1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 04:02:41 +01:00
llvm-mirror/lib/Target/PowerPC/PPCTargetMachine.cpp
Hal Finkel 8b6358ead9 [PowerPC] Initial support for the VSX instruction set
VSX is an ISA extension supported on the POWER7 and later cores that enhances
floating-point vector and scalar capabilities. Among other things, this adds
<2 x double> support and generally helps to reduce register pressure.

The interesting part of this ISA feature is the register configuration: there
are 64 new 128-bit vector registers, the 32 of which are super-registers of the
existing 32 scalar floating-point registers, and the second 32 of which overlap
with the 32 Altivec vector registers. This makes things like vector insertion
and extraction tricky: this can be free but only if we force a restriction to
the right register subclass when needed. A new "minipass" PPCVSXCopy takes care
of this (although it could do a more-optimal job of it; see the comment about
unnecessary copies below).

Please note that, currently, VSX is not enabled by default when targeting
anything because it is not yet ready for that.  The assembler and disassembler
are fully implemented and tested. However:

 - CodeGen support causes miscompiles; test-suite runtime failures:
      MultiSource/Benchmarks/FreeBench/distray/distray
      MultiSource/Benchmarks/McCat/08-main/main
      MultiSource/Benchmarks/Olden/voronoi/voronoi
      MultiSource/Benchmarks/mafft/pairlocalalign
      MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
      SingleSource/Benchmarks/CoyoteBench/almabench
      SingleSource/Benchmarks/Misc/matmul_f64_4x4

 - The lowering currently falls back to using Altivec instructions far more
   than it should. Worse, there are some things that are scalarized through the
   stack that shouldn't be.

 - A lot of unnecessary copies make it past the optimizers, and this needs to
   be fixed.

 - Many more regression tests are needed.

Normally, I'd fix these things prior to committing, but there are some
students and other contributors who would like to work this, and so it makes
sense to move this development process upstream where it can be subject to the
regular code-review procedures.

