llvm-project/llvm/lib/IR/LLVMContextImpl.h

395 lines
13 KiB
C
Raw Normal View History

//===-- LLVMContextImpl.h - The LLVMContextImpl opaque class ----*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file declares LLVMContextImpl, the opaque implementation
// of LLVMContext.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIB_IR_LLVMCONTEXTIMPL_H
#define LLVM_LIB_IR_LLVMCONTEXTIMPL_H
#include "AttributeImpl.h"
#include "ConstantsContext.h"
#include "LeaksContext.h"
#include "llvm/ADT/APFloat.h"
#include "llvm/ADT/APInt.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/DenseSet.h"
#include "llvm/ADT/FoldingSet.h"
#include "llvm/ADT/Hashing.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/StringMap.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/ValueHandle.h"
#include <vector>
namespace llvm {
class ConstantInt;
class ConstantFP;
class DiagnosticInfoOptimizationRemark;
class DiagnosticInfoOptimizationRemarkMissed;
class DiagnosticInfoOptimizationRemarkAnalysis;
class LLVMContext;
class Type;
class Value;
struct DenseMapAPIntKeyInfo {
static inline APInt getEmptyKey() {
APInt V(nullptr, 0);
V.VAL = 0;
return V;
}
static inline APInt getTombstoneKey() {
APInt V(nullptr, 0);
V.VAL = 1;
return V;
}
static unsigned getHashValue(const APInt &Key) {
return static_cast<unsigned>(hash_value(Key));
}
static bool isEqual(const APInt &LHS, const APInt &RHS) {
return LHS.getBitWidth() == RHS.getBitWidth() && LHS == RHS;
}
};
struct DenseMapAPFloatKeyInfo {
static inline APFloat getEmptyKey() { return APFloat(APFloat::Bogus, 1); }
static inline APFloat getTombstoneKey() { return APFloat(APFloat::Bogus, 2); }
static unsigned getHashValue(const APFloat &Key) {
return static_cast<unsigned>(hash_value(Key));
}
static bool isEqual(const APFloat &LHS, const APFloat &RHS) {
return LHS.bitwiseIsEqual(RHS);
}
};
struct AnonStructTypeKeyInfo {
struct KeyTy {
ArrayRef<Type*> ETypes;
bool isPacked;
KeyTy(const ArrayRef<Type*>& E, bool P) :
ETypes(E), isPacked(P) {}
KeyTy(const StructType *ST)
: ETypes(ST->elements()), isPacked(ST->isPacked()) {}
bool operator==(const KeyTy& that) const {
if (isPacked != that.isPacked)
return false;
if (ETypes != that.ETypes)
return false;
return true;
}
bool operator!=(const KeyTy& that) const {
return !this->operator==(that);
}
};
static inline StructType* getEmptyKey() {
return DenseMapInfo<StructType*>::getEmptyKey();
}
static inline StructType* getTombstoneKey() {
return DenseMapInfo<StructType*>::getTombstoneKey();
}
static unsigned getHashValue(const KeyTy& Key) {
Rewrite LLVM's generalized support library for hashing to follow the API of the proposed standard hashing interfaces (N3333), and to use a modified and tuned version of the CityHash algorithm. Some of the highlights of this change: -- Significantly higher quality hashing algorithm with very well distributed results, and extremely few collisions. Should be close to a checksum for up to 64-bit keys. Very little clustering or clumping of hash codes, to better distribute load on probed hash tables. -- Built-in support for reserved values. -- Simplified API that composes cleanly with other C++ idioms and APIs. -- Better scaling performance as keys grow. This is the fastest algorithm I've found and measured for moderately sized keys (such as show up in some of the uniquing and folding use cases) -- Support for enabling per-execution seeds to prevent table ordering or other artifacts of hashing algorithms to impact the output of LLVM. The seeding would make each run different and highlight these problems during bootstrap. This implementation was tested extensively using the SMHasher test suite, and pased with flying colors, doing better than the original CityHash algorithm even. I've included a unittest, although it is somewhat minimal at the moment. I've also added (or refactored into the proper location) type traits necessary to implement this, and converted users of GeneralHash over. My only immediate concerns with this implementation is the performance of hashing small keys. I've already started working to improve this, and will continue to do so. Currently, the only algorithms faster produce lower quality results, but it is likely there is a better compromise than the current one. Many thanks to Jeffrey Yasskin who did most of the work on the N3333 paper, pair-programmed some of this code, and reviewed much of it. Many thanks also go to Geoff Pike Pike and Jyrki Alakuijala, the original authors of CityHash on which this is heavily based, and Austin Appleby who created MurmurHash and the SMHasher test suite. Also thanks to Nadav, Tobias, Howard, Jay, Nick, Ahmed, and Duncan for all of the review comments! If there are further comments or concerns, please let me know and I'll jump on 'em. llvm-svn: 151822
