forked from OSchip/llvm-project
366 lines
11 KiB
C++
366 lines
11 KiB
C++
//===-- X86Subtarget.cpp - X86 Subtarget Information ----------------------===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file implements the X86 specific subclass of TargetSubtargetInfo.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "X86Subtarget.h"
|
|
#include "X86InstrInfo.h"
|
|
#include "X86TargetMachine.h"
|
|
#include "llvm/IR/Attributes.h"
|
|
#include "llvm/IR/Function.h"
|
|
#include "llvm/IR/GlobalValue.h"
|
|
#include "llvm/Support/CommandLine.h"
|
|
#include "llvm/Support/Debug.h"
|
|
#include "llvm/Support/ErrorHandling.h"
|
|
#include "llvm/Support/Host.h"
|
|
#include "llvm/Support/raw_ostream.h"
|
|
#include "llvm/Target/TargetMachine.h"
|
|
#include "llvm/Target/TargetOptions.h"
|
|
|
|
#if defined(_MSC_VER)
|
|
#include <intrin.h>
|
|
#endif
|
|
|
|
using namespace llvm;
|
|
|
|
#define DEBUG_TYPE "subtarget"
|
|
|
|
#define GET_SUBTARGETINFO_TARGET_DESC
|
|
#define GET_SUBTARGETINFO_CTOR
|
|
#include "X86GenSubtargetInfo.inc"
|
|
|
|
// Temporary option to control early if-conversion for x86 while adding machine
|
|
// models.
|
|
static cl::opt<bool>
|
|
X86EarlyIfConv("x86-early-ifcvt", cl::Hidden,
|
|
cl::desc("Enable early if-conversion on X86"));
|
|
|
|
|
|
/// Classify a blockaddress reference for the current subtarget according to how
|
|
/// we should reference it in a non-pcrel context.
|
|
unsigned char X86Subtarget::classifyBlockAddressReference() const {
|
|
return classifyLocalReference(nullptr);
|
|
}
|
|
|
|
/// Classify a global variable reference for the current subtarget according to
|
|
/// how we should reference it in a non-pcrel context.
|
|
unsigned char
|
|
X86Subtarget::classifyGlobalReference(const GlobalValue *GV) const {
|
|
return classifyGlobalReference(GV, *GV->getParent());
|
|
}
|
|
|
|
unsigned char
|
|
X86Subtarget::classifyLocalReference(const GlobalValue *GV) const {
|
|
// 64 bits can use %rip addressing for anything local.
|
|
if (is64Bit())
|
|
return X86II::MO_NO_FLAG;
|
|
|
|
// If this is for a position dependent executable, the static linker can
|
|
// figure it out.
|
|
if (!isPositionIndependent())
|
|
return X86II::MO_NO_FLAG;
|
|
|
|
// The COFF dynamic linker just patches the executable sections.
|
|
if (isTargetCOFF())
|
|
return X86II::MO_NO_FLAG;
|
|
|
|
if (isTargetDarwin()) {
|
|
// 32 bit macho has no relocation for a-b if a is undefined, even if
|
|
// b is in the section that is being relocated.
|
|
// This means we have to use o load even for GVs that are known to be
|
|
// local to the dso.
|
|
if (GV && (GV->isDeclarationForLinker() || GV->hasCommonLinkage()))
|
|
return X86II::MO_DARWIN_NONLAZY_PIC_BASE;
|
|
|
|
return X86II::MO_PIC_BASE_OFFSET;
|
|
}
|
|
|
|
return X86II::MO_GOTOFF;
|
|
}
|
|
|
|
unsigned char X86Subtarget::classifyGlobalReference(const GlobalValue *GV,
|
|
const Module &M) const {
|
|
// Large model never uses stubs.
|
|
if (TM.getCodeModel() == CodeModel::Large)
|
|
return X86II::MO_NO_FLAG;
|
|
|
|
// Absolute symbols can be referenced directly.
