maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Revert "Add Constant Hoisting Pass" 

This reverts commit r200022 to unbreak the build bots.

llvm-svn: 200024
This commit is contained in:
Juergen Ributzka 2014-01-24 18:40:30 +00:00
parent ccc18e1330
commit 50e7e80d00
20 changed files with 40 additions and 701 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llvm/include/llvm/Analysis/TargetTransformInfo.h
View File

@ -92,7 +92,6 @@ public:
enum TargetCostConstants {
TCC_Free = 0, ///< Expected to fold away in lowering.
TCC_Basic = 1, ///< The cost of a typical 'add' instruction.
TCC_Load = 3,
TCC_Expensive = 4 ///< The cost of a 'div' instruction on x86.
};
@ -300,13 +299,6 @@ public:
/// immediate of the specified type.
virtual unsigned getIntImmCost(const APInt &Imm, Type *Ty) const;
/// \brief Return the expected cost of materialization for the given integer
/// immediate of the specified type for a given instruction. The cost can be
/// zero if the immediate can be folded into the specified instruction.
virtual unsigned getIntImmCost(unsigned Opcode, const APInt &Imm,
Type *Ty) const;
virtual unsigned getIntImmCost(Intrinsic::ID IID, const APInt &Imm,
Type *Ty) const;
/// @}
/// \name Vector Target Information

22
llvm/include/llvm/CodeGen/SelectionDAG.h
View File

@ -401,22 +401,18 @@ public:
//===--------------------------------------------------------------------===//
// Node creation methods.
//
SDValue getConstant(uint64_t Val, EVT VT, bool isTarget = false,
bool isOpaque = false);
SDValue getConstant(const APInt &Val, EVT VT, bool isTarget = false,
bool isOpaque = false);
SDValue getConstant(const ConstantInt &Val, EVT VT, bool isTarget = false,
bool isOpaque = false);
SDValue getConstant(uint64_t Val, EVT VT, bool isTarget = false);
SDValue getConstant(const APInt &Val, EVT VT, bool isTarget = false);
SDValue getConstant(const ConstantInt &Val, EVT VT, bool isTarget = false);
SDValue getIntPtrConstant(uint64_t Val, bool isTarget = false);
SDValue getTargetConstant(uint64_t Val, EVT VT, bool isOpaque = false) {
return getConstant(Val, VT, true, isOpaque);
SDValue getTargetConstant(uint64_t Val, EVT VT) {
return getConstant(Val, VT, true);
}
SDValue getTargetConstant(const APInt &Val, EVT VT, bool isOpaque = false) {
return getConstant(Val, VT, true, isOpaque);
SDValue getTargetConstant(const APInt &Val, EVT VT) {
return getConstant(Val, VT, true);
}
SDValue getTargetConstant(const ConstantInt &Val, EVT VT,
bool isOpaque = false) {
return getConstant(Val, VT, true, isOpaque);
SDValue getTargetConstant(const ConstantInt &Val, EVT VT) {
return getConstant(Val, VT, true);
}
// The forms below that take a double should only be used for simple
// constants that can be exactly represented in VT. No checks are made.

5
llvm/include/llvm/CodeGen/SelectionDAGNodes.h
View File

@ -1250,10 +1250,9 @@ public:
class ConstantSDNode : public SDNode {
const ConstantInt *Value;
friend class SelectionDAG;
ConstantSDNode(bool isTarget, bool isOpaque, const ConstantInt *val, EVT VT)
ConstantSDNode(bool isTarget, const ConstantInt *val, EVT VT)
: SDNode(isTarget ? ISD::TargetConstant : ISD::Constant,
0, DebugLoc(), getSDVTList(VT)), Value(val) {
SubclassData |= isOpaque;
}
public:
@ -1266,8 +1265,6 @@ public:
bool isNullValue() const { return Value->isNullValue(); }
bool isAllOnesValue() const { return Value->isAllOnesValue(); }
bool isOpaque() const { return SubclassData & 1; }
static bool classof(const SDNode *N) {
return N->getOpcode() == ISD::Constant ||
N->getOpcode() == ISD::TargetConstant;

1
llvm/include/llvm/InitializePasses.h
View File

@ -90,7 +90,6 @@ void initializeCFGSimplifyPassPass(PassRegistry&);
void initializeFlattenCFGPassPass(PassRegistry&);
void initializeStructurizeCFGPass(PassRegistry&);
void initializeCFGViewerPass(PassRegistry&);
void initializeConstantHoistingPass(PassRegistry&);
void initializeCodeGenPreparePass(PassRegistry&);
void initializeConstantMergePass(PassRegistry&);
void initializeConstantPropagationPass(PassRegistry&);

1
llvm/include/llvm/LinkAllPasses.h
View File

@ -129,7 +129,6 @@ namespace {
(void) llvm::createJumpThreadingPass();
(void) llvm::createUnifyFunctionExitNodesPass();
(void) llvm::createInstCountPass();
(void) llvm::createConstantHoistingPass();
(void) llvm::createCodeGenPreparePass();
(void) llvm::createEarlyCSEPass();
(void) llvm::createGVNPass();

6
llvm/include/llvm/Transforms/Scalar.h
View File

@ -310,12 +310,6 @@ FunctionPass *createMemCpyOptPass();
//
Pass *createLoopDeletionPass();
//===----------------------------------------------------------------------===//
//
// ConstantHoisting - This pass prepares a function for expensive constants.
//
FunctionPass *createConstantHoistingPass();
//===----------------------------------------------------------------------===//
//
// CodeGenPrepare - This pass prepares a function for instruction selection.

