#include "X86TargetMachine.h"
#include "X86.h"
-#include "llvm/CodeGen/MachineFunction.h"
+#include "X86TargetObjectFile.h"
+#include "X86TargetTransformInfo.h"
#include "llvm/CodeGen/Passes.h"
-#include "llvm/PassManager.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/LegacyPassManager.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/FormattedStream.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Target/TargetOptions.h"
using namespace llvm;
+static cl::opt<bool> EnableMachineCombinerPass("x86-machine-combiner",
+ cl::desc("Enable the machine combiner pass"),
+ cl::init(true), cl::Hidden);
+
+namespace llvm {
+void initializeWinEHStatePassPass(PassRegistry &);
+}
+
extern "C" void LLVMInitializeX86Target() {
// Register the target.
- RegisterTargetMachine<X86_32TargetMachine> X(TheX86_32Target);
- RegisterTargetMachine<X86_64TargetMachine> Y(TheX86_64Target);
+ RegisterTargetMachine<X86TargetMachine> X(TheX86_32Target);
+ RegisterTargetMachine<X86TargetMachine> Y(TheX86_64Target);
+
+ PassRegistry &PR = *PassRegistry::getPassRegistry();
+ initializeWinEHStatePassPass(PR);
}
-void X86_32TargetMachine::anchor() { }
-
-X86_32TargetMachine::X86_32TargetMachine(const Target &T, StringRef TT,
- StringRef CPU, StringRef FS,
- const TargetOptions &Options,
- Reloc::Model RM, CodeModel::Model CM,
- CodeGenOpt::Level OL)
- : X86TargetMachine(T, TT, CPU, FS, Options, RM, CM, OL, false),
- DL(getSubtargetImpl()->isTargetDarwin() ?
- "e-p:32:32-f64:32:64-i64:32:64-f80:128:128-f128:128:128-"
- "n8:16:32-S128" :
- (getSubtargetImpl()->isTargetCygMing() ||
- getSubtargetImpl()->isTargetWindows()) ?
- "e-p:32:32-f64:64:64-i64:64:64-f80:32:32-f128:128:128-"
- "n8:16:32-S32" :
- "e-p:32:32-f64:32:64-i64:32:64-f80:32:32-f128:128:128-"
- "n8:16:32-S128"),
- InstrInfo(*this),
- TLInfo(*this),
- TSInfo(*this),
- JITInfo(*this),
- STTI(&TLInfo), VTTI(&TLInfo) {
+static std::unique_ptr<TargetLoweringObjectFile> createTLOF(const Triple &TT) {
+ if (TT.isOSBinFormatMachO()) {
+ if (TT.getArch() == Triple::x86_64)
+ return make_unique<X86_64MachoTargetObjectFile>();
+ return make_unique<TargetLoweringObjectFileMachO>();
+ }
+
+ if (TT.isOSLinux() || TT.isOSNaCl())
+ return make_unique<X86LinuxNaClTargetObjectFile>();
+ if (TT.isOSBinFormatELF())
+ return make_unique<X86ELFTargetObjectFile>();
+ if (TT.isKnownWindowsMSVCEnvironment() || TT.isWindowsCoreCLREnvironment())
+ return make_unique<X86WindowsTargetObjectFile>();
+ if (TT.isOSBinFormatCOFF())
+ return make_unique<TargetLoweringObjectFileCOFF>();
+ llvm_unreachable("unknown subtarget type");
}
-void X86_64TargetMachine::anchor() { }
-
-X86_64TargetMachine::X86_64TargetMachine(const Target &T, StringRef TT,
- StringRef CPU, StringRef FS,
- const TargetOptions &Options,
- Reloc::Model RM, CodeModel::Model CM,
- CodeGenOpt::Level OL)
- : X86TargetMachine(T, TT, CPU, FS, Options, RM, CM, OL, true),
- DL("e-p:64:64-s:64-f64:64:64-i64:64:64-f80:128:128-f128:128:128-"
- "n8:16:32:64-S128"),
- InstrInfo(*this),
- TLInfo(*this),
- TSInfo(*this),
- JITInfo(*this),
- STTI(&TLInfo), VTTI(&TLInfo){
+static std::string computeDataLayout(const Triple &TT) {
+ // X86 is little endian
+ std::string Ret = "e";
+
+ Ret += DataLayout::getManglingComponent(TT);
+ // X86 and x32 have 32 bit pointers.