|
|
if (GV && GV->isAbsoluteSymbolRef())
|
|
return X86II::MO_NO_FLAG;
|
|
|
|
if (TM.shouldAssumeDSOLocal(M, GV))
|
|
return classifyLocalReference(GV);
|
|
|
|
if (isTargetCOFF())
|
|
return X86II::MO_DLLIMPORT;
|
|
|
|
if (is64Bit())
|
|
return X86II::MO_GOTPCREL;
|
|
|
|
if (isTargetDarwin()) {
|
|
if (!isPositionIndependent())
|
|
return X86II::MO_DARWIN_NONLAZY;
|
|
return X86II::MO_DARWIN_NONLAZY_PIC_BASE;
|
|
}
|
|
|
|
return X86II::MO_GOT;
|
|
}
|
|
|
|
unsigned char
|
|
X86Subtarget::classifyGlobalFunctionReference(const GlobalValue *GV) const {
|
|
return classifyGlobalFunctionReference(GV, *GV->getParent());
|
|
}
|
|
|
|
unsigned char
|
|
X86Subtarget::classifyGlobalFunctionReference(const GlobalValue *GV,
|
|
const Module &M) const {
|
|
if (TM.shouldAssumeDSOLocal(M, GV))
|
|
return X86II::MO_NO_FLAG;
|
|
|
|
assert(!isTargetCOFF());
|
|
|
|
if (isTargetELF())
|
|
return X86II::MO_PLT;
|
|
|
|
if (is64Bit()) {
|
|
auto *F = dyn_cast_or_null<Function>(GV);
|
|
if (F && F->hasFnAttribute(Attribute::NonLazyBind))
|
|
// If the function is marked as non-lazy, generate an indirect call
|
|
// which loads from the GOT directly. This avoids runtime overhead
|
|
// at the cost of eager binding (and one extra byte of encoding).
|
|
return X86II::MO_GOTPCREL;
|
|
return X86II::MO_NO_FLAG;
|
|
}
|
|
|
|
return X86II::MO_NO_FLAG;
|
|
}
|
|
|
|
/// This function returns the name of a function which has an interface like
|
|
/// the non-standard bzero function, if such a function exists on the
|
|
/// current subtarget and it is considered preferable over memset with zero
|
|
/// passed as the second argument. Otherwise it returns null.
|
|
const char *X86Subtarget::getBZeroEntry() const {
|
|
// Darwin 10 has a __bzero entry point for this purpose.
|
|
if (getTargetTriple().isMacOSX() &&
|
|
!getTargetTriple().isMacOSXVersionLT(10, 6))
|
|
return "__bzero";
|
|
|
|
return nullptr;
|
|
}
|
|
|
|
bool X86Subtarget::hasSinCos() const {
|
|
return getTargetTriple().isMacOSX() &&
|
|
!getTargetTriple().isMacOSXVersionLT(10, 9) &&
|
|
is64Bit();
|
|
}
|
|
|
|
/// Return true if the subtarget allows calls to immediate address.
|
|
bool X86Subtarget::isLegalToCallImmediateAddr() const {
|
|
// FIXME: I386 PE/COFF supports PC relative calls using IMAGE_REL_I386_REL32
|
|
// but WinCOFFObjectWriter::RecordRelocation cannot emit them. Once it does,
|
|
// the following check for Win32 should be removed.
|
|
if (In64BitMode || isTargetWin32())
|
|
return false;
|
|
return isTargetELF() || TM.getRelocationModel() == Reloc::Static;
|
|
}
|
|
|
|
void X86Subtarget::initSubtargetFeatures(StringRef CPU, StringRef FS) {
|
|
std::string CPUName = CPU;
|
|
if (CPUName.empty())
|
|
CPUName = "generic";
|
|
|
|
// Make sure 64-bit features are available in 64-bit mode. (But make sure
|
|
// SSE2 can be turned off explicitly.)
|
|
std::string FullFS = FS;
|
|
if (In64BitMode) {
|
|
if (!FullFS.empty())
|
|
FullFS = "+64bit,+sse2," + FullFS;
|
|
else
|
|
FullFS = "+64bit,+sse2";
|
|
}
|
|
|
|
// LAHF/SAHF are always supported in non-64-bit mode.