22
llvm/lib/Analysis/TargetTransformInfo.cpp
View File

@ -158,16 +158,6 @@ unsigned TargetTransformInfo::getIntImmCost(const APInt &Imm, Type *Ty) const {
return PrevTTI->getIntImmCost(Imm, Ty);
}
unsigned TargetTransformInfo::getIntImmCost(unsigned Opcode, const APInt &Imm,
Type *Ty) const {
return PrevTTI->getIntImmCost(Opcode, Imm, Ty);
}
unsigned TargetTransformInfo::getIntImmCost(Intrinsic::ID IID, const APInt &Imm,
Type *Ty) const {
return PrevTTI->getIntImmCost(IID, Imm, Ty);
}
unsigned TargetTransformInfo::getNumberOfRegisters(bool Vector) const {
return PrevTTI->getNumberOfRegisters(Vector);
}
@ -551,17 +541,7 @@ struct NoTTI LLVM_FINAL : ImmutablePass, TargetTransformInfo {
}
unsigned getIntImmCost(const APInt &Imm, Type *Ty) const LLVM_OVERRIDE {
return TCC_Basic;
}
unsigned getIntImmCost(unsigned Opcode, const APInt &Imm,
Type *Ty) const LLVM_OVERRIDE {
return TCC_Free;
}
unsigned getIntImmCost(Intrinsic::ID IID, const APInt &Imm,
Type *Ty) const LLVM_OVERRIDE {
return TCC_Free;
return 1;
}
unsigned getNumberOfRegisters(bool Vector) const LLVM_OVERRIDE {

6
llvm/lib/CodeGen/Passes.cpp
View File

@ -70,8 +70,6 @@ static cl::opt<bool> DisableMachineSink("disable-machine-sink", cl::Hidden,
cl::desc("Disable Machine Sinking"));
static cl::opt<bool> DisableLSR("disable-lsr", cl::Hidden,
cl::desc("Disable Loop Strength Reduction Pass"));
static cl::opt<bool> DisableConstantHoisting("disable-constant-hoisting",
cl::Hidden, cl::desc("Disable ConstantHoisting"));
static cl::opt<bool> DisableCGP("disable-cgp", cl::Hidden,
cl::desc("Disable Codegen Prepare"));
static cl::opt<bool> DisableCopyProp("disable-copyprop", cl::Hidden,
@ -398,10 +396,6 @@ void TargetPassConfig::addIRPasses() {
// Make sure that no unreachable blocks are instruction selected.
addPass(createUnreachableBlockEliminationPass());
// Prepare expensive constants for SelectionDAG.
if (getOptLevel() != CodeGenOpt::None && !DisableConstantHoisting)
addPass(createConstantHoistingPass());
}
/// Turn exception handling constructs into something the code generators can

9
llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -3212,14 +3212,11 @@ SDValue DAGCombiner::visitOR(SDNode *N) {
if (N1C && N0.getOpcode() == ISD::AND && N0.getNode()->hasOneUse() &&
isa<ConstantSDNode>(N0.getOperand(1))) {
ConstantSDNode *C1 = cast<ConstantSDNode>(N0.getOperand(1));
if ((C1->getAPIntValue() & N1C->getAPIntValue()) != 0) {
SDValue COR = DAG.FoldConstantArithmetic(ISD::OR, VT, N1C, C1);
if (!COR.getNode())
return SDValue();
if ((C1->getAPIntValue() & N1C->getAPIntValue()) != 0)
return DAG.getNode(ISD::AND, SDLoc(N), VT,
DAG.getNode(ISD::OR, SDLoc(N0), VT,
N0.getOperand(0), N1), COR);
}
N0.getOperand(0), N1),
DAG.FoldConstantArithmetic(ISD::OR, VT, N1C, C1));
}
// fold (or (setcc x), (setcc y)) -> (setcc (or x, y))
if (isSetCCEquivalent(N0, LL, LR, CC0) && isSetCCEquivalent(N1, RL, RR, CC1)){

