llvm-project/llvm/lib/IR/Function.cpp

962 lines
32 KiB
C++
Raw Normal View History

//===-- Function.cpp - Implement the Global object classes ----------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
2001-06-07 04:29:01 +08:00
//
// This file implements the Function class for the IR library.
2001-06-07 04:29:01 +08:00
//
//===----------------------------------------------------------------------===//
#include "llvm/IR/Function.h"
#include "LLVMContextImpl.h"
#include "SymbolTableListTraitsImpl.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/CodeGen/ValueTypes.h"
#include "llvm/IR/CallSite.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/InstIterator.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Module.h"
#include "llvm/Support/ManagedStatic.h"
#include "llvm/Support/RWMutex.h"
#include "llvm/Support/StringPool.h"
#include "llvm/Support/Threading.h"
using namespace llvm;
// Explicit instantiations of SymbolTableListTraits since some of the methods
// are not in the public header file...
template class llvm::SymbolTableListTraits<Argument, Function>;
template class llvm::SymbolTableListTraits<BasicBlock, Function>;
2001-06-07 04:29:01 +08:00
//===----------------------------------------------------------------------===//
// Argument Implementation
//===----------------------------------------------------------------------===//
void Argument::anchor() { }
Argument::Argument(Type *Ty, const Twine &Name, Function *Par)
: Value(Ty, Value::ArgumentVal) {
Parent = nullptr;
if (Par)
Par->getArgumentList().push_back(this);
setName(Name);
}
void Argument::setParent(Function *parent) {
Parent = parent;
}
/// getArgNo - Return the index of this formal argument in its containing
/// function. For example in "void foo(int a, float b)" a is 0 and b is 1.
unsigned Argument::getArgNo() const {
const Function *F = getParent();
assert(F && "Argument is not in a function");
Function::const_arg_iterator AI = F->arg_begin();
unsigned ArgIdx = 0;
for (; &*AI != this; ++AI)
++ArgIdx;
return ArgIdx;
}
/// hasNonNullAttr - Return true if this argument has the nonnull attribute on
/// it in its containing function. Also returns true if at least one byte is
/// known to be dereferenceable and the pointer is in addrspace(0).
bool Argument::hasNonNullAttr() const {
if (!getType()->isPointerTy()) return false;
if (getParent()->getAttributes().
hasAttribute(getArgNo()+1, Attribute::NonNull))
return true;
else if (getDereferenceableBytes() > 0 &&
getType()->getPointerAddressSpace() == 0)
return true;
return false;
}
/// hasByValAttr - Return true if this argument has the byval attribute on it
/// in its containing function.
bool Argument::hasByValAttr() const {
if (!getType()->isPointerTy()) return false;
return getParent()->getAttributes().
hasAttribute(getArgNo()+1, Attribute::ByVal);
}
/// \brief Return true if this argument has the inalloca attribute on it in
/// its containing function.
bool Argument::hasInAllocaAttr() const {
if (!getType()->isPointerTy()) return false;
return getParent()->getAttributes().
hasAttribute(getArgNo()+1, Attribute::InAlloca);
}
bool Argument::hasByValOrInAllocaAttr() const {
if (!getType()->isPointerTy()) return false;
AttributeSet Attrs = getParent()->getAttributes();
return Attrs.hasAttribute(getArgNo() + 1, Attribute::ByVal) ||
Attrs.hasAttribute(getArgNo() + 1, Attribute::InAlloca);
}
unsigned Argument::getParamAlignment() const {
assert(getType()->isPointerTy() && "Only pointers have alignments");
return getParent()->getParamAlignment(getArgNo()+1);
}
uint64_t Argument::getDereferenceableBytes() const {
assert(getType()->isPointerTy() &&
"Only pointers have dereferenceable bytes");
return getParent()->getDereferenceableBytes(getArgNo()+1);
}
/// hasNestAttr - Return true if this argument has the nest attribute on
/// it in its containing function.
bool Argument::hasNestAttr() const {
if (!getType()->isPointerTy()) return false;
return getParent()->getAttributes().
hasAttribute(getArgNo()+1, Attribute::Nest);
}
/// hasNoAliasAttr - Return true if this argument has the noalias attribute on
/// it in its containing function.
bool Argument::hasNoAliasAttr() const {
if (!getType()->isPointerTy()) return false;
return getParent()->getAttributes().
hasAttribute(getArgNo()+1, Attribute::NoAlias);
}
/// hasNoCaptureAttr - Return true if this argument has the nocapture attribute
/// on it in its containing function.
bool Argument::hasNoCaptureAttr() const {
if (!getType()->isPointerTy()) return false;
return getParent()->getAttributes().
hasAttribute(getArgNo()+1, Attribute::NoCapture);
}
/// hasSRetAttr - Return true if this argument has the sret attribute on
/// it in its containing function.
bool Argument::hasStructRetAttr() const {
if (!getType()->isPointerTy()) return false;
if (this != getParent()->arg_begin())
return false; // StructRet param must be first param
return getParent()->getAttributes().
hasAttribute(1, Attribute::StructRet);
}
/// hasReturnedAttr - Return true if this argument has the returned attribute on
/// it in its containing function.
bool Argument::hasReturnedAttr() const {
return getParent()->getAttributes().
hasAttribute(getArgNo()+1, Attribute::Returned);
}
/// hasZExtAttr - Return true if this argument has the zext attribute on it in
/// its containing function.
bool Argument::hasZExtAttr() const {
return getParent()->getAttributes().
hasAttribute(getArgNo()+1, Attribute::ZExt);
}
/// hasSExtAttr Return true if this argument has the sext attribute on it in its
/// containing function.