|
|
if (!In64BitMode) {
|
|
if (!FullFS.empty())
|
|
FullFS = "+sahf," + FullFS;
|
|
else
|
|
FullFS = "+sahf";
|
|
}
|
|
|
|
|
|
// Parse features string and set the CPU.
|
|
ParseSubtargetFeatures(CPUName, FullFS);
|
|
|
|
// All CPUs that implement SSE4.2 or SSE4A support unaligned accesses of
|
|
// 16-bytes and under that are reasonably fast. These features were
|
|
// introduced with Intel's Nehalem/Silvermont and AMD's Family10h
|
|
// micro-architectures respectively.
|
|
if (hasSSE42() || hasSSE4A())
|
|
IsUAMem16Slow = false;
|
|
|
|
InstrItins = getInstrItineraryForCPU(CPUName);
|
|
|
|
// It's important to keep the MCSubtargetInfo feature bits in sync with
|
|
// target data structure which is shared with MC code emitter, etc.
|
|
if (In64BitMode)
|
|
ToggleFeature(X86::Mode64Bit);
|
|
else if (In32BitMode)
|
|
ToggleFeature(X86::Mode32Bit);
|
|
else if (In16BitMode)
|
|
ToggleFeature(X86::Mode16Bit);
|
|
else
|
|
llvm_unreachable("Not 16-bit, 32-bit or 64-bit mode!");
|
|
|
|
DEBUG(dbgs() << "Subtarget features: SSELevel " << X86SSELevel
|
|
<< ", 3DNowLevel " << X863DNowLevel
|
|
<< ", 64bit " << HasX86_64 << "\n");
|
|
assert((!In64BitMode || HasX86_64) &&
|
|
"64-bit code requested on a subtarget that doesn't support it!");
|
|
|
|
// Stack alignment is 16 bytes on Darwin, Linux, kFreeBSD and Solaris (both
|
|
// 32 and 64 bit) and for all 64-bit targets.
|
|
if (StackAlignOverride)
|
|
stackAlignment = StackAlignOverride;
|
|
else if (isTargetDarwin() || isTargetLinux() || isTargetSolaris() ||
|
|
isTargetKFreeBSD() || In64BitMode)
|
|
stackAlignment = 16;
|
|
|
|
assert((!isPMULLDSlow() || hasSSE41()) &&
|
|
"Feature Slow PMULLD can only be set on a subtarget with SSE4.1");
|
|
}
|
|
|
|
void X86Subtarget::initializeEnvironment() {
|
|
X86SSELevel = NoSSE;
|
|
X863DNowLevel = NoThreeDNow;
|
|
HasX87 = false;
|
|
HasCMov = false;
|
|
HasX86_64 = false;
|
|
HasPOPCNT = false;
|
|
HasSSE4A = false;
|
|
HasAES = false;
|
|
HasFXSR = false;
|
|
HasXSAVE = false;
|
|
HasXSAVEOPT = false;
|
|
HasXSAVEC = false;
|
|
HasXSAVES = false;
|
|
HasPCLMUL = false;
|
|
HasFMA = false;
|
|
HasFMA4 = false;
|
|
HasXOP = false;
|
|
HasTBM = false;
|
|
HasMOVBE = false;
|
|
HasRDRAND = false;
|
|
HasF16C = false;
|
|
HasFSGSBase = false;
|
|
HasLZCNT = false;
|
|
HasBMI = false;
|
|
HasBMI2 = false;
|
|
HasVBMI = false;
|
|
HasIFMA = false;
|
|
HasRTM = false;
|
|
HasHLE = false;
|
|
HasERI = false;
|
|
HasCDI = false;
|
|
HasPFI = false;
|
|
HasDQI = false;
|
|
HasBWI = false;
|
|
HasVLX = false;
|
|
HasADX = false;
|
|
HasPKU = false;
|
|
HasSHA = false;
|
|
HasPRFCHW = false;
|
|
HasRDSEED = false;
|
|
HasLAHFSAHF = false;
|
|
HasMWAITX = false;
|
|
HasMPX = false;
|
|
IsBTMemSlow = false;
|
|
IsPMULLDSlow = false;
|
|
IsSHLDSlow = false;
|
|
IsUAMem16Slow = false;
|
|
IsUAMem32Slow = false;
|
|
HasSSEUnalignedMem = false;
|
|
HasCmpxchg16b = false;
|
|
UseLeaForSP = false;
|
|
HasFastPartialYMMWrite = false;
|
|
HasFastScalarFSQRT = false;
|
|
HasFastVectorFSQRT = false;
|
|
HasFastLZCNT = false;
|
|
HasSlowDivide32 = false;
|
|
HasSlowDivide64 = false;
|
|
PadShortFunctions = false;
|
|
CallRegIndirect = false;
|
|
LEAUsesAG = false;
|
|
SlowLEA = false;
|
|
SlowIncDec = false;
|
|
stackAlignment = 4;
|
|
// FIXME: this is a known good value for Yonah. How about others?