+ if ((TT.isArch64Bit() &&
+ (TT.getEnvironment() == Triple::GNUX32 || TT.isOSNaCl())) ||
+ !TT.isArch64Bit())
+ Ret += "-p:32:32";
+
+ // Some ABIs align 64 bit integers and doubles to 64 bits, others to 32.
+ if (TT.isArch64Bit() || TT.isOSWindows() || TT.isOSNaCl())
+ Ret += "-i64:64";
+ else
+ Ret += "-f64:32:64";
+
+ // Some ABIs align long double to 128 bits, others to 32.
+ if (TT.isOSNaCl())
+ ; // No f80
+ else if (TT.isArch64Bit() || TT.isOSDarwin())
+ Ret += "-f80:128";
+ else
+ Ret += "-f80:32";
+
+ // The registers can hold 8, 16, 32 or, in x86-64, 64 bits.
+ if (TT.isArch64Bit())
+ Ret += "-n8:16:32:64";
+ else
+ Ret += "-n8:16:32";
+
+ // The stack is aligned to 32 bits on some ABIs and 128 bits on others.
+ if (!TT.isArch64Bit() && TT.isOSWindows())
+ Ret += "-a:0:32-S32";
+ else
+ Ret += "-S128";
+
+ return Ret;
}
/// X86TargetMachine ctor - Create an X86 target.
///
-X86TargetMachine::X86TargetMachine(const Target &T, StringRef TT,
+X86TargetMachine::X86TargetMachine(const Target &T, const Triple &TT,
StringRef CPU, StringRef FS,
const TargetOptions &Options,
Reloc::Model RM, CodeModel::Model CM,
- CodeGenOpt::Level OL,
- bool is64Bit)
- : LLVMTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL),
- Subtarget(TT, CPU, FS, Options.StackAlignmentOverride, is64Bit),
- FrameLowering(*this, Subtarget),
- InstrItins(Subtarget.getInstrItineraryData()){
- // Determine the PICStyle based on the target selected.
- if (getRelocationModel() == Reloc::Static) {
- // Unless we're in PIC or DynamicNoPIC mode, set the PIC style to None.
- Subtarget.setPICStyle(PICStyles::None);
- } else if (Subtarget.is64Bit()) {
- // PIC in 64 bit mode is always rip-rel.
- Subtarget.setPICStyle(PICStyles::RIPRel);
- } else if (Subtarget.isTargetCygMing()) {
- Subtarget.setPICStyle(PICStyles::None);
- } else if (Subtarget.isTargetDarwin()) {
- if (getRelocationModel() == Reloc::PIC_)
- Subtarget.setPICStyle(PICStyles::StubPIC);
- else {
- assert(getRelocationModel() == Reloc::DynamicNoPIC);
- Subtarget.setPICStyle(PICStyles::StubDynamicNoPIC);
- }
- } else if (Subtarget.isTargetELF()) {
- Subtarget.setPICStyle(PICStyles::GOT);
- }
+ CodeGenOpt::Level OL)
+ : LLVMTargetMachine(T, computeDataLayout(TT), TT, CPU, FS, Options, RM, CM,
+ OL),
+ TLOF(createTLOF(getTargetTriple())),
+ Subtarget(TT, CPU, FS, *this, Options.StackAlignmentOverride) {
+ // Windows stack unwinder gets confused when execution flow "falls through"
+ // after a call to 'noreturn' function.
