+        continue;
+
+      R = R.unionWith(SeenI->second);
+      // We need to ensure I has no users that have not been seen.
+      // If it does, transformation would be illegal.
+      //
+      // Don't count the roots, as they terminate the graphs.
+      if (Roots.count(I) == 0) {
+        // Set the type of the conversion while we're here.
+        if (!ConvertedToTy)
+          ConvertedToTy = I->getType();
+        for (User *U : I->users()) {
+          Instruction *UI = dyn_cast<Instruction>(U);
+          if (!UI || SeenInsts.find(UI) == SeenInsts.end()) {
+            DEBUG(dbgs() << "F2I: Failing because of " << *U << "\n");
+            Fail = true;
+            break;
+          }
+        }
+      }
+      if (Fail)
+        break;
+    }
+
+    // If the set was empty, or we failed, or the range is poisonous,
+    // bail out.
+    if (ECs.member_begin(It) == ECs.member_end() || Fail ||
+        R.isFullSet() || R.isSignWrappedSet())
+      continue;
+    assert(ConvertedToTy && "Must have set the convertedtoty by this point!");
+    
+    // The number of bits required is the maximum of the upper and
+    // lower limits, plus one so it can be signed.
+    unsigned MinBW = std::max(R.getLower().getMinSignedBits(),
+                              R.getUpper().getMinSignedBits()) + 1;
+    DEBUG(dbgs() << "F2I: MinBitwidth=" << MinBW << ", R: " << R << "\n");
+
+    // If we've run off the realms of the exactly representable integers,
+    // the floating point result will differ from an integer approximation.
+
+    // Do we need more bits than are in the mantissa of the type we converted
+    // to? semanticsPrecision returns the number of mantissa bits plus one
+    // for the sign bit.
+    unsigned MaxRepresentableBits
+      = APFloat::semanticsPrecision(ConvertedToTy->getFltSemantics()) - 1;
+    if (MinBW > MaxRepresentableBits) {
+      DEBUG(dbgs() << "F2I: Value not guaranteed to be representable!\n");
+      continue;
+    }
+    if (MinBW > 64) {
+      DEBUG(dbgs() << "F2I: Value requires more than 64 bits to represent!\n");
+      continue;
+    }
+
+    // OK, R is known to be representable. Now pick a type for it.
+    // FIXME: Pick the smallest legal type that will fit.
+    Type *Ty = (MinBW > 32) ? Type::getInt64Ty(*Ctx) : Type::getInt32Ty(*Ctx);
+
+    for (auto MI = ECs.member_begin(It), ME = ECs.member_end();
+         MI != ME; ++MI)
+      convert(*MI, Ty);
+    MadeChange = true;
+  }
+
+  return MadeChange;
+}
+
+Value *Float2Int::convert(Instruction *I, Type *ToTy) {
+  if (ConvertedInsts.find(I) != ConvertedInsts.end())
+    // Already converted this instruction.
+    return ConvertedInsts[I];
+
+  SmallVector<Value*,4> NewOperands;
+  for (Value *V : I->operands()) {
+    // Don't recurse if we're an instruction that terminates the path.
+    if (I->getOpcode() == Instruction::UIToFP ||
+        I->getOpcode() == Instruction::SIToFP) {
+      NewOperands.push_back(V);
+    } else if (Instruction *VI = dyn_cast<Instruction>(V)) {
+      NewOperands.push_back(convert(VI, ToTy));
+    } else if (ConstantFP *CF = dyn_cast<ConstantFP>(V)) {
+      APSInt Val(ToTy->getPrimitiveSizeInBits(), true);
+      bool Exact;
+      CF->getValueAPF().convertToInteger(Val,
+                                         APFloat::rmNearestTiesToEven,
+                                         &Exact);
+      NewOperands.push_back(ConstantInt::get(ToTy, Val));
+    } else {
+      llvm_unreachable("Unhandled operand type?");
+    }
+  }
+
+  // Now create a new instruction.
+  IRBuilder<> IRB(I);
+  Value *NewV = nullptr;
+  switch (I->getOpcode()) {
+  default: llvm_unreachable("Unhandled instruction!");
+
+  case Instruction::FPToUI:
+    NewV = IRB.CreateZExtOrTrunc(NewOperands[0], I->getType());
+    break;
+
+  case Instruction::FPToSI:
+    NewV = IRB.CreateSExtOrTrunc(NewOperands[0], I->getType());
+    break;
+
+  case Instruction::FCmp: {
+    CmpInst::Predicate P = mapFCmpPred(cast<CmpInst>(I)->getPredicate());
+    assert(P != CmpInst::BAD_ICMP_PREDICATE && "Unhandled predicate!");
+    NewV = IRB.CreateICmp(P, NewOperands[0], NewOperands[1], I->getName());
+    break;
+  }
+
+  case Instruction::UIToFP:
+    NewV = IRB.CreateZExtOrTrunc(NewOperands[0], ToTy);
+    break;
+
+  case Instruction::SIToFP:
+    NewV = IRB.CreateSExtOrTrunc(NewOperands[0], ToTy);
+    break;
+
+  case Instruction::FAdd:
+  case Instruction::FSub:
+  case Instruction::FMul:
+    NewV = IRB.CreateBinOp(mapBinOpcode(I->getOpcode()),
+                           NewOperands[0], NewOperands[1],
+                           I->getName());
+    break;
+  }
+
+  // If we're a root instruction, RAUW.
+  if (Roots.count(I))
+    I->replaceAllUsesWith(NewV);
+
+  ConvertedInsts[I] = NewV;
+  return NewV;
+}
+
+// Perform dead code elimination on the instructions we just modified.
+void Float2Int::cleanup() {
+  for (auto I = ConvertedInsts.rbegin(), E = ConvertedInsts.rend();
+       I != E; ++I)
+    I->first->eraseFromParent();
+}
+
+bool Float2Int::runOnFunction(Function &F) {
+  DEBUG(dbgs() << "F2I: Looking at function " << F.getName() << "\n");
+  // Clear out all state.
+  ECs = EquivalenceClasses<Instruction*>();
+  SeenInsts.clear();
+  ConvertedInsts.clear();
+  Roots.clear();
+
+  Ctx = &F.getParent()->getContext();
+
+  findRoots(F, Roots);
+
+  walkBackwards(Roots);
+  walkForwards();
+
+  bool Modified = validateAndTransform();
+  if (Modified)
+    cleanup();
+  return Modified;
+}
+
+FunctionPass *llvm::createFloat2IntPass() {
+  return new Float2Int();
+}
+

