llvm-6502/lib/Target/X86/X86TargetMachine.cpp
Nadav Rotem 5d1f5c1737 Revert revision 171524. Original message:
URL: http://llvm.org/viewvc/llvm-project?rev=171524&view=rev
Log:
The current Intel Atom microarchitecture has a feature whereby when a function
returns early then it is slightly faster to execute a sequence of NOP
instructions to wait until the return address is ready,
as opposed to simply stalling on the ret instruction
until the return address is ready.

When compiling for X86 Atom only, this patch will run a pass, called
"X86PadShortFunction" which will add NOP instructions where less than four
cycles elapse between function entry and return.

It includes tests.

Patch by Andy Zhang.




git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171603 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-05 05:42:48 +00:00

203 lines
7.0 KiB
C++

//===-- X86TargetMachine.cpp - Define TargetMachine for the X86 -----------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the X86 specific subclass of TargetMachine.
//
//===----------------------------------------------------------------------===//
#include "X86TargetMachine.h"
#include "X86.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/PassManager.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/FormattedStream.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Target/TargetOptions.h"
using namespace llvm;
extern "C" void LLVMInitializeX86Target() {
// Register the target.
RegisterTargetMachine<X86_32TargetMachine> X(TheX86_32Target);
RegisterTargetMachine<X86_64TargetMachine> Y(TheX86_64Target);
}
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) {
}
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){
}
/// X86TargetMachine ctor - Create an X86 target.
///
X86TargetMachine::X86TargetMachine(const Target &T, StringRef 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);
}
// default to hard float ABI
if (Options.FloatABIType == FloatABI::Default)
this->Options.FloatABIType = FloatABI::Hard;
}
//===----------------------------------------------------------------------===//
// Command line options for x86
//===----------------------------------------------------------------------===//
static cl::opt<bool>
UseVZeroUpper("x86-use-vzeroupper",
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"));
//===----------------------------------------------------------------------===//
// Pass Pipeline Configuration
//===----------------------------------------------------------------------===//
namespace {
/// X86 Code Generator Pass Configuration Options.
class X86PassConfig : public TargetPassConfig {
public:
X86PassConfig(X86TargetMachine *TM, PassManagerBase &PM)
: TargetPassConfig(TM, PM) {}
X86TargetMachine &getX86TargetMachine() const {
return getTM<X86TargetMachine>();
}
const X86Subtarget &getX86Subtarget() const {
return *getX86TargetMachine().getSubtargetImpl();
}
virtual bool addInstSelector();
virtual bool addPreRegAlloc();
virtual bool addPostRegAlloc();
virtual bool addPreEmitPass();
};
} // namespace
TargetPassConfig *X86TargetMachine::createPassConfig(PassManagerBase &PM) {
X86PassConfig *PC = new X86PassConfig(this, PM);
if (X86EarlyIfConv && Subtarget.hasCMov())
PC->enablePass(&EarlyIfConverterID);
return PC;
}
bool X86PassConfig::addInstSelector() {
// Install an instruction selector.
addPass(createX86ISelDag(getX86TargetMachine(), getOptLevel()));
// For ELF, cleanup any local-dynamic TLS accesses.
if (getX86Subtarget().isTargetELF() && getOptLevel() != CodeGenOpt::None)
addPass(createCleanupLocalDynamicTLSPass());
// For 32-bit, prepend instructions to set the "global base reg" for PIC.
if (!getX86Subtarget().is64Bit())
addPass(createGlobalBaseRegPass());
return false;
}
bool X86PassConfig::addPreRegAlloc() {
return false; // -print-machineinstr shouldn't print after this.
}
bool X86PassConfig::addPostRegAlloc() {
addPass(createX86FloatingPointStackifierPass());
return true; // -print-machineinstr should print after this.
}
bool X86PassConfig::addPreEmitPass() {
bool ShouldPrint = false;
if (getOptLevel() != CodeGenOpt::None && getX86Subtarget().hasSSE2()) {
addPass(createExecutionDependencyFixPass(&X86::VR128RegClass));
ShouldPrint = true;
}
if (getX86Subtarget().hasAVX() && UseVZeroUpper) {
addPass(createX86IssueVZeroUpperPass());
ShouldPrint = true;
}
return ShouldPrint;
}
bool X86TargetMachine::addCodeEmitter(PassManagerBase &PM,
JITCodeEmitter &JCE) {
PM.add(createX86JITCodeEmitterPass(*this, JCE));
return false;
}