41
llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
View File

@ -384,12 +384,9 @@ static void AddNodeIDCustom(FoldingSetNodeID &ID, const SDNode *N) {
llvm_unreachable("Should only be used on nodes with operands");
default: break; // Normal nodes don't need extra info.
case ISD::TargetConstant:
case ISD::Constant: {
const ConstantSDNode *C = cast<ConstantSDNode>(N);
ID.AddPointer(C->getConstantIntValue());
ID.AddBoolean(C->isOpaque());
case ISD::Constant:
ID.AddPointer(cast<ConstantSDNode>(N)->getConstantIntValue());
break;
}
case ISD::TargetConstantFP:
case ISD::ConstantFP: {
ID.AddPointer(cast<ConstantFPSDNode>(N)->getConstantFPValue());
@ -974,21 +971,19 @@ SDValue SelectionDAG::getNOT(SDLoc DL, SDValue Val, EVT VT) {
return getNode(ISD::XOR, DL, VT, Val, NegOne);
}
SDValue SelectionDAG::getConstant(uint64_t Val, EVT VT, bool isT, bool isO) {
SDValue SelectionDAG::getConstant(uint64_t Val, EVT VT, bool isT) {
EVT EltVT = VT.getScalarType();
assert((EltVT.getSizeInBits() >= 64 ||
(uint64_t)((int64_t)Val >> EltVT.getSizeInBits()) + 1 < 2) &&
"getConstant with a uint64_t value that doesn't fit in the type!");
return getConstant(APInt(EltVT.getSizeInBits(), Val), VT, isT, isO);
return getConstant(APInt(EltVT.getSizeInBits(), Val), VT, isT);
}
SDValue SelectionDAG::getConstant(const APInt &Val, EVT VT, bool isT, bool isO)
{
return getConstant(*ConstantInt::get(*Context, Val), VT, isT, isO);
SDValue SelectionDAG::getConstant(const APInt &Val, EVT VT, bool isT) {
return getConstant(*ConstantInt::get(*Context, Val), VT, isT);
}
SDValue SelectionDAG::getConstant(const ConstantInt &Val, EVT VT, bool isT,
bool isO) {
SDValue SelectionDAG::getConstant(const ConstantInt &Val, EVT VT, bool isT) {
assert(VT.isInteger() && "Cannot create FP integer constant!");
EVT EltVT = VT.getScalarType();
@ -1030,7 +1025,7 @@ SDValue SelectionDAG::getConstant(const ConstantInt &Val, EVT VT, bool isT,
for (unsigned i = 0; i < ViaVecNumElts / VT.getVectorNumElements(); ++i) {
EltParts.push_back(getConstant(NewVal.lshr(i * ViaEltSizeInBits)
.trunc(ViaEltSizeInBits),
ViaEltVT, isT, isO));
ViaEltVT, isT));
}
// EltParts is currently in little endian order. If we actually want
@ -1061,7 +1056,6 @@ SDValue SelectionDAG::getConstant(const ConstantInt &Val, EVT VT, bool isT,
FoldingSetNodeID ID;
AddNodeIDNode(ID, Opc, getVTList(EltVT), 0, 0);
ID.AddPointer(Elt);
ID.AddBoolean(isO);
void *IP = 0;
SDNode *N = NULL;
if ((N = CSEMap.FindNodeOrInsertPos(ID, IP)))
@ -1069,7 +1063,7 @@ SDValue SelectionDAG::getConstant(const ConstantInt &Val, EVT VT, bool isT,
return SDValue(N, 0);
if (!N) {
N = new (NodeAllocator) ConstantSDNode(isT, isO, Elt, EltVT);
N = new (NodeAllocator) ConstantSDNode(isT, Elt, EltVT);
CSEMap.InsertNode(N, IP);
AllNodes.push_back(N);
}
@ -2795,13 +2789,10 @@ SDValue SelectionDAG::FoldConstantArithmetic(unsigned Opcode, EVT VT,
ConstantSDNode *Scalar1 = dyn_cast<ConstantSDNode>(Cst1);
ConstantSDNode *Scalar2 = dyn_cast<ConstantSDNode>(Cst2);
if (Scalar1 && Scalar2 && (Scalar1->isOpaque() || Scalar2->isOpaque()))
return SDValue();
if (Scalar1 && Scalar2)
if (Scalar1 && Scalar2) {
// Scalar instruction.
Inputs.push_back(std::make_pair(Scalar1, Scalar2));
else {
} else {
// For vectors extract each constant element into Inputs so we can constant
// fold them individually.
BuildVectorSDNode *BV1 = dyn_cast<BuildVectorSDNode>(Cst1);
@ -2817,9 +2808,6 @@ SDValue SelectionDAG::FoldConstantArithmetic(unsigned Opcode, EVT VT,
if (!V1 || !V2) // Not a constant, bail.
return SDValue();
if (V1->isOpaque() || V2->isOpaque())
return SDValue();
// Avoid BUILD_VECTOR nodes that perform implicit truncation.
// FIXME: This is valid and could be handled by truncating the APInts.
if (V1->getValueType(0) != SVT || V2->getValueType(0) != SVT)
@ -3573,11 +3561,10 @@ static SDValue getMemsetStringVal(EVT VT, SDLoc dl, SelectionDAG &DAG,
Val |= (uint64_t)(unsigned char)Str[i] << (NumVTBytes-i-1)*8;
}
// If the "cost" of materializing the integer immediate is less than the cost
// of a load, then it is cost effective to turn the load into the immediate.
// If the "cost" of materializing the integer immediate is 1 or free, then
// it is cost effective to turn the load into the immediate.
const TargetTransformInfo *TTI = DAG.getTargetTransformInfo();
if (TTI->getIntImmCost(Val, VT.getTypeForEVT(*DAG.getContext())) <
TargetTransformInfo::TCC_Load)
if (TTI->getIntImmCost(Val, VT.getTypeForEVT(*DAG.getContext())) < 2)
return DAG.getConstant(Val, VT);
return SDValue(0, 0);
}

3
llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
View File

@ -2945,9 +2945,6 @@ void SelectionDAGBuilder::visitBitCast(const User &I) {
if (DestVT != N.getValueType())
setValue(&I, DAG.getNode(ISD::BITCAST, getCurSDLoc(),
DestVT, N)); // convert types.
else if(ConstantSDNode *C = dyn_cast<ConstantSDNode>(N))
setValue(&I, DAG.getConstant(C->getAPIntValue(), C->getValueType(0),
/*isTarget=*/false, /*isOpaque*/true));
else
setValue(&I, N); // noop cast.
}

10
llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
View File

@ -81,10 +81,7 @@ std::string SDNode::getOperationName(const SelectionDAG *G) const {
case ISD::VALUETYPE: return "ValueType";
case ISD::Register: return "Register";
case ISD::RegisterMask: return "RegisterMask";
case ISD::Constant:
if (cast<ConstantSDNode>(this)->isOpaque())
return "OpaqueConstant";
return "Constant";
case ISD::Constant: return "Constant";
case ISD::ConstantFP: return "ConstantFP";
case ISD::GlobalAddress: return "GlobalAddress";
case ISD::GlobalTLSAddress: return "GlobalTLSAddress";
@ -114,10 +111,7 @@ std::string SDNode::getOperationName(const SelectionDAG *G) const {
}
case ISD::BUILD_VECTOR: return "BUILD_VECTOR";
case ISD::TargetConstant:
if (cast<ConstantSDNode>(this)->isOpaque())
return "OpaqueTargetConstant";
return "TargetConstant";
case ISD::TargetConstant: return "TargetConstant";
case ISD::TargetConstantFP: return "TargetConstantFP";
case ISD::TargetGlobalAddress: return "TargetGlobalAddress";
case ISD::TargetGlobalTLSAddress: return "TargetGlobalTLSAddress";