lib/Transforms/Scalar/Scalar.cpp

@@ -77,6 +77,7 @@ void llvm::initializeScalarOpts(PassRegistry &Registry) {
   initializeLoadCombinePass(Registry);
   initializePlaceBackedgeSafepointsImplPass(Registry);
   initializePlaceSafepointsPass(Registry);
+  initializeFloat2IntPass(Registry);
 }
 
 void LLVMInitializeScalarOpts(LLVMPassRegistryRef R) {

test/Transforms/Float2Int/basic.ll

@@ -0,0 +1,242 @@
+; RUN: opt < %s -float2int -S | FileCheck %s
+
+;
+; Positive tests
+;
+
+; CHECK-LABEL: @simple1
+; CHECK:  %1 = zext i8 %a to i32
+; CHECK:  %2 = add i32 %1, 1
+; CHECK:  %3 = trunc i32 %2 to i16
+; CHECK:  ret i16 %3
+define i16 @simple1(i8 %a) {
+  %1 = uitofp i8 %a to float
+  %2 = fadd float %1, 1.0
+  %3 = fptoui float %2 to i16
+  ret i16 %3
+}
+
+; CHECK-LABEL: @simple2
+; CHECK:  %1 = zext i8 %a to i32
+; CHECK:  %2 = sub i32 %1, 1
+; CHECK:  %3 = trunc i32 %2 to i8
+; CHECK:  ret i8 %3
+define i8 @simple2(i8 %a) {
+  %1 = uitofp i8 %a to float
+  %2 = fsub float %1, 1.0
+  %3 = fptoui float %2 to i8
+  ret i8 %3
+}
+
+; CHECK-LABEL: @simple3
+; CHECK:  %1 = zext i8 %a to i32
+; CHECK:  %2 = sub i32 %1, 1
+; CHECK:  ret i32 %2
+define i32 @simple3(i8 %a) {
+  %1 = uitofp i8 %a to float
+  %2 = fsub float %1, 1.0
+  %3 = fptoui float %2 to i32
+  ret i32 %3
+}
+
+; CHECK-LABEL: @cmp
+; CHECK:  %1 = zext i8 %a to i32
+; CHECK:  %2 = zext i8 %b to i32
+; CHECK:  %3 = icmp slt i32 %1, %2
+; CHECK:  ret i1 %3
+define i1 @cmp(i8 %a, i8 %b) {
+  %1 = uitofp i8 %a to float
+  %2 = uitofp i8 %b to float
+  %3 = fcmp ult float %1, %2
+  ret i1 %3
+}
+
+; CHECK-LABEL: @simple4
+; CHECK:  %1 = zext i32 %a to i64
+; CHECK:  %2 = add i64 %1, 1
+; CHECK:  %3 = trunc i64 %2 to i32
+; CHECK:  ret i32 %3
+define i32 @simple4(i32 %a) {
+  %1 = uitofp i32 %a to double
+  %2 = fadd double %1, 1.0
+  %3 = fptoui double %2 to i32
+  ret i32 %3
+}
+
+; CHECK-LABEL: @simple5
+; CHECK:  %1 = zext i8 %a to i32
+; CHECK:  %2 = zext i8 %b to i32
+; CHECK:  %3 = add i32 %1, 1
+; CHECK:  %4 = mul i32 %3, %2
+; CHECK:  ret i32 %4
+define i32 @simple5(i8 %a, i8 %b) {
+  %1 = uitofp i8 %a to float
+  %2 = uitofp i8 %b to float
+  %3 = fadd float %1, 1.0
+  %4 = fmul float %3, %2
+  %5 = fptoui float %4 to i32
+  ret i32 %5
+}
+
+; The two chains don't interact - failure of one shouldn't
+; cause failure of the other.
+
+; CHECK-LABEL: @multi1
+; CHECK:  %1 = zext i8 %a to i32
+; CHECK:  %2 = zext i8 %b to i32
+; CHECK:  %fc = uitofp i8 %c to float
+; CHECK:  %x1 = add i32 %1, %2