2012-03-02 02:55:25 +08:00
return hash_combine(hash_combine_range(Key.ETypes.begin(),
Key.ETypes.end()),
Key.isPacked);
}
static unsigned getHashValue(const StructType *ST) {
return getHashValue(KeyTy(ST));
}
static bool isEqual(const KeyTy& LHS, const StructType *RHS) {
if (RHS == getEmptyKey() || RHS == getTombstoneKey())
return false;
return LHS == KeyTy(RHS);
}
static bool isEqual(const StructType *LHS, const StructType *RHS) {
return LHS == RHS;
}
};
struct FunctionTypeKeyInfo {
struct KeyTy {
const Type *ReturnType;
ArrayRef<Type*> Params;
bool isVarArg;
KeyTy(const Type* R, const ArrayRef<Type*>& P, bool V) :
ReturnType(R), Params(P), isVarArg(V) {}
KeyTy(const FunctionType *FT)
: ReturnType(FT->getReturnType()), Params(FT->params()),
isVarArg(FT->isVarArg()) {}
bool operator==(const KeyTy& that) const {
if (ReturnType != that.ReturnType)
return false;
if (isVarArg != that.isVarArg)
return false;
if (Params != that.Params)
return false;
return true;
}
bool operator!=(const KeyTy& that) const {
return !this->operator==(that);
}
};
static inline FunctionType* getEmptyKey() {
return DenseMapInfo<FunctionType*>::getEmptyKey();
}
static inline FunctionType* getTombstoneKey() {
return DenseMapInfo<FunctionType*>::getTombstoneKey();
}
static unsigned getHashValue(const KeyTy& Key) {
Rewrite LLVM's generalized support library for hashing to follow the API of the proposed standard hashing interfaces (N3333), and to use a modified and tuned version of the CityHash algorithm. Some of the highlights of this change: -- Significantly higher quality hashing algorithm with very well distributed results, and extremely few collisions. Should be close to a checksum for up to 64-bit keys. Very little clustering or clumping of hash codes, to better distribute load on probed hash tables. -- Built-in support for reserved values. -- Simplified API that composes cleanly with other C++ idioms and APIs. -- Better scaling performance as keys grow. This is the fastest algorithm I've found and measured for moderately sized keys (such as show up in some of the uniquing and folding use cases) -- Support for enabling per-execution seeds to prevent table ordering or other artifacts of hashing algorithms to impact the output of LLVM. The seeding would make each run different and highlight these problems during bootstrap. This implementation was tested extensively using the SMHasher test suite, and pased with flying colors, doing better than the original CityHash algorithm even. I've included a unittest, although it is somewhat minimal at the moment. I've also added (or refactored into the proper location) type traits necessary to implement this, and converted users of GeneralHash over. My only immediate concerns with this implementation is the performance of hashing small keys. I've already started working to improve this, and will continue to do so. Currently, the only algorithms faster produce lower quality results, but it is likely there is a better compromise than the current one. Many thanks to Jeffrey Yasskin who did most of the work on the N3333 paper, pair-programmed some of this code, and reviewed much of it. Many thanks also go to Geoff Pike Pike and Jyrki Alakuijala, the original authors of CityHash on which this is heavily based, and Austin Appleby who created MurmurHash and the SMHasher test suite. Also thanks to Nadav, Tobias, Howard, Jay, Nick, Ahmed, and Duncan for all of the review comments! If there are further comments or concerns, please let me know and I'll jump on 'em. llvm-svn: 151822
2012-03-02 02:55:25 +08:00
return hash_combine(Key.ReturnType,
hash_combine_range(Key.Params.begin(),
Key.Params.end()),
Key.isVarArg);
}
static unsigned getHashValue(const FunctionType *FT) {
return getHashValue(KeyTy(FT));
}
static bool isEqual(const KeyTy& LHS, const FunctionType *RHS) {
if (RHS == getEmptyKey() || RHS == getTombstoneKey())
return false;
return LHS == KeyTy(RHS);
}
static bool isEqual(const FunctionType *LHS, const FunctionType *RHS) {
return LHS == RHS;
}
};
/// \brief DenseMapInfo for GenericMDNode.