18
llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
View File

@ -1470,23 +1470,17 @@ TargetLowering::SimplifySetCC(EVT VT, SDValue N0, SDValue N1,
if (Cond == ISD::SETGE || Cond == ISD::SETUGE) {
if (C1 == MinVal) return DAG.getConstant(1, VT); // X >= MIN --> true
// X >= C0 --> X > (C0-1)
APInt C = C1-1;
if (!N1C->isOpaque() || (N1C->isOpaque() && C.getBitWidth() <= 64 &&
isLegalICmpImmediate(C.getSExtValue())))
return DAG.getSetCC(dl, VT, N0,
DAG.getConstant(C, N1.getValueType()),
(Cond == ISD::SETGE) ? ISD::SETGT : ISD::SETUGT);
return DAG.getSetCC(dl, VT, N0,
DAG.getConstant(C1-1, N1.getValueType()),
(Cond == ISD::SETGE) ? ISD::SETGT : ISD::SETUGT);
}
if (Cond == ISD::SETLE || Cond == ISD::SETULE) {
if (C1 == MaxVal) return DAG.getConstant(1, VT); // X <= MAX --> true
// X <= C0 --> X < (C0+1)
APInt C = C1+1;
if (!N1C->isOpaque() || (N1C->isOpaque() && C.getBitWidth() <= 64 &&
isLegalICmpImmediate(C.getSExtValue())))
return DAG.getSetCC(dl, VT, N0,
DAG.getConstant(C, N1.getValueType()),
(Cond == ISD::SETLE) ? ISD::SETLT : ISD::SETULT);
return DAG.getSetCC(dl, VT, N0,
DAG.getConstant(C1+1, N1.getValueType()),
(Cond == ISD::SETLE) ? ISD::SETLT : ISD::SETULT);
}
if ((Cond == ISD::SETLT || Cond == ISD::SETULT) && C1 == MinVal)

95
llvm/lib/Target/X86/X86TargetTransformInfo.cpp
View File

@ -18,7 +18,6 @@
#include "X86.h"
#include "X86TargetMachine.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/Support/Debug.h"
#include "llvm/Target/CostTable.h"
#include "llvm/Target/TargetLowering.h"
@ -108,14 +107,6 @@ public:
virtual unsigned getReductionCost(unsigned Opcode, Type *Ty,
bool IsPairwiseForm) const LLVM_OVERRIDE;
virtual unsigned getIntImmCost(const APInt &Imm,
Type *Ty) const LLVM_OVERRIDE;
virtual unsigned getIntImmCost(unsigned Opcode, const APInt &Imm,
Type *Ty) const LLVM_OVERRIDE;
virtual unsigned getIntImmCost(Intrinsic::ID IID, const APInt &Imm,
Type *Ty) const LLVM_OVERRIDE;
/// @}
};
@ -703,89 +694,3 @@ unsigned X86TTI::getReductionCost(unsigned Opcode, Type *ValTy,
return TargetTransformInfo::getReductionCost(Opcode, ValTy, IsPairwise);
}
unsigned X86TTI::getIntImmCost(const APInt &Imm, Type *Ty) const {
assert(Ty->isIntegerTy());
unsigned BitSize = Ty->getPrimitiveSizeInBits();
if (BitSize == 0)
return ~0U;
if (Imm.getBitWidth() <= 64 &&
(isInt<32>(Imm.getSExtValue()) || isUInt<32>(Imm.getZExtValue())))
return TCC_Basic;
else
return 2 * TCC_Basic;
}
unsigned X86TTI::getIntImmCost(unsigned Opcode, const APInt &Imm,
Type *Ty) const {
assert(Ty->isIntegerTy());
unsigned BitSize = Ty->getPrimitiveSizeInBits();
if (BitSize == 0)
return ~0U;
switch (Opcode) {
case Instruction::Add:
case Instruction::Sub:
case Instruction::Mul:
case Instruction::UDiv:
case Instruction::SDiv:
case Instruction::URem:
case Instruction::SRem:
case Instruction::Shl:
case Instruction::LShr:
case Instruction::AShr:
case Instruction::And:
case Instruction::Or:
case Instruction::Xor:
case Instruction::ICmp:
if (Imm.getBitWidth() <= 64 && isInt<32>(Imm.getSExtValue()))
return TCC_Free;
else
return X86TTI::getIntImmCost(Imm, Ty);
case Instruction::Trunc:
case Instruction::ZExt:
case Instruction::SExt:
case Instruction::IntToPtr:
case Instruction::PtrToInt:
case Instruction::BitCast:
case Instruction::Call:
case Instruction::Select:
case Instruction::Ret:
case Instruction::Load:
case Instruction::Store:
return X86TTI::getIntImmCost(Imm, Ty);
}
return TargetTransformInfo::getIntImmCost(Opcode, Imm, Ty);
}
unsigned X86TTI::getIntImmCost(Intrinsic::ID IID, const APInt &Imm,
Type *Ty) const {
assert(Ty->isIntegerTy());
unsigned BitSize = Ty->getPrimitiveSizeInBits();
if (BitSize == 0)
return ~0U;
switch (IID) {
default: return TargetTransformInfo::getIntImmCost(IID, Imm, Ty);
case Intrinsic::sadd_with_overflow:
case Intrinsic::uadd_with_overflow:
case Intrinsic::ssub_with_overflow:
case Intrinsic::usub_with_overflow:
case Intrinsic::smul_with_overflow:
case Intrinsic::umul_with_overflow:
if (Imm.getBitWidth() <= 64 && isInt<32>(Imm.getSExtValue()))
return TCC_Free;
else
return X86TTI::getIntImmCost(Imm, Ty);
case Intrinsic::experimental_stackmap:
case Intrinsic::experimental_patchpoint_void:
case Intrinsic::experimental_patchpoint_i64:
if (Imm.getBitWidth() <= 64 && isInt<64>(Imm.getSExtValue()))
return TCC_Free;
else
return X86TTI::getIntImmCost(Imm, Ty);
}
}