bool Argument::hasSExtAttr() const {
return getParent()->getAttributes().
hasAttribute(getArgNo()+1, Attribute::SExt);
}
/// Return true if this argument has the readonly or readnone attribute on it
/// in its containing function.
bool Argument::onlyReadsMemory() const {
return getParent()->getAttributes().
hasAttribute(getArgNo()+1, Attribute::ReadOnly) ||
getParent()->getAttributes().
hasAttribute(getArgNo()+1, Attribute::ReadNone);
}
/// addAttr - Add attributes to an argument.
void Argument::addAttr(AttributeSet AS) {
assert(AS.getNumSlots() <= 1 &&
"Trying to add more than one attribute set to an argument!");
AttrBuilder B(AS, AS.getSlotIndex(0));
getParent()->addAttributes(getArgNo() + 1,
AttributeSet::get(Parent->getContext(),
getArgNo() + 1, B));
}
/// removeAttr - Remove attributes from an argument.
void Argument::removeAttr(AttributeSet AS) {
assert(AS.getNumSlots() <= 1 &&
"Trying to remove more than one attribute set from an argument!");
AttrBuilder B(AS, AS.getSlotIndex(0));
getParent()->removeAttributes(getArgNo() + 1,
AttributeSet::get(Parent->getContext(),
getArgNo() + 1, B));
}
//===----------------------------------------------------------------------===//
// Helper Methods in Function
//===----------------------------------------------------------------------===//
bool Function::isMaterializable() const {
return getGlobalObjectSubClassData();
}
void Function::setIsMaterializable(bool V) { setGlobalObjectSubClassData(V); }
LLVMContext &Function::getContext() const {
return getType()->getContext();
}
FunctionType *Function::getFunctionType() const {
return cast<FunctionType>(getType()->getElementType());
}
bool Function::isVarArg() const {
return getFunctionType()->isVarArg();
}
Type *Function::getReturnType() const {
return getFunctionType()->getReturnType();
}
void Function::removeFromParent() {
getParent()->getFunctionList().remove(this);
}
void Function::eraseFromParent() {
getParent()->getFunctionList().erase(this);
}
//===----------------------------------------------------------------------===//
// Function Implementation
//===----------------------------------------------------------------------===//
Function::Function(FunctionType *Ty, LinkageTypes Linkage, const Twine &name,
Module *ParentModule)
: GlobalObject(PointerType::getUnqual(Ty), Value::FunctionVal, nullptr, 0,
Linkage, name) {
assert(FunctionType::isValidReturnType(getReturnType()) &&
"invalid return type");
setIsMaterializable(false);
SymTab = new ValueSymbolTable();
// If the function has arguments, mark them as lazily built.
if (Ty->getNumParams())
setValueSubclassData(1); // Set the "has lazy arguments" bit.
if (ParentModule)
ParentModule->getFunctionList().push_back(this);
// Ensure intrinsics have the right parameter attributes.
if (unsigned IID = getIntrinsicID())
setAttributes(Intrinsic::getAttributes(getContext(), Intrinsic::ID(IID)));
2001-06-07 04:29:01 +08:00
}
Function::~Function() {
dropAllReferences(); // After this it is safe to delete instructions.
2001-06-07 04:29:01 +08:00
// Delete all of the method arguments and unlink from symbol table...
ArgumentList.clear();
delete SymTab;
// Remove the function from the on-the-side GC table.
clearGC();
// Remove the intrinsicID from the Cache.
if (getValueName() && isIntrinsic())
getContext().pImpl->IntrinsicIDCache.erase(this);
2001-06-07 04:29:01 +08:00
}
void Function::BuildLazyArguments() const {
// Create the arguments vector, all arguments start out unnamed.
FunctionType *FT = getFunctionType();
for (unsigned i = 0, e = FT->getNumParams(); i != e; ++i) {
assert(!FT->getParamType(i)->isVoidTy() &&
"Cannot have void typed arguments!");
ArgumentList.push_back(new Argument(FT->getParamType(i)));
}
// Clear the lazy arguments bit.
unsigned SDC = getSubclassDataFromValue();
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
const_cast<Function*>(this)->setValueSubclassData(SDC &= ~(1<<0));
}
size_t Function::arg_size() const {
return getFunctionType()->getNumParams();
}
bool Function::arg_empty() const {
return getFunctionType()->getNumParams() == 0;
}
void Function::setParent(Module *parent) {
2001-06-07 04:29:01 +08:00
Parent = parent;
}
// dropAllReferences() - This function causes all the subinstructions to "let
// go" of all references that they are maintaining. This allows one to
// 'delete' a whole class at a time, even though there may be circular
// references... first all references are dropped, and all use counts go to
2003-10-11 01:54:14 +08:00
// zero. Then everything is deleted for real. Note that no operations are
// valid on an object that has "dropped all references", except operator
2001-06-07 04:29:01 +08:00
// delete.