///
/// Note that we don't need the is-function-local bit, since that's implicit in
/// the operands.
struct GenericMDNodeInfo {
struct KeyTy {
ArrayRef<Value *> Ops;
unsigned Hash;
KeyTy(ArrayRef<Value *> Ops)
: Ops(Ops), Hash(hash_combine_range(Ops.begin(), Ops.end())) {}
KeyTy(GenericMDNode *N, SmallVectorImpl<Value *> &Storage) {
Storage.resize(N->getNumOperands());
for (unsigned I = 0, E = N->getNumOperands(); I != E; ++I)
Storage[I] = N->getOperand(I);
Ops = Storage;
Hash = hash_combine_range(Ops.begin(), Ops.end());
}
bool operator==(const GenericMDNode *RHS) const {
if (RHS == getEmptyKey() || RHS == getTombstoneKey())
return false;
if (Hash != RHS->getHash() || Ops.size() != RHS->getNumOperands())
return false;
for (unsigned I = 0, E = Ops.size(); I != E; ++I)
if (Ops[I] != RHS->getOperand(I))
return false;
return true;
}
};
static inline GenericMDNode *getEmptyKey() {
return DenseMapInfo<GenericMDNode *>::getEmptyKey();
}
static inline GenericMDNode *getTombstoneKey() {
return DenseMapInfo<GenericMDNode *>::getTombstoneKey();
}
static unsigned getHashValue(const KeyTy &Key) { return Key.Hash; }
static unsigned getHashValue(const GenericMDNode *U) {
return U->getHash();
}
static bool isEqual(const KeyTy &LHS, const GenericMDNode *RHS) {
return LHS == RHS;
}
static bool isEqual(const GenericMDNode *LHS, const GenericMDNode *RHS) {
return LHS == RHS;
}
};
/// DebugRecVH - This is a CallbackVH used to keep the Scope -> index maps
/// up to date as MDNodes mutate. This class is implemented in DebugLoc.cpp.
class DebugRecVH : public CallbackVH {
/// Ctx - This is the LLVM Context being referenced.
LLVMContextImpl *Ctx;
/// Idx - The index into either ScopeRecordIdx or ScopeInlinedAtRecords that
/// this reference lives in. If this is zero, then it represents a
/// non-canonical entry that has no DenseMap value. This can happen due to
/// RAUW.
int Idx;
public:
DebugRecVH(MDNode *n, LLVMContextImpl *ctx, int idx)
: CallbackVH(n), Ctx(ctx), Idx(idx) {}
MDNode *get() const {
return cast_or_null<MDNode>(getValPtr());
}
void deleted() override;
void allUsesReplacedWith(Value *VNew) override;
};
class LLVMContextImpl {
public:
/// OwnedModules - The set of modules instantiated in this context, and which
/// will be automatically deleted if this context is deleted.