|
|
MaxInlineSizeThreshold = 128;
|
|
UseSoftFloat = false;
|
|
}
|
|
|
|
X86Subtarget &X86Subtarget::initializeSubtargetDependencies(StringRef CPU,
|
|
StringRef FS) {
|
|
initializeEnvironment();
|
|
initSubtargetFeatures(CPU, FS);
|
|
return *this;
|
|
}
|
|
|
|
X86Subtarget::X86Subtarget(const Triple &TT, StringRef CPU, StringRef FS,
|
|
const X86TargetMachine &TM,
|
|
unsigned StackAlignOverride)
|
|
: X86GenSubtargetInfo(TT, CPU, FS), X86ProcFamily(Others),
|
|
PICStyle(PICStyles::None), TM(TM), TargetTriple(TT),
|
|
StackAlignOverride(StackAlignOverride),
|
|
In64BitMode(TargetTriple.getArch() == Triple::x86_64),
|
|
In32BitMode(TargetTriple.getArch() == Triple::x86 &&
|
|
TargetTriple.getEnvironment() != Triple::CODE16),
|
|
In16BitMode(TargetTriple.getArch() == Triple::x86 &&
|
|
TargetTriple.getEnvironment() == Triple::CODE16),
|
|
TSInfo(), InstrInfo(initializeSubtargetDependencies(CPU, FS)),
|
|
TLInfo(TM, *this), FrameLowering(*this, getStackAlignment()) {
|
|
// Determine the PICStyle based on the target selected.
|
|
if (!isPositionIndependent())
|
|
setPICStyle(PICStyles::None);
|
|
else if (is64Bit())
|
|
setPICStyle(PICStyles::RIPRel);
|
|
else if (isTargetCOFF())
|
|
setPICStyle(PICStyles::None);
|
|
else if (isTargetDarwin())
|
|
setPICStyle(PICStyles::StubPIC);
|
|
else if (isTargetELF())
|
|
setPICStyle(PICStyles::GOT);
|
|
}
|
|
|
|
const CallLowering *X86Subtarget::getCallLowering() const {
|
|
assert(GISel && "Access to GlobalISel APIs not set");
|
|
return GISel->getCallLowering();
|
|
}
|
|
|
|
const InstructionSelector *X86Subtarget::getInstructionSelector() const {
|
|
assert(GISel && "Access to GlobalISel APIs not set");
|
|
return GISel->getInstructionSelector();
|
|
}
|
|
|
|
const LegalizerInfo *X86Subtarget::getLegalizerInfo() const {
|
|
assert(GISel && "Access to GlobalISel APIs not set");
|
|
return GISel->getLegalizerInfo();
|
|
}
|
|
|
|
const RegisterBankInfo *X86Subtarget::getRegBankInfo() const {
|
|
assert(GISel && "Access to GlobalISel APIs not set");
|
|
return GISel->getRegBankInfo();
|
|
}
|
|
|
|
bool X86Subtarget::enableEarlyIfConversion() const {
|
|
return hasCMov() && X86EarlyIfConv;
|
|
}
|
|
|