//
void Function::dropAllReferences() {
setIsMaterializable(false);
for (iterator I = begin(), E = end(); I != E; ++I)
I->dropAllReferences();
// Delete all basic blocks. They are now unused, except possibly by
// blockaddresses, but BasicBlock's destructor takes care of those.
while (!BasicBlocks.empty())
BasicBlocks.begin()->eraseFromParent();
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
// Prefix and prologue data are stored in a side table.
setPrefixData(nullptr);
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
setPrologueData(nullptr);
2001-06-07 04:29:01 +08:00
}
void Function::addAttribute(unsigned i, Attribute::AttrKind attr) {
AttributeSet PAL = getAttributes();
PAL = PAL.addAttribute(getContext(), i, attr);
setAttributes(PAL);
}
void Function::addAttributes(unsigned i, AttributeSet attrs) {
AttributeSet PAL = getAttributes();
PAL = PAL.addAttributes(getContext(), i, attrs);
setAttributes(PAL);
}
void Function::removeAttributes(unsigned i, AttributeSet attrs) {
AttributeSet PAL = getAttributes();
PAL = PAL.removeAttributes(getContext(), i, attrs);
setAttributes(PAL);
}
void Function::addDereferenceableAttr(unsigned i, uint64_t Bytes) {
AttributeSet PAL = getAttributes();
PAL = PAL.addDereferenceableAttr(getContext(), i, Bytes);
setAttributes(PAL);
}
// Maintain the GC name for each function in an on-the-side table. This saves
// allocating an additional word in Function for programs which do not use GC
// (i.e., most programs) at the cost of increased overhead for clients which do
// use GC.
static DenseMap<const Function*,PooledStringPtr> *GCNames;
static StringPool *GCNamePool;
2009-06-19 04:56:48 +08:00
static ManagedStatic<sys::SmartRWMutex<true> > GCLock;
bool Function::hasGC() const {
sys::SmartScopedReader<true> Reader(*GCLock);
2009-06-19 04:56:48 +08:00
return GCNames && GCNames->count(this);
}
const char *Function::getGC() const {
assert(hasGC() && "Function has no collector");
sys::SmartScopedReader<true> Reader(*GCLock);
2009-06-19 04:56:48 +08:00
return *(*GCNames)[this];
}
void Function::setGC(const char *Str) {
sys::SmartScopedWriter<true> Writer(*GCLock);
if (!GCNamePool)
GCNamePool = new StringPool();
if (!GCNames)
GCNames = new DenseMap<const Function*,PooledStringPtr>();
(*GCNames)[this] = GCNamePool->intern(Str);
}
void Function::clearGC() {
sys::SmartScopedWriter<true> Writer(*GCLock);
if (GCNames) {
GCNames->erase(this);
if (GCNames->empty()) {
delete GCNames;
GCNames = nullptr;
if (GCNamePool->empty()) {
delete GCNamePool;
GCNamePool = nullptr;
}
}
}
}
/// copyAttributesFrom - copy all additional attributes (those not needed to
/// create a Function) from the Function Src to this one.
void Function::copyAttributesFrom(const GlobalValue *Src) {
assert(isa<Function>(Src) && "Expected a Function!");
GlobalObject::copyAttributesFrom(Src);
const Function *SrcF = cast<Function>(Src);
setCallingConv(SrcF->getCallingConv());
setAttributes(SrcF->getAttributes());
if (SrcF->hasGC())
setGC(SrcF->getGC());
else
clearGC();
if (SrcF->hasPrefixData())
setPrefixData(SrcF->getPrefixData());
else
setPrefixData(nullptr);
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
if (SrcF->hasPrologueData())
setPrologueData(SrcF->getPrologueData());
else
setPrologueData(nullptr);
}
/// getIntrinsicID - This method returns the ID number of the specified
/// function, or Intrinsic::not_intrinsic if the function is not an
2003-10-11 01:54:14 +08:00
/// intrinsic, or if the pointer is null. This value is always defined to be
/// zero to allow easy checking for whether a function is intrinsic or not. The
/// particular intrinsic functions which correspond to this value are defined in
/// llvm/Intrinsics.h. Results are cached in the LLVM context, subsequent
/// requests for the same ID return results much faster from the cache.
///
unsigned Function::getIntrinsicID() const {
const ValueName *ValName = this->getValueName();
if (!ValName || !isIntrinsic())
return 0;
LLVMContextImpl::IntrinsicIDCacheTy &IntrinsicIDCache =
getContext().pImpl->IntrinsicIDCache;
if (!IntrinsicIDCache.count(this)) {
unsigned Id = lookupIntrinsicID();
IntrinsicIDCache[this]=Id;
return Id;
}
return IntrinsicIDCache[this];
}
/// This private method does the actual lookup of an intrinsic ID when the query
/// could not be answered from the cache.
unsigned Function::lookupIntrinsicID() const {
const ValueName *ValName = this->getValueName();
unsigned Len = ValName->getKeyLength();
const char *Name = ValName->getKeyData();
#define GET_FUNCTION_RECOGNIZER
#include "llvm/IR/Intrinsics.gen"
#undef GET_FUNCTION_RECOGNIZER
return 0;
}
/// Returns a stable mangling for the type specified for use in the name
/// mangling scheme used by 'any' types in intrinsic signatures. The mangling
/// of named types is simply their name. Manglings for unnamed types consist
/// of a prefix ('p' for pointers, 'a' for arrays, 'f_' for functions)
/// combined with the mangling of their component types. A vararg function
/// type will have a suffix of 'vararg'. Since function types can contain
/// other function types, we close a function type mangling with suffix 'f'
/// which can't be confused with it's prefix. This ensures we don't have
/// collisions between two unrelated function types. Otherwise, you might
/// parse ffXX as f(fXX) or f(fX)X. (X is a placeholder for any other type.)