+; CHECK:  %z = fadd float %fc, %d
+; CHECK:  %w = fptoui float %z to i32
+; CHECK:  %r = add i32 %x1, %w
+; CHECK:  ret i32 %r
+define i32 @multi1(i8 %a, i8 %b, i8 %c, float %d) {
+  %fa = uitofp i8 %a to float
+  %fb = uitofp i8 %b to float
+  %fc = uitofp i8 %c to float
+  %x = fadd float %fa, %fb
+  %y = fptoui float %x to i32
+  %z = fadd float %fc, %d
+  %w = fptoui float %z to i32
+  %r = add i32 %y, %w
+  ret i32 %r
+}
+
+; CHECK-LABEL: @simple_negzero
+; CHECK:  %1 = zext i8 %a to i32
+; CHECK:  %2 = add i32 %1, 0
+; CHECK:  %3 = trunc i32 %2 to i16
+; CHECK:  ret i16 %3
+define i16 @simple_negzero(i8 %a) {
+  %1 = uitofp i8 %a to float
+  %2 = fadd fast float %1, -0.0
+  %3 = fptoui float %2 to i16
+  ret i16 %3
+}
+
+;
+; Negative tests
+;
+
+; CHECK-LABEL: @neg_multi1
+; CHECK:  %fa = uitofp i8 %a to float
+; CHECK:  %fc = uitofp i8 %c to float
+; CHECK:  %x = fadd float %fa, %fc
+; CHECK:  %y = fptoui float %x to i32
+; CHECK:  %z = fadd float %fc, %d
+; CHECK:  %w = fptoui float %z to i32
+; CHECK:  %r = add i32 %y, %w
+; CHECK:  ret i32 %r
+; The two chains intersect, which means because one fails, no
+; transform can occur.
+define i32 @neg_multi1(i8 %a, i8 %b, i8 %c, float %d) {
+  %fa = uitofp i8 %a to float
+  %fc = uitofp i8 %c to float
+  %x = fadd float %fa, %fc
+  %y = fptoui float %x to i32
+  %z = fadd float %fc, %d
+  %w = fptoui float %z to i32
+  %r = add i32 %y, %w
+  ret i32 %r
+}
+
+; CHECK-LABEL: @neg_muld
+; CHECK:  %fa = uitofp i32 %a to double
+; CHECK:  %fb = uitofp i32 %b to double
+; CHECK:  %mul = fmul double %fa, %fb
+; CHECK:  %r = fptoui double %mul to i64
+; CHECK:  ret i64 %r
+; The i32 * i32 = i64, which has 64 bits, which is greater than the 52 bits
+; that can be exactly represented in a double.
+define i64 @neg_muld(i32 %a, i32 %b) {
+  %fa = uitofp i32 %a to double
+  %fb = uitofp i32 %b to double
+  %mul = fmul double %fa, %fb
+  %r = fptoui double %mul to i64
+  ret i64 %r
+}
+
+; CHECK-LABEL: @neg_mulf
+; CHECK:  %fa = uitofp i16 %a to float
+; CHECK:  %fb = uitofp i16 %b to float
+; CHECK:  %mul = fmul float %fa, %fb
+; CHECK:  %r = fptoui float %mul to i32
+; CHECK:  ret i32 %r
+; The i16 * i16 = i32, which can't be represented in a float, but can in a
+; double. This should fail, as the written code uses floats, not doubles so
+; the original result may be inaccurate.
+define i32 @neg_mulf(i16 %a, i16 %b) {
+  %fa = uitofp i16 %a to float
+  %fb = uitofp i16 %b to float
+  %mul = fmul float %fa, %fb