SmallPtrSet<Module*, 4> OwnedModules;
LLVMContext::InlineAsmDiagHandlerTy InlineAsmDiagHandler;
void *InlineAsmDiagContext;
LLVMContext::DiagnosticHandlerTy DiagnosticHandler;
void *DiagnosticContext;
bool RespectDiagnosticFilters;
LLVMContext::YieldCallbackTy YieldCallback;
void *YieldOpaqueHandle;
typedef DenseMap<APInt, ConstantInt *, DenseMapAPIntKeyInfo> IntMapTy;
IntMapTy IntConstants;
2014-12-06 13:57:06 +08:00
typedef DenseMap<APFloat, ConstantFP *, DenseMapAPFloatKeyInfo> FPMapTy;
FPMapTy FPConstants;
FoldingSet<AttributeImpl> AttrsSet;
FoldingSet<AttributeSetImpl> AttrsLists;
FoldingSet<AttributeSetNode> AttrsSetNodes;
StringMap<MDString> MDStringCache;
DenseSet<GenericMDNode *, GenericMDNodeInfo> MDNodeSet;
// MDNodes may be uniqued or not uniqued. When they're not uniqued, they
// aren't in the MDNodeSet, but they're still shared between objects, so no
// one object can destroy them. This set allows us to at least destroy them
// on Context destruction.
SmallPtrSet<GenericMDNode *, 1> NonUniquedMDNodes;
DenseMap<Type*, ConstantAggregateZero*> CAZConstants;
typedef ConstantUniqueMap<ConstantArray> ArrayConstantsTy;
ArrayConstantsTy ArrayConstants;
typedef ConstantUniqueMap<ConstantStruct> StructConstantsTy;
StructConstantsTy StructConstants;
typedef ConstantUniqueMap<ConstantVector> VectorConstantsTy;
VectorConstantsTy VectorConstants;
DenseMap<PointerType*, ConstantPointerNull*> CPNConstants;
DenseMap<Type*, UndefValue*> UVConstants;
StringMap<ConstantDataSequential*> CDSConstants;
DenseMap<std::pair<const Function *, const BasicBlock *>, BlockAddress *>
BlockAddresses;
ConstantUniqueMap<ConstantExpr> ExprConstants;
ConstantUniqueMap<InlineAsm> InlineAsms;
ConstantInt *TheTrueVal;
ConstantInt *TheFalseVal;
LeakDetectorImpl<Value> LLVMObjects;
// Basic type instances.
Type VoidTy, LabelTy, HalfTy, FloatTy, DoubleTy, MetadataTy;
Type X86_FP80Ty, FP128Ty, PPC_FP128Ty, X86_MMXTy;
IntegerType Int1Ty, Int8Ty, Int16Ty, Int32Ty, Int64Ty;
/// TypeAllocator - All dynamically allocated types are allocated from this.
/// They live forever until the context is torn down.
BumpPtrAllocator TypeAllocator;
DenseMap<unsigned, IntegerType*> IntegerTypes;
typedef DenseSet<FunctionType *, FunctionTypeKeyInfo> FunctionTypeSet;
FunctionTypeSet FunctionTypes;
typedef DenseSet<StructType *, AnonStructTypeKeyInfo> StructTypeSet;
StructTypeSet AnonStructTypes;
StringMap<StructType*> NamedStructTypes;
unsigned NamedStructTypesUniqueID;
DenseMap<std::pair<Type *, uint64_t>, ArrayType*> ArrayTypes;
DenseMap<std::pair<Type *, unsigned>, VectorType*> VectorTypes;
DenseMap<Type*, PointerType*> PointerTypes; // Pointers in AddrSpace = 0
DenseMap<std::pair<Type*, unsigned>, PointerType*> ASPointerTypes;
/// ValueHandles - This map keeps track of all of the value handles that are
/// watching a Value*. The Value::HasValueHandle bit is used to know
/// whether or not a value has an entry in this map.
typedef DenseMap<Value*, ValueHandleBase*> ValueHandlesTy;
ValueHandlesTy ValueHandles;
/// CustomMDKindNames - Map to hold the metadata string to ID mapping.
StringMap<unsigned> CustomMDKindNames;
typedef std::pair<unsigned, TrackingVH<MDNode> > MDPairTy;
typedef SmallVector<MDPairTy, 2> MDMapTy;
/// MetadataStore - Collection of per-instruction metadata used in this
/// context.