1
llvm/lib/Transforms/Scalar/CMakeLists.txt
View File

@ -1,7 +1,6 @@
add_llvm_library(LLVMScalarOpts
ADCE.cpp
CodeGenPrepare.cpp
ConstantHoisting.cpp
ConstantProp.cpp
CorrelatedValuePropagation.cpp
DCE.cpp

4
llvm/lib/Transforms/Scalar/CodeGenPrepare.cpp
View File

@ -240,7 +240,7 @@ bool CodeGenPrepare::runOnFunction(Function &F) {
bool CodeGenPrepare::EliminateFallThrough(Function &F) {
bool Changed = false;
// Scan all of the blocks in the function, except for the entry block.
for (Function::iterator I = llvm::next(F.begin()), E = F.end(); I != E; ) {
for (Function::iterator I = ++F.begin(), E = F.end(); I != E; ) {
BasicBlock *BB = I++;
// If the destination block has a single pred, then this is a trivial
// edge, just collapse it.
@ -276,7 +276,7 @@ bool CodeGenPrepare::EliminateFallThrough(Function &F) {
bool CodeGenPrepare::EliminateMostlyEmptyBlocks(Function &F) {
bool MadeChange = false;
// Note that this intentionally skips the entry block.
for (Function::iterator I = llvm::next(F.begin()), E = F.end(); I != E; ) {
for (Function::iterator I = ++F.begin(), E = F.end(); I != E; ) {
BasicBlock *BB = I++;
// If this block doesn't end with an uncond branch, ignore it.