/// Manglings of integers, floats, and vectors ('i', 'f', and 'v' prefix in most
/// cases) fall back to the MVT codepath, where they could be mangled to
/// 'x86mmx', for example; matching on derived types is not sufficient to mangle
/// everything.
static std::string getMangledTypeStr(Type* Ty) {
std::string Result;
if (PointerType* PTyp = dyn_cast<PointerType>(Ty)) {
Result += "p" + llvm::utostr(PTyp->getAddressSpace()) +
getMangledTypeStr(PTyp->getElementType());
} else if (ArrayType* ATyp = dyn_cast<ArrayType>(Ty)) {
Result += "a" + llvm::utostr(ATyp->getNumElements()) +
getMangledTypeStr(ATyp->getElementType());
} else if (StructType* STyp = dyn_cast<StructType>(Ty)) {
if (!STyp->isLiteral())
Result += STyp->getName();
else
llvm_unreachable("TODO: implement literal types");
} else if (FunctionType* FT = dyn_cast<FunctionType>(Ty)) {
Result += "f_" + getMangledTypeStr(FT->getReturnType());
for (size_t i = 0; i < FT->getNumParams(); i++)
Result += getMangledTypeStr(FT->getParamType(i));
if (FT->isVarArg())
Result += "vararg";
// Ensure nested function types are distinguishable.
Result += "f";
} else if (Ty)
Result += EVT::getEVT(Ty).getEVTString();
return Result;
}
std::string Intrinsic::getName(ID id, ArrayRef<Type*> Tys) {
assert(id < num_intrinsics && "Invalid intrinsic ID!");
static const char * const Table[] = {
"not_intrinsic",
#define GET_INTRINSIC_NAME_TABLE
#include "llvm/IR/Intrinsics.gen"
#undef GET_INTRINSIC_NAME_TABLE
};
if (Tys.empty())
return Table[id];
std::string Result(Table[id]);
for (unsigned i = 0; i < Tys.size(); ++i) {
Result += "." + getMangledTypeStr(Tys[i]);
}
return Result;
}
/// IIT_Info - These are enumerators that describe the entries returned by the
/// getIntrinsicInfoTableEntries function.
///
/// NOTE: This must be kept in synch with the copy in TblGen/IntrinsicEmitter!
enum IIT_Info {
// Common values should be encoded with 0-15.
IIT_Done = 0,
IIT_I1 = 1,
IIT_I8 = 2,
IIT_I16 = 3,
IIT_I32 = 4,
IIT_I64 = 5,
IIT_F16 = 6,
IIT_F32 = 7,
IIT_F64 = 8,
IIT_V2 = 9,
IIT_V4 = 10,
IIT_V8 = 11,
IIT_V16 = 12,
IIT_V32 = 13,
IIT_PTR = 14,
IIT_ARG = 15,
// Values from 16+ are only encodable with the inefficient encoding.
IIT_V64 = 16,
IIT_MMX = 17,
IIT_METADATA = 18,
IIT_EMPTYSTRUCT = 19,
IIT_STRUCT2 = 20,
IIT_STRUCT3 = 21,
IIT_STRUCT4 = 22,
IIT_STRUCT5 = 23,
IIT_EXTEND_ARG = 24,
IIT_TRUNC_ARG = 25,
IIT_ANYPTR = 26,
IIT_V1 = 27,
IIT_VARARG = 28,
IIT_HALF_VEC_ARG = 29,
IIT_SAME_VEC_WIDTH_ARG = 30,
Masked Gather and Scatter Intrinsics. Gather and Scatter are new introduced intrinsics, comming after recently implemented masked load and store. This is the first patch for Gather and Scatter intrinsics. It includes only the syntax, parsing and verification. Gather and Scatter intrinsics allow to perform multiple memory accesses (read/write) in one vector instruction. The intrinsics are not target specific and will have the following syntax: Gather: declare <16 x i32> @llvm.masked.gather.v16i32(<16 x i32*> <vector of ptrs>, i32 <alignment>, <16 x i1> <mask>, <16 x i32> <passthru>) declare <8 x float> @llvm.masked.gather.v8f32(<8 x float*><vector of ptrs>, i32 <alignment>, <8 x i1> <mask>, <8 x float><passthru>) Scatter: declare void @llvm.masked.scatter.v8i32(<8 x i32><vector value to be stored> , <8 x i32*><vector of ptrs> , i32 <alignment>, <8 x i1> <mask>) declare void @llvm.masked.scatter.v16i32(<16 x i32> <vector value to be stored> , <16 x i32*> <vector of ptrs>, i32 <alignment>, <16 x i1><mask> ) Vector of ptrs - a set of source/destination addresses, to load/store the value. Mask - switches on/off vector lanes to prevent memory access for switched-off lanes vector of ptrs, value and mask should have the same vector width. These are code examples where gather / scatter should be used and will allow function vectorization ;void foo1(int * restrict A, int * restrict B, int * restrict C) { ; for (int i=0; i<SIZE; i++) { ; A[i] = B[C[i]]; ; } ;} ;void foo3(int * restrict A, int * restrict B) { ; for (int i=0; i<SIZE; i++) { ; A[B[i]] = i+5; ; } ;} Tests will come in the following patches, with CodeGen and Vectorizer. http://reviews.llvm.org/D7433 llvm-svn: 228521
2015-02-08 16:27:19 +08:00
IIT_PTR_TO_ARG = 31,
IIT_VEC_OF_PTRS_TO_ELT = 32
};
static void DecodeIITType(unsigned &NextElt, ArrayRef<unsigned char> Infos,
SmallVectorImpl<Intrinsic::IITDescriptor> &OutputTable) {
IIT_Info Info = IIT_Info(Infos[NextElt++]);
unsigned StructElts = 2;
using namespace Intrinsic;
switch (Info) {
case IIT_Done:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Void, 0));
return;
case IIT_VARARG:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::VarArg, 0));
return;
case IIT_MMX:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::MMX, 0));
return;
case IIT_METADATA:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Metadata, 0));
return;
case IIT_F16:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Half, 0));
return;
case IIT_F32:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Float, 0));
return;
case IIT_F64:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Double, 0));
return;
case IIT_I1:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Integer, 1));
return;
case IIT_I8:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Integer, 8));
return;
case IIT_I16:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Integer,16));