+  %r = fptoui float %mul to i32
+  ret i32 %r
+}
+
+; CHECK-LABEL: @neg_cmp
+; CHECK:  %1 = uitofp i8 %a to float
+; CHECK:  %2 = uitofp i8 %b to float
+; CHECK:  %3 = fcmp false float %1, %2
+; CHECK:  ret i1 %3
+; "false" doesn't have an icmp equivalent.
+define i1 @neg_cmp(i8 %a, i8 %b) {
+  %1 = uitofp i8 %a to float
+  %2 = uitofp i8 %b to float
+  %3 = fcmp false float %1, %2
+  ret i1 %3
+}
+
+; CHECK-LABEL: @neg_div
+; CHECK:  %1 = uitofp i8 %a to float
+; CHECK:  %2 = fdiv float %1, 1.0
+; CHECK:  %3 = fptoui float %2 to i16
+; CHECK:  ret i16 %3
+; Division isn't a supported operator.
+define i16 @neg_div(i8 %a) {
+  %1 = uitofp i8 %a to float
+  %2 = fdiv float %1, 1.0
+  %3 = fptoui float %2 to i16
+  ret i16 %3
+}
+
+; CHECK-LABEL: @neg_remainder
+; CHECK:  %1 = uitofp i8 %a to float
+; CHECK:  %2 = fadd float %1, 1.2
+; CHECK:  %3 = fptoui float %2 to i16
+; CHECK:  ret i16 %3
+; 1.2 is not an integer.
+define i16 @neg_remainder(i8 %a) {
+  %1 = uitofp i8 %a to float
+  %2 = fadd float %1, 1.25
+  %3 = fptoui float %2 to i16
+  ret i16 %3
+}
+
+; CHECK-LABEL: @neg_toolarge
+; CHECK:  %1 = uitofp i80 %a to fp128
+; CHECK:  %2 = fadd fp128 %1, %1
+; CHECK:  %3 = fptoui fp128 %2 to i80
+; CHECK:  ret i80 %3
+; i80 > i64, which is the largest bitwidth handleable by default.
+define i80 @neg_toolarge(i80 %a) {
+  %1 = uitofp i80 %a to fp128
+  %2 = fadd fp128 %1, %1
+  %3 = fptoui fp128 %2 to i80
+  ret i80 %3
+}
+
+; CHECK-LABEL: @neg_calluser
+; CHECK: sitofp
+; CHECK: fcmp
+; The sequence %1..%3 cannot be converted because %4 uses %2.
+define i32 @neg_calluser(i32 %value) {
+  %1 = sitofp i32 %value to double
+  %2 = fadd double %1, 1.0
+  %3 = fcmp olt double %2, 0.000000e+00
+  %4 = tail call double @g(double %2)
+  %5 = fptosi double %4 to i32
+  %6 = zext i1 %3 to i32
+  %7 = add i32 %6, %5
+  ret i32 %7
+}
+declare double @g(double)

test/Transforms/Float2Int/toolarge.ll

@@ -0,0 +1,16 @@
+; RUN: opt < %s -float2int -float2int-max-integer-bw=256 -S | FileCheck %s
+
+; CHECK-LABEL: @neg_toolarge
+; CHECK:  %1 = uitofp i80 %a to fp128
+; CHECK:  %2 = fadd fp128 %1, %1
+; CHECK:  %3 = fptoui fp128 %2 to i80
+; CHECK:  ret i80 %3
+; fp128 has a 112-bit mantissa, which can hold an i80. But we only support
+; up to i64, so it should fail (even though the max integer bitwidth is 256).
+define i80 @neg_toolarge(i80 %a) {
+  %1 = uitofp i80 %a to fp128
+  %2 = fadd fp128 %1, %1
+  %3 = fptoui fp128 %2 to i80
+  ret i80 %3
+}
+