+ // To prevent that, we emit a trap for 'unreachable' IR instructions.
+ // (which on X86, happens to be the 'ud2' instruction)
+ if (Subtarget.isTargetWin64())
+ this->Options.TrapUnreachable = true;
+
+ // By default (and when -ffast-math is on), enable estimate codegen for
+ // everything except scalar division. By default, use 1 refinement step for
+ // all operations. Defaults may be overridden by using command-line options.
+ // Scalar division estimates are disabled because they break too much
+ // real-world code. These defaults match GCC behavior.
+ this->Options.Reciprocals.setDefaults("sqrtf", true, 1);
+ this->Options.Reciprocals.setDefaults("divf", false, 1);
+ this->Options.Reciprocals.setDefaults("vec-sqrtf", true, 1);
+ this->Options.Reciprocals.setDefaults("vec-divf", true, 1);
+
+ initAsmInfo();
+}
- // default to hard float ABI
- if (Options.FloatABIType == FloatABI::Default)
- this->Options.FloatABIType = FloatABI::Hard;
+X86TargetMachine::~X86TargetMachine() {}
+
+const X86Subtarget *
+X86TargetMachine::getSubtargetImpl(const Function &F) const {
+ Attribute CPUAttr = F.getFnAttribute("target-cpu");
+ Attribute FSAttr = F.getFnAttribute("target-features");
+
+ std::string CPU = !CPUAttr.hasAttribute(Attribute::None)
+ ? CPUAttr.getValueAsString().str()
+ : TargetCPU;
+ std::string FS = !FSAttr.hasAttribute(Attribute::None)
+ ? FSAttr.getValueAsString().str()
+ : TargetFS;
+
+ // FIXME: This is related to the code below to reset the target options,
+ // we need to know whether or not the soft float flag is set on the
+ // function before we can generate a subtarget. We also need to use
+ // it as a key for the subtarget since that can be the only difference
+ // between two functions.
+ bool SoftFloat =
+ F.hasFnAttribute("use-soft-float") &&
+ F.getFnAttribute("use-soft-float").getValueAsString() == "true";
+ // If the soft float attribute is set on the function turn on the soft float
+ // subtarget feature.
+ if (SoftFloat)
+ FS += FS.empty() ? "+soft-float" : ",+soft-float";
+
+ auto &I = SubtargetMap[CPU + FS];
+ if (!I) {
+ // This needs to be done before we create a new subtarget since any
+ // creation will depend on the TM and the code generation flags on the
+ // function that reside in TargetOptions.
+ resetTargetOptions(F);
+ I = llvm::make_unique<X86Subtarget>(TargetTriple, CPU, FS, *this,
+ Options.StackAlignmentOverride);
+ }
+ return I.get();
}
//===----------------------------------------------------------------------===//
// Command line options for x86
//===----------------------------------------------------------------------===//
static cl::opt<bool>
-UseVZeroUpper("x86-use-vzeroupper",
+UseVZeroUpper("x86-use-vzeroupper", cl::Hidden,
cl::desc("Minimize AVX to SSE transition penalty"),
cl::init(true));
-// Temporary option to control early if-conversion for x86 while adding machine
-// models.
-static cl::opt<bool>
-X86EarlyIfConv("x86-early-ifcvt",
- cl::desc("Enable early if-conversion on X86"));
+//===----------------------------------------------------------------------===//
+// X86 TTI query.