return;
case IIT_I32:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Integer, 32));
return;
case IIT_I64:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Integer, 64));
return;
case IIT_V1:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Vector, 1));
DecodeIITType(NextElt, Infos, OutputTable);
return;
case IIT_V2:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Vector, 2));
DecodeIITType(NextElt, Infos, OutputTable);
return;
case IIT_V4:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Vector, 4));
DecodeIITType(NextElt, Infos, OutputTable);
return;
case IIT_V8:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Vector, 8));
DecodeIITType(NextElt, Infos, OutputTable);
return;
case IIT_V16:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Vector, 16));
DecodeIITType(NextElt, Infos, OutputTable);
return;
case IIT_V32:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Vector, 32));
DecodeIITType(NextElt, Infos, OutputTable);
return;
case IIT_V64:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Vector, 64));
DecodeIITType(NextElt, Infos, OutputTable);
return;
case IIT_PTR:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Pointer, 0));
DecodeIITType(NextElt, Infos, OutputTable);
return;
case IIT_ANYPTR: { // [ANYPTR addrspace, subtype]
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Pointer,
Infos[NextElt++]));
DecodeIITType(NextElt, Infos, OutputTable);
return;
}
case IIT_ARG: {
unsigned ArgInfo = (NextElt == Infos.size() ? 0 : Infos[NextElt++]);
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Argument, ArgInfo));
return;
}
case IIT_EXTEND_ARG: {
unsigned ArgInfo = (NextElt == Infos.size() ? 0 : Infos[NextElt++]);
OutputTable.push_back(IITDescriptor::get(IITDescriptor::ExtendArgument,
ArgInfo));
return;
}
case IIT_TRUNC_ARG: {
unsigned ArgInfo = (NextElt == Infos.size() ? 0 : Infos[NextElt++]);
OutputTable.push_back(IITDescriptor::get(IITDescriptor::TruncArgument,
ArgInfo));
return;
}
case IIT_HALF_VEC_ARG: {
unsigned ArgInfo = (NextElt == Infos.size() ? 0 : Infos[NextElt++]);
OutputTable.push_back(IITDescriptor::get(IITDescriptor::HalfVecArgument,
ArgInfo));
return;
}
case IIT_SAME_VEC_WIDTH_ARG: {
unsigned ArgInfo = (NextElt == Infos.size() ? 0 : Infos[NextElt++]);
OutputTable.push_back(IITDescriptor::get(IITDescriptor::SameVecWidthArgument,
ArgInfo));
return;
}
case IIT_PTR_TO_ARG: {
unsigned ArgInfo = (NextElt == Infos.size() ? 0 : Infos[NextElt++]);
OutputTable.push_back(IITDescriptor::get(IITDescriptor::PtrToArgument,
ArgInfo));
return;
}
Masked Gather and Scatter Intrinsics. Gather and Scatter are new introduced intrinsics, comming after recently implemented masked load and store. This is the first patch for Gather and Scatter intrinsics. It includes only the syntax, parsing and verification. Gather and Scatter intrinsics allow to perform multiple memory accesses (read/write) in one vector instruction. The intrinsics are not target specific and will have the following syntax: Gather: declare <16 x i32> @llvm.masked.gather.v16i32(<16 x i32*> <vector of ptrs>, i32 <alignment>, <16 x i1> <mask>, <16 x i32> <passthru>) declare <8 x float> @llvm.masked.gather.v8f32(<8 x float*><vector of ptrs>, i32 <alignment>, <8 x i1> <mask>, <8 x float><passthru>) Scatter: declare void @llvm.masked.scatter.v8i32(<8 x i32><vector value to be stored> , <8 x i32*><vector of ptrs> , i32 <alignment>, <8 x i1> <mask>) declare void @llvm.masked.scatter.v16i32(<16 x i32> <vector value to be stored> , <16 x i32*> <vector of ptrs>, i32 <alignment>, <16 x i1><mask> ) Vector of ptrs - a set of source/destination addresses, to load/store the value. Mask - switches on/off vector lanes to prevent memory access for switched-off lanes vector of ptrs, value and mask should have the same vector width. These are code examples where gather / scatter should be used and will allow function vectorization ;void foo1(int * restrict A, int * restrict B, int * restrict C) { ; for (int i=0; i<SIZE; i++) { ; A[i] = B[C[i]]; ; } ;} ;void foo3(int * restrict A, int * restrict B) { ; for (int i=0; i<SIZE; i++) { ; A[B[i]] = i+5; ; } ;} Tests will come in the following patches, with CodeGen and Vectorizer. http://reviews.llvm.org/D7433 llvm-svn: 228521
2015-02-08 16:27:19 +08:00
case IIT_VEC_OF_PTRS_TO_ELT: {
unsigned ArgInfo = (NextElt == Infos.size() ? 0 : Infos[NextElt++]);
OutputTable.push_back(IITDescriptor::get(IITDescriptor::VecOfPtrsToElt,
ArgInfo));
return;
}
case IIT_EMPTYSTRUCT:
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Struct, 0));
return;
case IIT_STRUCT5: ++StructElts; // FALL THROUGH.
case IIT_STRUCT4: ++StructElts; // FALL THROUGH.
case IIT_STRUCT3: ++StructElts; // FALL THROUGH.
case IIT_STRUCT2: {
OutputTable.push_back(IITDescriptor::get(IITDescriptor::Struct,StructElts));
for (unsigned i = 0; i != StructElts; ++i)
DecodeIITType(NextElt, Infos, OutputTable);
return;
}
}
llvm_unreachable("unhandled");
}
#define GET_INTRINSIC_GENERATOR_GLOBAL
#include "llvm/IR/Intrinsics.gen"
#undef GET_INTRINSIC_GENERATOR_GLOBAL
void Intrinsic::getIntrinsicInfoTableEntries(ID id,
SmallVectorImpl<IITDescriptor> &T){
// Check to see if the intrinsic's type was expressible by the table.
unsigned TableVal = IIT_Table[id-1];
// Decode the TableVal into an array of IITValues.