429
llvm/lib/Transforms/Scalar/ConstantHoisting.cpp
View File

@ -1,429 +0,0 @@
//===- ConstantHoisting.cpp - Prepare code for expensive constants --------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This pass identifies expensive constants to hoist and coalesces them to
// better prepare it for SelectionDAG-based code generation. This works around
// the limitations of the basic-block-at-a-time approach.
//
// First it scans all instructions for integer constants and calculates its
// cost. If the constant can be folded into the instruction (the cost is
// TCC_Free) or the cost is just a simple operation (TCC_BASIC), then we don't
// consider it expensive and leave it alone. This is the default behavior and
// the default implementation of getIntImmCost will always return TCC_Free.
//
// If the cost is more than TCC_BASIC, then the integer constant can't be folded
// into the instruction and it might be beneficial to hoist the constant.
// Similar constants are coalesced to reduce register pressure and
// materialization code.
//
// When a constant is hoisted, it is also hidden behind a bitcast to force it to
// be live-out of the basic block. Otherwise the constant would be just
// duplicated and each basic block would have its own copy in the SelectionDAG.
// The SelectionDAG recognizes such constants as opaque and doesn't perform
// certain transformations on them, which would create a new expensive constant.
//
// This optimization is only applied to integer constants in instructions and
// simple (this means not nested) constant cast experessions. For example:
// %0 = load i64* inttoptr (i64 big_constant to i64*)
//===----------------------------------------------------------------------===//
#define DEBUG_TYPE "consthoist"
#include "llvm/Transforms/Scalar.h"
#include "llvm/ADT/MapVector.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/Pass.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
using namespace llvm;
STATISTIC(NumConstantsHoisted, "Number of constants hoisted");
STATISTIC(NumConstantsRebased, "Number of constants rebased");
namespace {
typedef SmallVector<User *, 4> ConstantUseListType;
struct ConstantCandidate {
unsigned CumulativeCost;
ConstantUseListType Uses;
};
struct ConstantInfo {
ConstantInt *BaseConstant;
struct RebasedConstantInfo {
ConstantInt *OriginalConstant;
Constant *Offset;
ConstantUseListType Uses;
};
typedef SmallVector<RebasedConstantInfo, 4> RebasedConstantListType;
RebasedConstantListType RebasedConstants;
};
class ConstantHoisting : public FunctionPass {
const TargetTransformInfo *TTI;
DominatorTree *DT;
/// Keeps track of expensive constants found in the function.
typedef MapVector<ConstantInt *, ConstantCandidate> ConstantMapType;
ConstantMapType ConstantMap;
/// These are the final constants we decided to hoist.
SmallVector<ConstantInfo, 4> Constants;
public:
static char ID; // Pass identification, replacement for typeid
ConstantHoisting() : FunctionPass(ID), TTI(0) {
initializeConstantHoistingPass(*PassRegistry::getPassRegistry());
}
bool runOnFunction(Function &F);
const char *getPassName() const { return "Constant Hoisting"; }
virtual void getAnalysisUsage(AnalysisUsage &AU) const {
AU.setPreservesCFG();
AU.addRequired<DominatorTreeWrapperPass>();
AU.addRequired<TargetTransformInfo>();
}
private:
void CollectConstant(User *U, unsigned Opcode, Intrinsic::ID IID,
ConstantInt *C);
void CollectConstants(Instruction *I);
void CollectConstants(Function &F);
void FindAndMakeBaseConstant(ConstantMapType::iterator S,
ConstantMapType::iterator E);
void FindBaseConstants();
Instruction *FindConstantInsertionPoint(Function &F,
const ConstantInfo &CI) const;
void EmitBaseConstants(Function &F, User *U, Instruction *Base,
Constant *Offset, ConstantInt *OriginalConstant);
bool EmitBaseConstants(Function &F);
bool OptimizeConstants(Function &F);
};
}
char ConstantHoisting::ID = 0;
INITIALIZE_PASS_BEGIN(ConstantHoisting, "consthoist", "Constant Hoisting",
false, false)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_AG_DEPENDENCY(TargetTransformInfo)
INITIALIZE_PASS_END(ConstantHoisting, "consthoist", "Constant Hoisting",
false, false)
FunctionPass *llvm::createConstantHoistingPass() {
return new ConstantHoisting();
}
/// \brief Perform the constant hoisting optimization for the given function.
bool ConstantHoisting::runOnFunction(Function &F) {
DEBUG(dbgs() << "********** Constant Hoisting **********\n");
DEBUG(dbgs() << "********** Function: " << F.getName() << '\n');
DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
TTI = &getAnalysis<TargetTransformInfo>();
return OptimizeConstants(F);
}
void ConstantHoisting::CollectConstant(User * U, unsigned Opcode,
Intrinsic::ID IID, ConstantInt *C) {
unsigned Cost;
if (Opcode)
Cost = TTI->getIntImmCost(Opcode, C->getValue(), C->getType());
else
Cost = TTI->getIntImmCost(IID, C->getValue(), C->getType());
if (Cost > TargetTransformInfo::TCC_Basic) {
ConstantCandidate &CC = ConstantMap[C];
CC.CumulativeCost += Cost;
CC.Uses.push_back(U);
}
}
/// \brief Scan the instruction or constant expression for expensive integer
/// constants and record them in the constant map.
void ConstantHoisting::CollectConstants(Instruction *I) {
unsigned Opcode = 0;
Intrinsic::ID IID = Intrinsic::not_intrinsic;
if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(I))
IID = II->getIntrinsicID();
else
Opcode = I->getOpcode();
// Scan all operands.
for (User::op_iterator O = I->op_begin(), E = I->op_end(); O != E; ++O) {
if (ConstantInt *C = dyn_cast<ConstantInt>(O)) {
CollectConstant(I, Opcode, IID, C);
continue;
}
if (ConstantExpr *CE = dyn_cast<ConstantExpr>(O)) {
// We only handle constant cast expressions.
if (!CE->isCast())
continue;
if (ConstantInt *C = dyn_cast<ConstantInt>(CE->getOperand(0))) {
// Ignore the cast expression and use the opcode of the instruction.
CollectConstant(CE, Opcode, IID, C);
continue;
}
}
}
}
/// \brief Collect all integer constants in the function that cannot be folded
/// into an instruction itself.
void ConstantHoisting::CollectConstants(Function &F) {
for (Function::iterator BB = F.begin(), E = F.end(); BB != E; ++BB)
for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ++I)
CollectConstants(I);
}
/// \brief Compare function for sorting integer constants by type and by value
/// within a type in ConstantMaps.
static bool
ConstantMapLessThan(const std::pair<ConstantInt *, ConstantCandidate> &LHS,
const std::pair<ConstantInt *, ConstantCandidate> &RHS) {
if (LHS.first->getType() == RHS.first->getType())
return LHS.first->getValue().ult(RHS.first->getValue());
else
return LHS.first->getType()->getBitWidth() <
RHS.first->getType()->getBitWidth();
}
/// \brief Find the base constant within the given range and rebase all other
/// constants with respect to the base constant.
void ConstantHoisting::FindAndMakeBaseConstant(ConstantMapType::iterator S,
ConstantMapType::iterator E) {
ConstantMapType::iterator MaxCostItr = S;
unsigned NumUses = 0;
// Use the constant that has the maximum cost as base constant.
for (ConstantMapType::iterator I = S; I != E; ++I) {
NumUses += I->second.Uses.size();
if (I->second.CumulativeCost > MaxCostItr->second.CumulativeCost)
MaxCostItr = I;
}
// Don't hoist constants that have only one use.
if (NumUses <= 1)
return;