llvm-svn: 203768
2014-03-13 07:58:58 +00:00

203 lines
6.2 KiB
C++

//===-- PPCTargetMachine.cpp - Define TargetMachine for PowerPC -----------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// Top-level implementation for the PowerPC target.
//
//===----------------------------------------------------------------------===//
#include "PPCTargetMachine.h"
#include "PPC.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/MC/MCStreamer.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;
static cl::
opt<bool> DisableCTRLoops("disable-ppc-ctrloops", cl::Hidden,
cl::desc("Disable CTR loops for PPC"));
extern "C" void LLVMInitializePowerPCTarget() {
// Register the targets
RegisterTargetMachine<PPC32TargetMachine> A(ThePPC32Target);
RegisterTargetMachine<PPC64TargetMachine> B(ThePPC64Target);
RegisterTargetMachine<PPC64TargetMachine> C(ThePPC64LETarget);
}
/// Return the datalayout string of a subtarget.
static std::string getDataLayoutString(const PPCSubtarget &ST) {
const Triple &T = ST.getTargetTriple();
std::string Ret;
// Most PPC* platforms are big endian, PPC64LE is little endian.
if (ST.isLittleEndian())
Ret = "e";
else
Ret = "E";
Ret += DataLayout::getManglingComponent(T);
// PPC32 has 32 bit pointers. The PS3 (OS Lv2) is a PPC64 machine with 32 bit
// pointers.
if (!ST.isPPC64() || T.getOS() == Triple::Lv2)
Ret += "-p:32:32";
// Note, the alignment values for f64 and i64 on ppc64 in Darwin
// documentation are wrong; these are correct (i.e. "what gcc does").
if (ST.isPPC64() || ST.isSVR4ABI())
Ret += "-i64:64";
else
Ret += "-f64:32:64";
// PPC64 has 32 and 64 bit registers, PPC32 has only 32 bit ones.
if (ST.isPPC64())
Ret += "-n32:64";
else
Ret += "-n32";
return Ret;
}
PPCTargetMachine::PPCTargetMachine(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, is64Bit, OL),
DL(getDataLayoutString(Subtarget)), InstrInfo(*this),
FrameLowering(Subtarget), JITInfo(*this, is64Bit),
TLInfo(*this), TSInfo(*this),
InstrItins(Subtarget.getInstrItineraryData()) {
initAsmInfo();
}
void PPC32TargetMachine::anchor() { }
PPC32TargetMachine::PPC32TargetMachine(const Target &T, StringRef TT,
StringRef CPU, StringRef FS,
const TargetOptions &Options,
Reloc::Model RM, CodeModel::Model CM,
CodeGenOpt::Level OL)
: PPCTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL, false) {
}
void PPC64TargetMachine::anchor() { }
PPC64TargetMachine::PPC64TargetMachine(const Target &T, StringRef TT,
StringRef CPU, StringRef FS,
const TargetOptions &Options,
Reloc::Model RM, CodeModel::Model CM,
CodeGenOpt::Level OL)
: PPCTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL, true) {
}
//===----------------------------------------------------------------------===//
// Pass Pipeline Configuration
//===----------------------------------------------------------------------===//
namespace {
/// PPC Code Generator Pass Configuration Options.
class PPCPassConfig : public TargetPassConfig {
public:
PPCPassConfig(PPCTargetMachine *TM, PassManagerBase &PM)
: TargetPassConfig(TM, PM) {}
PPCTargetMachine &getPPCTargetMachine() const {
return getTM<PPCTargetMachine>();
}
const PPCSubtarget &getPPCSubtarget() const {
return *getPPCTargetMachine().getSubtargetImpl();
}
virtual bool addPreISel();
virtual bool addILPOpts();
virtual bool addInstSelector();
virtual bool addPreSched2();
virtual bool addPreEmitPass();
};
} // namespace
TargetPassConfig *PPCTargetMachine::createPassConfig(PassManagerBase &PM) {
return new PPCPassConfig(this, PM);
}
bool PPCPassConfig::addPreISel() {
if (!DisableCTRLoops && getOptLevel() != CodeGenOpt::None)
addPass(createPPCCTRLoops(getPPCTargetMachine()));
return false;
}
bool PPCPassConfig::addILPOpts() {
if (getPPCSubtarget().hasISEL()) {
addPass(&EarlyIfConverterID);
return true;
}
return false;
}
bool PPCPassConfig::addInstSelector() {
// Install an instruction selector.
addPass(createPPCISelDag(getPPCTargetMachine()));
#ifndef NDEBUG
if (!DisableCTRLoops && getOptLevel() != CodeGenOpt::None)
addPass(createPPCCTRLoopsVerify());
#endif
addPass(createPPCVSXCopyPass());
return false;
}
bool PPCPassConfig::addPreSched2() {
if (getOptLevel() != CodeGenOpt::None)
addPass(&IfConverterID);
return true;
}
bool PPCPassConfig::addPreEmitPass() {
if (getOptLevel() != CodeGenOpt::None)
addPass(createPPCEarlyReturnPass());
// Must run branch selection immediately preceding the asm printer.
addPass(createPPCBranchSelectionPass());
return false;
}
bool PPCTargetMachine::addCodeEmitter(PassManagerBase &PM,
JITCodeEmitter &JCE) {
// Inform the subtarget that we are in JIT mode. FIXME: does this break macho
// writing?
Subtarget.SetJITMode();
// Machine code emitter pass for PowerPC.
PM.add(createPPCJITCodeEmitterPass(*this, JCE));
return false;
}
void PPCTargetMachine::addAnalysisPasses(PassManagerBase &PM) {
// Add first the target-independent BasicTTI pass, then our PPC pass. This
// allows the PPC pass to delegate to the target independent layer when
// appropriate.
PM.add(createBasicTargetTransformInfoPass(this));
PM.add(createPPCTargetTransformInfoPass(this));
}