SmallVector<unsigned char, 8> IITValues;
ArrayRef<unsigned char> IITEntries;
unsigned NextElt = 0;
if ((TableVal >> 31) != 0) {
// This is an offset into the IIT_LongEncodingTable.
IITEntries = IIT_LongEncodingTable;
// Strip sentinel bit.
NextElt = (TableVal << 1) >> 1;
} else {
// Decode the TableVal into an array of IITValues. If the entry was encoded
// into a single word in the table itself, decode it now.
do {
IITValues.push_back(TableVal & 0xF);
TableVal >>= 4;
} while (TableVal);
IITEntries = IITValues;
NextElt = 0;
}
// Okay, decode the table into the output vector of IITDescriptors.
DecodeIITType(NextElt, IITEntries, T);
while (NextElt != IITEntries.size() && IITEntries[NextElt] != 0)
DecodeIITType(NextElt, IITEntries, T);
}
static Type *DecodeFixedType(ArrayRef<Intrinsic::IITDescriptor> &Infos,
ArrayRef<Type*> Tys, LLVMContext &Context) {
using namespace Intrinsic;
IITDescriptor D = Infos.front();
Infos = Infos.slice(1);
switch (D.Kind) {
case IITDescriptor::Void: return Type::getVoidTy(Context);
case IITDescriptor::VarArg: return Type::getVoidTy(Context);
case IITDescriptor::MMX: return Type::getX86_MMXTy(Context);
case IITDescriptor::Metadata: return Type::getMetadataTy(Context);
case IITDescriptor::Half: return Type::getHalfTy(Context);
case IITDescriptor::Float: return Type::getFloatTy(Context);
case IITDescriptor::Double: return Type::getDoubleTy(Context);
case IITDescriptor::Integer:
return IntegerType::get(Context, D.Integer_Width);
case IITDescriptor::Vector:
return VectorType::get(DecodeFixedType(Infos, Tys, Context),D.Vector_Width);
case IITDescriptor::Pointer:
return PointerType::get(DecodeFixedType(Infos, Tys, Context),
D.Pointer_AddressSpace);
case IITDescriptor::Struct: {
Type *Elts[5];
assert(D.Struct_NumElements <= 5 && "Can't handle this yet");
for (unsigned i = 0, e = D.Struct_NumElements; i != e; ++i)
Elts[i] = DecodeFixedType(Infos, Tys, Context);
return StructType::get(Context, makeArrayRef(Elts,D.Struct_NumElements));
}
case IITDescriptor::Argument:
return Tys[D.getArgumentNumber()];
case IITDescriptor::ExtendArgument: {
Type *Ty = Tys[D.getArgumentNumber()];
if (VectorType *VTy = dyn_cast<VectorType>(Ty))
return VectorType::getExtendedElementVectorType(VTy);
return IntegerType::get(Context, 2 * cast<IntegerType>(Ty)->getBitWidth());
}
case IITDescriptor::TruncArgument: {
Type *Ty = Tys[D.getArgumentNumber()];
if (VectorType *VTy = dyn_cast<VectorType>(Ty))
return VectorType::getTruncatedElementVectorType(VTy);
IntegerType *ITy = cast<IntegerType>(Ty);
assert(ITy->getBitWidth() % 2 == 0);
return IntegerType::get(Context, ITy->getBitWidth() / 2);
}
case IITDescriptor::HalfVecArgument:
return VectorType::getHalfElementsVectorType(cast<VectorType>(
Tys[D.getArgumentNumber()]));
case IITDescriptor::SameVecWidthArgument: {
Type *EltTy = DecodeFixedType(Infos, Tys, Context);
Type *Ty = Tys[D.getArgumentNumber()];
if (VectorType *VTy = dyn_cast<VectorType>(Ty)) {
return VectorType::get(EltTy, VTy->getNumElements());
}
llvm_unreachable("unhandled");
}
case IITDescriptor::PtrToArgument: {
Type *Ty = Tys[D.getArgumentNumber()];
return PointerType::getUnqual(Ty);
}
Masked Gather and Scatter Intrinsics. Gather and Scatter are new introduced intrinsics, comming after recently implemented masked load and store. This is the first patch for Gather and Scatter intrinsics. It includes only the syntax, parsing and verification. Gather and Scatter intrinsics allow to perform multiple memory accesses (read/write) in one vector instruction. The intrinsics are not target specific and will have the following syntax: Gather: declare <16 x i32> @llvm.masked.gather.v16i32(<16 x i32*> <vector of ptrs>, i32 <alignment>, <16 x i1> <mask>, <16 x i32> <passthru>) declare <8 x float> @llvm.masked.gather.v8f32(<8 x float*><vector of ptrs>, i32 <alignment>, <8 x i1> <mask>, <8 x float><passthru>) Scatter: declare void @llvm.masked.scatter.v8i32(<8 x i32><vector value to be stored> , <8 x i32*><vector of ptrs> , i32 <alignment>, <8 x i1> <mask>) declare void @llvm.masked.scatter.v16i32(<16 x i32> <vector value to be stored> , <16 x i32*> <vector of ptrs>, i32 <alignment>, <16 x i1><mask> ) Vector of ptrs - a set of source/destination addresses, to load/store the value. Mask - switches on/off vector lanes to prevent memory access for switched-off lanes vector of ptrs, value and mask should have the same vector width. These are code examples where gather / scatter should be used and will allow function vectorization ;void foo1(int * restrict A, int * restrict B, int * restrict C) { ; for (int i=0; i<SIZE; i++) { ; A[i] = B[C[i]]; ; } ;} ;void foo3(int * restrict A, int * restrict B) { ; for (int i=0; i<SIZE; i++) { ; A[B[i]] = i+5; ; } ;} Tests will come in the following patches, with CodeGen and Vectorizer. http://reviews.llvm.org/D7433 llvm-svn: 228521
2015-02-08 16:27:19 +08:00
case IITDescriptor::VecOfPtrsToElt: {
Type *Ty = Tys[D.getArgumentNumber()];
VectorType *VTy = dyn_cast<VectorType>(Ty);
if (!VTy)
llvm_unreachable("Expected an argument of Vector Type");
Type *EltTy = VTy->getVectorElementType();
return VectorType::get(PointerType::getUnqual(EltTy),
VTy->getNumElements());
}
}
llvm_unreachable("unhandled");
}
FunctionType *Intrinsic::getType(LLVMContext &Context,
ID id, ArrayRef<Type*> Tys) {
SmallVector<IITDescriptor, 8> Table;
getIntrinsicInfoTableEntries(id, Table);
ArrayRef<IITDescriptor> TableRef = Table;
Type *ResultTy = DecodeFixedType(TableRef, Tys, Context);
SmallVector<Type*, 8> ArgTys;
while (!TableRef.empty())
ArgTys.push_back(DecodeFixedType(TableRef, Tys, Context));
// DecodeFixedType returns Void for IITDescriptor::Void and IITDescriptor::VarArg