ConstantInfo CI;
CI.BaseConstant = MaxCostItr->first;
Type *Ty = CI.BaseConstant->getType();
// Rebase the constants with respect to the base constant.
for (ConstantMapType::iterator I = S; I != E; ++I) {
APInt Diff = I->first->getValue() - CI.BaseConstant->getValue();
ConstantInfo::RebasedConstantInfo RCI;
RCI.OriginalConstant = I->first;
RCI.Offset = ConstantInt::get(Ty, Diff);
RCI.Uses = llvm_move(I->second.Uses);
CI.RebasedConstants.push_back(RCI);
}
Constants.push_back(CI);
}
/// \brief Finds and combines constants that can be easily rematerialized with
/// an add from a common base constant.
void ConstantHoisting::FindBaseConstants() {
// Sort the constants by value and type. This invalidates the mapping.
std::sort(ConstantMap.begin(), ConstantMap.end(), ConstantMapLessThan);
// Simple linear scan through the sorted constant map for viable merge
// candidates.
ConstantMapType::iterator MinValItr = ConstantMap.begin();
for (ConstantMapType::iterator I = llvm::next(ConstantMap.begin()),
E = ConstantMap.end(); I != E; ++I) {
if (MinValItr->first->getType() == I->first->getType()) {
// Check if the constant is in range of an add with immediate.
APInt Diff = I->first->getValue() - MinValItr->first->getValue();
if ((Diff.getBitWidth() <= 64) &&
TTI->isLegalAddImmediate(Diff.getSExtValue()))
continue;
}
// We either have now a different constant type or the constant is not in
// range of an add with immediate anymore.
FindAndMakeBaseConstant(MinValItr, I);
// Start a new base constant search.
MinValItr = I;
}
// Finalize the last base constant search.
FindAndMakeBaseConstant(MinValItr, ConstantMap.end());
}
/// \brief Records the basic block of the instruction or all basic blocks of the
/// users of the constant expression.
static void CollectBasicBlocks(SmallPtrSet<BasicBlock *, 4> &BBs, User *U) {
if (Instruction *I = dyn_cast<Instruction>(U))
BBs.insert(I->getParent());
else if (ConstantExpr *CE = dyn_cast<ConstantExpr>(U))
// Find all users of this constant expression.
for (Value::use_iterator UU = CE->use_begin(), E = CE->use_end();
UU != E; ++UU)
// Only record users that are instructions. We don't want to go down a
// nested constant expression chain.
if (Instruction *I = dyn_cast<Instruction>(*UU))
BBs.insert(I->getParent());
}
/// \brief Find an insertion point that dominates all uses.
Instruction *ConstantHoisting::
FindConstantInsertionPoint(Function &F, const ConstantInfo &CI) const {
BasicBlock *Entry = &F.getEntryBlock();
// Collect all basic blocks.
SmallPtrSet<BasicBlock *, 4> BBs;
ConstantInfo::RebasedConstantListType::const_iterator RCI, RCE;
for (RCI = CI.RebasedConstants.begin(), RCE = CI.RebasedConstants.end();
RCI != RCE; ++RCI)
for (SmallVectorImpl<User *>::const_iterator U = RCI->Uses.begin(),
E = RCI->Uses.end(); U != E; ++U)
CollectBasicBlocks(BBs, *U);
if (BBs.count(Entry))
return Entry->getFirstInsertionPt();
while (BBs.size() >= 2) {
BasicBlock *BB, *BB1, *BB2;
BB1 = *BBs.begin();
BB2 = *llvm::next(BBs.begin());
BB = DT->findNearestCommonDominator(BB1, BB2);
if (BB == Entry)
return Entry->getFirstInsertionPt();
BBs.erase(BB1);
BBs.erase(BB2);
BBs.insert(BB);
}
assert((BBs.size() == 1) && "Expected only one element.");
return (*BBs.begin())->getFirstInsertionPt();
}
/// \brief Emit materialization code for all rebased constants and update their
/// users.
void ConstantHoisting::EmitBaseConstants(Function &F, User *U,
Instruction *Base, Constant *Offset,
ConstantInt *OriginalConstant) {
if (Instruction *I = dyn_cast<Instruction>(U)) {
Instruction *Mat = Base;
if (!Offset->isNullValue()) {
Mat = BinaryOperator::Create(Instruction::Add, Base, Offset,
"const_mat", I);
// Use the same debug location as the instruction we are about to update.
Mat->setDebugLoc(I->getDebugLoc());
DEBUG(dbgs() << "Materialize constant (" << *Base->getOperand(0)
<< " + " << *Offset << ") in BB "
<< I->getParent()->getName() << '\n' << *Mat << '\n');
}
DEBUG(dbgs() << "Update: " << *I << '\n');
I->replaceUsesOfWith(OriginalConstant, Mat);
DEBUG(dbgs() << "To: " << *I << '\n');
return;
}
assert(isa<ConstantExpr>(U) && "Expected a ConstantExpr.");
ConstantExpr *CE = cast<ConstantExpr>(U);
for (Value::use_iterator UU = CE->use_begin(), E = CE->use_end();
UU != E; ++UU) {
// We only handel instructions here and won't walk down a ConstantExpr chain
// to replace all ConstExpr with instructions.
if (Instruction *I = dyn_cast<Instruction>(*UU)) {
Instruction *Mat = Base;
if (!Offset->isNullValue()) {
Mat = BinaryOperator::Create(Instruction::Add, Base, Offset,
"const_mat", I);
// Use the same debug location as the instruction we are about to
// update.
Mat->setDebugLoc(I->getDebugLoc());
DEBUG(dbgs() << "Materialize constant (" << *Base->getOperand(0)
<< " + " << *Offset << ") in BB "
<< I->getParent()->getName() << '\n' << *Mat << '\n');
}
Instruction *ICE = CE->getAsInstruction();
ICE->replaceUsesOfWith(OriginalConstant, Mat);
ICE->insertBefore(I);
// Use the same debug location as the instruction we are about to update.
ICE->setDebugLoc(I->getDebugLoc());
DEBUG(dbgs() << "Create instruction: " << *ICE << '\n');
DEBUG(dbgs() << "Update: " << *I << '\n');
I->replaceUsesOfWith(CE, ICE);
DEBUG(dbgs() << "To: " << *I << '\n');
}
}
}
/// \brief Hoist and hide the base constant behind a bitcast and emit
/// materialization code for derived constants.
bool ConstantHoisting::EmitBaseConstants(Function &F) {
bool MadeChange = false;
SmallVectorImpl<ConstantInfo>::iterator CI, CE;
for (CI = Constants.begin(), CE = Constants.end(); CI != CE; ++CI) {
// Hoist and hide the base constant behind a bitcast.
Instruction *IP = FindConstantInsertionPoint(F, *CI);
IntegerType *Ty = CI->BaseConstant->getType();
Instruction *Base = new BitCastInst(CI->BaseConstant, Ty, "const", IP);
DEBUG(dbgs() << "Hoist constant (" << *CI->BaseConstant << ") to BB "
<< IP->getParent()->getName() << '\n');
NumConstantsHoisted++;
// Emit materialization code for all rebased constants.
ConstantInfo::RebasedConstantListType::iterator RCI, RCE;
for (RCI = CI->RebasedConstants.begin(), RCE = CI->RebasedConstants.end();
RCI != RCE; ++RCI) {
NumConstantsRebased++;
for (SmallVectorImpl<User *>::iterator U = RCI->Uses.begin(),
E = RCI->Uses.end(); U != E; ++U)
EmitBaseConstants(F, *U, Base, RCI->Offset, RCI->OriginalConstant);
}
// Use the same debug location as the last user of the constant.
assert(!Base->use_empty() && "The use list is empty!?");
assert(isa<Instruction>(Base->use_back()) &&
"All uses should be instructions.");
Base->setDebugLoc(cast<Instruction>(Base->use_back())->getDebugLoc());
// Correct for base constant, which we counted above too.
NumConstantsRebased--;
MadeChange = true;
}
return MadeChange;
}
/// \brief Optimize expensive integer constants in the given function.
bool ConstantHoisting::OptimizeConstants(Function &F) {
bool MadeChange = false;
// Collect all constant candidates.
CollectConstants(F);
// There are no constants to worry about.
if (ConstantMap.empty())
return MadeChange;
// Combine constants that can be easily materialized with an add from a common
// base constant.
FindBaseConstants();
// Finaly hoist the base constant and emit materializating code for dependent
// constants.
MadeChange |= EmitBaseConstants(F);
ConstantMap.clear();
Constants.clear();
return MadeChange;
}

