1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-25 05:52:53 +02:00
llvm-mirror/lib/Target/X86/X86TargetMachine.cpp
Bruno Cardoso Lopes 8024703a16 Introduce a pass to insert vzeroupper instructions to avoid AVX to
SSE transition penalty. The pass is enabled through the "x86-use-vzeroupper"
llc command line option. This is only the first step (very naive and
conservative one) to sketch out the idea, but proper DFA is coming next
to allow smarter decisions. Comments and ideas now and in further commits
will be very appreciated.

llvm-svn: 138317
2011-08-23 01:14:17 +00:00

154 lines
5.6 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/PassManager.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/FormattedStream.h"
#include "llvm/Target/TargetOptions.h"
#include "llvm/Target/TargetRegistry.h"
using namespace llvm;
extern "C" void LLVMInitializeX86Target() {
// Register the target.
RegisterTargetMachine<X86_32TargetMachine> X(TheX86_32Target);
RegisterTargetMachine<X86_64TargetMachine> Y(TheX86_64Target);
}
X86_32TargetMachine::X86_32TargetMachine(const Target &T, StringRef TT,
StringRef CPU, StringRef FS,
Reloc::Model RM, CodeModel::Model CM)
: X86TargetMachine(T, TT, CPU, FS, RM, CM, false),
DataLayout(getSubtargetImpl()->isTargetDarwin() ?
"e-p:32:32-f64:32:64-i64:32:64-f80:128:128-f128:128:128-n8:16:32" :
(getSubtargetImpl()->isTargetCygMing() ||
getSubtargetImpl()->isTargetWindows()) ?
"e-p:32:32-f64:64:64-i64:64:64-f80:32:32-f128:128:128-n8:16:32" :
"e-p:32:32-f64:32:64-i64:32:64-f80:32:32-f128:128:128-n8:16:32"),
InstrInfo(*this),
TSInfo(*this),
TLInfo(*this),
JITInfo(*this) {
}
X86_64TargetMachine::X86_64TargetMachine(const Target &T, StringRef TT,
StringRef CPU, StringRef FS,
Reloc::Model RM, CodeModel::Model CM)
: X86TargetMachine(T, TT, CPU, FS, RM, CM, true),
DataLayout("e-p:64:64-s:64-f64:64:64-i64:64:64-f80:128:128-f128:128:128-n8:16:32:64"),
InstrInfo(*this),
TSInfo(*this),
TLInfo(*this),
JITInfo(*this) {
}
/// X86TargetMachine ctor - Create an X86 target.
///
X86TargetMachine::X86TargetMachine(const Target &T, StringRef TT,
StringRef CPU, StringRef FS,
Reloc::Model RM, CodeModel::Model CM,
bool is64Bit)
: LLVMTargetMachine(T, TT, CPU, FS, RM, CM),
Subtarget(TT, CPU, FS, StackAlignmentOverride, is64Bit),
FrameLowering(*this, Subtarget),
ELFWriterInfo(is64Bit, true) {
// 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 (FloatABIType == FloatABI::Default)
FloatABIType = FloatABI::Hard;
}
//===----------------------------------------------------------------------===//
// Command line options for x86
//===----------------------------------------------------------------------===//
bool UseVZeroUpper;
static cl::opt<bool, true>
VZeroUpper("x86-use-vzeroupper",
cl::desc("Minimize AVX to SSE transition penalty"),
cl::location(UseVZeroUpper), cl::init(false));
//===----------------------------------------------------------------------===//
// Pass Pipeline Configuration
//===----------------------------------------------------------------------===//
bool X86TargetMachine::addInstSelector(PassManagerBase &PM,
CodeGenOpt::Level OptLevel) {
// Install an instruction selector.
PM.add(createX86ISelDag(*this, OptLevel));
// For 32-bit, prepend instructions to set the "global base reg" for PIC.
if (!Subtarget.is64Bit())
PM.add(createGlobalBaseRegPass());
return false;
}
bool X86TargetMachine::addPreRegAlloc(PassManagerBase &PM,
CodeGenOpt::Level OptLevel) {
PM.add(createX86MaxStackAlignmentHeuristicPass());
return false; // -print-machineinstr shouldn't print after this.
}
bool X86TargetMachine::addPostRegAlloc(PassManagerBase &PM,
CodeGenOpt::Level OptLevel) {
PM.add(createX86FloatingPointStackifierPass());
return true; // -print-machineinstr should print after this.
}
bool X86TargetMachine::addPreEmitPass(PassManagerBase &PM,
CodeGenOpt::Level OptLevel) {
if (OptLevel != CodeGenOpt::None && Subtarget.hasSSE2()) {
PM.add(createSSEDomainFixPass());
return true;
}
if (Subtarget.hasAVX() && UseVZeroUpper) {
PM.add(createX86IssueVZeroUpperPass());
return true;
}
return false;
}
bool X86TargetMachine::addCodeEmitter(PassManagerBase &PM,
CodeGenOpt::Level OptLevel,
JITCodeEmitter &JCE) {
PM.add(createX86JITCodeEmitterPass(*this, JCE));
return false;
}