// If we see void type as the type of the last argument, it is vararg intrinsic
if (!ArgTys.empty() && ArgTys.back()->isVoidTy()) {
ArgTys.pop_back();
return FunctionType::get(ResultTy, ArgTys, true);
}
return FunctionType::get(ResultTy, ArgTys, false);
}
bool Intrinsic::isOverloaded(ID id) {
#define GET_INTRINSIC_OVERLOAD_TABLE
#include "llvm/IR/Intrinsics.gen"
#undef GET_INTRINSIC_OVERLOAD_TABLE
}
/// This defines the "Intrinsic::getAttributes(ID id)" method.
#define GET_INTRINSIC_ATTRIBUTES
#include "llvm/IR/Intrinsics.gen"
#undef GET_INTRINSIC_ATTRIBUTES
Function *Intrinsic::getDeclaration(Module *M, ID id, ArrayRef<Type*> Tys) {
// There can never be multiple globals with the same name of different types,
// because intrinsics must be a specific type.
return
cast<Function>(M->getOrInsertFunction(getName(id, Tys),
getType(M->getContext(), id, Tys)));
}
// This defines the "Intrinsic::getIntrinsicForGCCBuiltin()" method.
#define GET_LLVM_INTRINSIC_FOR_GCC_BUILTIN
#include "llvm/IR/Intrinsics.gen"
#undef GET_LLVM_INTRINSIC_FOR_GCC_BUILTIN
// This defines the "Intrinsic::getIntrinsicForMSBuiltin()" method.
#define GET_LLVM_INTRINSIC_FOR_MS_BUILTIN
#include "llvm/IR/Intrinsics.gen"
#undef GET_LLVM_INTRINSIC_FOR_MS_BUILTIN
/// hasAddressTaken - returns true if there are any uses of this function
/// other than direct calls or invokes to it.
bool Function::hasAddressTaken(const User* *PutOffender) const {
[C++11] Add range based accessors for the Use-Def chain of a Value. This requires a number of steps. 1) Move value_use_iterator into the Value class as an implementation detail 2) Change it to actually be a *Use* iterator rather than a *User* iterator. 3) Add an adaptor which is a User iterator that always looks through the Use to the User. 4) Wrap these in Value::use_iterator and Value::user_iterator typedefs. 5) Add the range adaptors as Value::uses() and Value::users(). 6) Update *all* of the callers to correctly distinguish between whether they wanted a use_iterator (and to explicitly dig out the User when needed), or a user_iterator which makes the Use itself totally opaque. Because #6 requires churning essentially everything that walked the Use-Def chains, I went ahead and added all of the range adaptors and switched them to range-based loops where appropriate. Also because the renaming requires at least churning every line of code, it didn't make any sense to split these up into multiple commits -- all of which would touch all of the same lies of code. The result is still not quite optimal. The Value::use_iterator is a nice regular iterator, but Value::user_iterator is an iterator over User*s rather than over the User objects themselves. As a consequence, it fits a bit awkwardly into the range-based world and it has the weird extra-dereferencing 'operator->' that so many of our iterators have. I think this could be fixed by providing something which transforms a range of T&s into a range of T*s, but that *can* be separated into another patch, and it isn't yet 100% clear whether this is the right move. However, this change gets us most of the benefit and cleans up a substantial amount of code around Use and User. =] llvm-svn: 203364
2014-03-09 11:16:01 +08:00
for (const Use &U : uses()) {
const User *FU = U.getUser();
if (isa<BlockAddress>(FU))
continue;
[C++11] Add range based accessors for the Use-Def chain of a Value. This requires a number of steps. 1) Move value_use_iterator into the Value class as an implementation detail 2) Change it to actually be a *Use* iterator rather than a *User* iterator. 3) Add an adaptor which is a User iterator that always looks through the Use to the User. 4) Wrap these in Value::use_iterator and Value::user_iterator typedefs. 5) Add the range adaptors as Value::uses() and Value::users(). 6) Update *all* of the callers to correctly distinguish between whether they wanted a use_iterator (and to explicitly dig out the User when needed), or a user_iterator which makes the Use itself totally opaque. Because #6 requires churning essentially everything that walked the Use-Def chains, I went ahead and added all of the range adaptors and switched them to range-based loops where appropriate. Also because the renaming requires at least churning every line of code, it didn't make any sense to split these up into multiple commits -- all of which would touch all of the same lies of code. The result is still not quite optimal. The Value::use_iterator is a nice regular iterator, but Value::user_iterator is an iterator over User*s rather than over the User objects themselves. As a consequence, it fits a bit awkwardly into the range-based world and it has the weird extra-dereferencing 'operator->' that so many of our iterators have. I think this could be fixed by providing something which transforms a range of T&s into a range of T*s, but that *can* be separated into another patch, and it isn't yet 100% clear whether this is the right move. However, this change gets us most of the benefit and cleans up a substantial amount of code around Use and User. =] llvm-svn: 203364
2014-03-09 11:16:01 +08:00
if (!isa<CallInst>(FU) && !isa<InvokeInst>(FU))
return PutOffender ? (*PutOffender = FU, true) : true;
ImmutableCallSite CS(cast<Instruction>(FU));
if (!CS.isCallee(&U))
return PutOffender ? (*PutOffender = FU, true) : true;
}
return false;
}
bool Function::isDefTriviallyDead() const {
// Check the linkage
if (!hasLinkOnceLinkage() && !hasLocalLinkage() &&
!hasAvailableExternallyLinkage())
return false;
// Check if the function is used by anything other than a blockaddress.