1
llvm/lib/Transforms/Scalar/Scalar.cpp
View File

@ -30,7 +30,6 @@ void llvm::initializeScalarOpts(PassRegistry &Registry) {
initializeADCEPass(Registry);
initializeSampleProfileLoaderPass(Registry);
initializeCodeGenPreparePass(Registry);
initializeConstantHoistingPass(Registry);
initializeConstantPropagationPass(Registry);
initializeCorrelatedValuePropagationPass(Registry);
initializeDCEPass(Registry);

6
llvm/test/CodeGen/ARM/memcpy-inline.ll
View File

@ -38,8 +38,7 @@ entry:
define void @t2(i8* nocapture %C) nounwind {
entry:
; CHECK-LABEL: t2:
; CHECK: movw [[REG2:r[0-9]+]], #16716
; CHECK: movt [[REG2:r[0-9]+]], #72
; CHECK: ldr [[REG2:r[0-9]+]], [r1, #32]
; CHECK: str [[REG2]], [r0, #32]
; CHECK: vld1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1]
; CHECK: vst1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]
@ -80,8 +79,7 @@ entry:
; CHECK: strb [[REG5]], [r0, #6]
; CHECK: movw [[REG6:r[0-9]+]], #21587
; CHECK: strh [[REG6]], [r0, #4]
; CHECK: movw [[REG7:r[0-9]+]], #18500
; CHECK: movt [[REG7:r[0-9]+]], #22866
; CHECK: ldr [[REG7:r[0-9]+]],
; CHECK: str [[REG7]]
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([7 x i8]* @.str5, i64 0, i64 0), i64 7, i32 1, i1 false)
ret void

53
llvm/test/CodeGen/X86/large-constants.ll
View File

@ -1,53 +0,0 @@
; RUN: llc < %s -mtriple=x86_64-darwin -mcpu=corei7 | grep movabsq | count 2
define i64 @constant_hoisting(i64 %o0, i64 %o1, i64 %o2, i64 %o3, i64 %o4, i64 %o5) {
entry:
%l0 = and i64 %o0, -281474976710654
%c0 = icmp ne i64 %l0, 0
br i1 %c0, label %fail, label %bb1
bb1:
%l1 = and i64 %o1, -281474976710654
%c1 = icmp ne i64 %l1, 0
br i1 %c1, label %fail, label %bb2
bb2:
%l2 = and i64 %o2, -281474976710654
%c2 = icmp ne i64 %l2, 0
br i1 %c2, label %fail, label %bb3
bb3:
%l3 = and i64 %o3, -281474976710654
%c3 = icmp ne i64 %l3, 0
br i1 %c3, label %fail, label %bb4
bb4:
%l4 = and i64 %o4, -281474976710653
%c4 = icmp ne i64 %l4, 0
br i1 %c4, label %fail, label %bb5
bb5:
%l5 = and i64 %o5, -281474976710652
%c5 = icmp ne i64 %l5, 0
br i1 %c5, label %fail, label %bb6
bb6:
ret i64 %l5
fail:
ret i64 -1
}
define void @constant_expressions() {
entry:
%0 = load i64* inttoptr (i64 add (i64 51250129900, i64 0) to i64*)
%1 = load i64* inttoptr (i64 add (i64 51250129900, i64 8) to i64*)
%2 = load i64* inttoptr (i64 add (i64 51250129900, i64 16) to i64*)
%3 = load i64* inttoptr (i64 add (i64 51250129900, i64 24) to i64*)
%4 = add i64 %0, %1
%5 = add i64 %2, %3
%6 = add i64 %4, %5
store i64 %6, i64* inttoptr (i64 add (i64 51250129900, i64 0) to i64*)
ret void
}