DenseMap<const Instruction *, MDMapTy> MetadataStore;
/// ScopeRecordIdx - This is the index in ScopeRecords for an MDNode scope
/// entry with no "inlined at" element.
DenseMap<MDNode*, int> ScopeRecordIdx;
/// ScopeRecords - These are the actual mdnodes (in a value handle) for an
/// index. The ValueHandle ensures that ScopeRecordIdx stays up to date if
/// the MDNode is RAUW'd.
std::vector<DebugRecVH> ScopeRecords;
/// ScopeInlinedAtIdx - This is the index in ScopeInlinedAtRecords for an
/// scope/inlined-at pair.
DenseMap<std::pair<MDNode*, MDNode*>, int> ScopeInlinedAtIdx;
/// ScopeInlinedAtRecords - These are the actual mdnodes (in value handles)
/// for an index. The ValueHandle ensures that ScopeINlinedAtIdx stays up
/// to date.
std::vector<std::pair<DebugRecVH, DebugRecVH> > ScopeInlinedAtRecords;
/// DiscriminatorTable - This table maps file:line locations to an
/// integer representing the next DWARF path discriminator to assign to
/// instructions in different blocks at the same location.
DenseMap<std::pair<const char *, unsigned>, unsigned> DiscriminatorTable;
/// IntrinsicIDCache - Cache of intrinsic name (string) to numeric ID mappings
/// requested in this context
typedef DenseMap<const Function*, unsigned> IntrinsicIDCacheTy;
IntrinsicIDCacheTy IntrinsicIDCache;
/// \brief Mapping from a function to its prefix data, which is stored as the
/// operand of an unparented ReturnInst so that the prefix data has a Use.
typedef DenseMap<const Function *, ReturnInst *> PrefixDataMapTy;
PrefixDataMapTy PrefixDataMap;
Prologue support Patch by Ben Gamari! This redefines the `prefix` attribute introduced previously and introduces a `prologue` attribute. There are a two primary usecases that these attributes aim to serve, 1. Function prologue sigils 2. Function hot-patching: Enable the user to insert `nop` operations at the beginning of the function which can later be safely replaced with a call to some instrumentation facility 3. Runtime metadata: Allow a compiler to insert data for use by the runtime during execution. GHC is one example of a compiler that needs this functionality for its tables-next-to-code functionality. Previously `prefix` served cases (1) and (2) quite well by allowing the user to introduce arbitrary data at the entrypoint but before the function body. Case (3), however, was poorly handled by this approach as it required that prefix data was valid executable code. Here we redefine the notion of prefix data to instead be data which occurs immediately before the function entrypoint (i.e. the symbol address). Since prefix data now occurs before the function entrypoint, there is no need for the data to be valid code. The previous notion of prefix data now goes under the name "prologue data" to emphasize its duality with the function epilogue. The intention here is to handle cases (1) and (2) with prologue data and case (3) with prefix data. References ---------- This idea arose out of discussions[1] with Reid Kleckner in response to a proposal to introduce the notion of symbol offsets to enable handling of case (3). [1] http://lists.cs.uiuc.edu/pipermail/llvmdev/2014-May/073235.html Test Plan: testsuite Differential Revision: http://reviews.llvm.org/D6454 llvm-svn: 223189
2014-12-03 10:08:38 +08:00
/// \brief Mapping from a function to its prologue data, which is stored as
/// the operand of an unparented ReturnInst so that the prologue data has a
/// Use.
typedef DenseMap<const Function *, ReturnInst *> PrologueDataMapTy;
PrologueDataMapTy PrologueDataMap;
int getOrAddScopeRecordIdxEntry(MDNode *N, int ExistingIdx);
int getOrAddScopeInlinedAtIdxEntry(MDNode *Scope, MDNode *IA,int ExistingIdx);
LLVMContextImpl(LLVMContext &C);
~LLVMContextImpl();
};
}
#endif