+//===----------------------------------------------------------------------===//
+
+TargetIRAnalysis X86TargetMachine::getTargetIRAnalysis() {
+ return TargetIRAnalysis([this](const Function &F) {
+ return TargetTransformInfo(X86TTIImpl(this, F));
+ });
+}
+
//===----------------------------------------------------------------------===//
// Pass Pipeline Configuration
return getTM<X86TargetMachine>();
}
- const X86Subtarget &getX86Subtarget() const {
- return *getX86TargetMachine().getSubtargetImpl();
- }
-
- virtual bool addInstSelector();
- virtual bool addPreRegAlloc();
- virtual bool addPostRegAlloc();
- virtual bool addPreEmitPass();
+ void addIRPasses() override;
+ bool addInstSelector() override;
+ bool addILPOpts() override;
+ bool addPreISel() override;
+ void addPreRegAlloc() override;
+ void addPostRegAlloc() override;
+ void addPreEmitPass() override;
+ void addPreSched2() override;
};
} // namespace
TargetPassConfig *X86TargetMachine::createPassConfig(PassManagerBase &PM) {
- X86PassConfig *PC = new X86PassConfig(this, PM);
+ return new X86PassConfig(this, PM);
+}
- if (X86EarlyIfConv && Subtarget.hasCMov())
- PC->enablePass(&EarlyIfConverterID);
+void X86PassConfig::addIRPasses() {
+ addPass(createAtomicExpandPass(&getX86TargetMachine()));
- return PC;
+ TargetPassConfig::addIRPasses();
}
bool X86PassConfig::addInstSelector() {
addPass(createX86ISelDag(getX86TargetMachine(), getOptLevel()));
// For ELF, cleanup any local-dynamic TLS accesses.
- if (getX86Subtarget().isTargetELF() && getOptLevel() != CodeGenOpt::None)
+ if (TM->getTargetTriple().isOSBinFormatELF() &&
+ getOptLevel() != CodeGenOpt::None)
addPass(createCleanupLocalDynamicTLSPass());
- // For 32-bit, prepend instructions to set the "global base reg" for PIC.
- if (!getX86Subtarget().is64Bit())
- addPass(createGlobalBaseRegPass());
+ addPass(createX86GlobalBaseRegPass());
return false;
}
-bool X86PassConfig::addPreRegAlloc() {
- return false; // -print-machineinstr shouldn't print after this.
+bool X86PassConfig::addILPOpts() {
+ addPass(&EarlyIfConverterID);
+ if (EnableMachineCombinerPass)
+ addPass(&MachineCombinerID);
+ return true;
+}
+
+bool X86PassConfig::addPreISel() {
+ // Only add this pass for 32-bit x86 Windows.
+ const Triple &TT = TM->getTargetTriple();
+ if (TT.isOSWindows() && TT.getArch() == Triple::x86)
+ addPass(createX86WinEHStatePass());
+ return true;
}
-bool X86PassConfig::addPostRegAlloc() {
+void X86PassConfig::addPreRegAlloc() {
+ addPass(createX86CallFrameOptimization());
+}
+
+void X86PassConfig::addPostRegAlloc() {
addPass(createX86FloatingPointStackifierPass());
- return true; // -print-machineinstr should print after this.
}
-bool X86PassConfig::addPreEmitPass() {
- bool ShouldPrint = false;
- if (getOptLevel() != CodeGenOpt::None && getX86Subtarget().hasSSE2()) {
+void X86PassConfig::addPreSched2() { addPass(createX86ExpandPseudoPass()); }
+
+void X86PassConfig::addPreEmitPass() {
+ if (getOptLevel() != CodeGenOpt::None)
addPass(createExecutionDependencyFixPass(&X86::VR128RegClass));
- ShouldPrint = true;
- }
- if (getX86Subtarget().hasAVX() && UseVZeroUpper) {
+ if (UseVZeroUpper)
addPass(createX86IssueVZeroUpperPass());
- ShouldPrint = true;
- }
- return ShouldPrint;
-}
-
-bool X86TargetMachine::addCodeEmitter(PassManagerBase &PM,
- JITCodeEmitter &JCE) {
- PM.add(createX86JITCodeEmitterPass(*this, JCE));
-
- return false;
+ if (getOptLevel() != CodeGenOpt::None) {
+ addPass(createX86PadShortFunctions());
+ addPass(createX86FixupLEAs());
+ }
}