[C++11] Add range based accessors for the Use-Def chain of a Value. This requires a number of steps. 1) Move value_use_iterator into the Value class as an implementation detail 2) Change it to actually be a *Use* iterator rather than a *User* iterator. 3) Add an adaptor which is a User iterator that always looks through the Use to the User. 4) Wrap these in Value::use_iterator and Value::user_iterator typedefs. 5) Add the range adaptors as Value::uses() and Value::users(). 6) Update *all* of the callers to correctly distinguish between whether they wanted a use_iterator (and to explicitly dig out the User when needed), or a user_iterator which makes the Use itself totally opaque. Because #6 requires churning essentially everything that walked the Use-Def chains, I went ahead and added all of the range adaptors and switched them to range-based loops where appropriate. Also because the renaming requires at least churning every line of code, it didn't make any sense to split these up into multiple commits -- all of which would touch all of the same lies of code. The result is still not quite optimal. The Value::use_iterator is a nice regular iterator, but Value::user_iterator is an iterator over User*s rather than over the User objects themselves. As a consequence, it fits a bit awkwardly into the range-based world and it has the weird extra-dereferencing 'operator->' that so many of our iterators have. I think this could be fixed by providing something which transforms a range of T&s into a range of T*s, but that *can* be separated into another patch, and it isn't yet 100% clear whether this is the right move. However, this change gets us most of the benefit and cleans up a substantial amount of code around Use and User. =] llvm-svn: 203364
2014-03-09 11:16:01 +08:00
for (const User *U : users())
if (!isa<BlockAddress>(U))
return false;
return true;
}
/// callsFunctionThatReturnsTwice - Return true if the function has a call to
/// setjmp or other function that gcc recognizes as "returning twice".
bool Function::callsFunctionThatReturnsTwice() const {
for (const_inst_iterator
I = inst_begin(this), E = inst_end(this); I != E; ++I) {
ImmutableCallSite CS(&*I);
if (CS && CS.hasFnAttr(Attribute::ReturnsTwice))
return true;
}
return false;
}
Constant *Function::getPrefixData() const {
assert(hasPrefixData());
const LLVMContextImpl::PrefixDataMapTy &PDMap =
getContext().pImpl->PrefixDataMap;
assert(PDMap.find(this) != PDMap.end());
return cast<Constant>(PDMap.find(this)->second->getReturnValue());
}
void Function::setPrefixData(Constant *PrefixData) {
if (!PrefixData && !hasPrefixData())
return;
unsigned SCData = getSubclassDataFromValue();
LLVMContextImpl::PrefixDataMapTy &PDMap = getContext().pImpl->PrefixDataMap;
ReturnInst *&PDHolder = PDMap[this];
if (PrefixData) {
if (PDHolder)
PDHolder->setOperand(0, PrefixData);
else
PDHolder = ReturnInst::Create(getContext(), PrefixData);
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
SCData |= (1<<1);
} else {
delete PDHolder;
PDMap.erase(this);
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
SCData &= ~(1<<1);
}
setValueSubclassData(SCData);
}
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
Constant *Function::getPrologueData() const {
assert(hasPrologueData());
const LLVMContextImpl::PrologueDataMapTy &SOMap =
getContext().pImpl->PrologueDataMap;
assert(SOMap.find(this) != SOMap.end());
return cast<Constant>(SOMap.find(this)->second->getReturnValue());
}
void Function::setPrologueData(Constant *PrologueData) {
if (!PrologueData && !hasPrologueData())
return;
unsigned PDData = getSubclassDataFromValue();
LLVMContextImpl::PrologueDataMapTy &PDMap = getContext().pImpl->PrologueDataMap;
ReturnInst *&PDHolder = PDMap[this];
if (PrologueData) {
if (PDHolder)
PDHolder->setOperand(0, PrologueData);
else
PDHolder = ReturnInst::Create(getContext(), PrologueData);
PDData |= (1<<2);
} else {
delete PDHolder;
PDMap.erase(this);
PDData &= ~(1<<2);
}
setValueSubclassData(PDData);
}