llvm-6502/lib/Target/PowerPC/PPCTargetMachine.cpp
Hal Finkel b8a6712c27 [PowerPC] Prepare loops for pre-increment loads/stores
PowerPC supports pre-increment load/store instructions (except for Altivec/VSX
vector load/stores). Using these on embedded cores can be very important, but
most loops are not naturally set up to use them. We can often change that,
however, by placing loops into a non-canonical form. Generically, this means
transforming loops like this:

  for (int i = 0; i < n; ++i)
    array[i] = c;

to look like this:

  T *p = array[-1];
  for (int i = 0; i < n; ++i)
    *++p = c;

the key point is that addresses accessed are pulled into dedicated PHIs and
"pre-decremented" in the loop preheader. This allows the use of pre-increment
load/store instructions without loop peeling.

A target-specific late IR-level pass (running post-LSR), PPCLoopPreIncPrep, is
introduced to perform this transformation. I've used this code out-of-tree for
generating code for the PPC A2 for over a year. Somewhat to my surprise,
running the test suite + externals on a P7 with this transformation enabled
showed no performance regressions, and one speedup:

External/SPEC/CINT2006/483.xalancbmk/483.xalancbmk
	-2.32514% +/- 1.03736%

So I'm going to enable it on everything for now. I was surprised by this
because, on the POWER cores, these pre-increment load/store instructions are
cracked (and, thus, harder to schedule effectively). But seeing no regressions,
and feeling that it is generally easier to split instructions apart late than
it is to combine them late, this might be the better approach regardless.

In the future, we might want to integrate this functionality into LSR (but
currently LSR does not create new PHI nodes, so (for that and other reasons)
significant work would need to be done).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228328 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-05 18:43:00 +00:00

288 lines
9.4 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 "PPCTargetObjectFile.h"
#include "PPCTargetTransformInfo.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/IR/Function.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"
#include "llvm/Transforms/Scalar.h"
using namespace llvm;
static cl::
opt<bool> DisableCTRLoops("disable-ppc-ctrloops", cl::Hidden,
cl::desc("Disable CTR loops for PPC"));
static cl::
opt<bool> DisablePreIncPrep("disable-ppc-preinc-prep", cl::Hidden,
cl::desc("Disable PPC loop preinc prep"));
static cl::opt<bool>
VSXFMAMutateEarly("schedule-ppc-vsx-fma-mutation-early",
cl::Hidden, cl::desc("Schedule VSX FMA instruction mutation early"));
static cl::opt<bool>
EnableGEPOpt("ppc-gep-opt", cl::Hidden,
cl::desc("Enable optimizations on complex GEPs"),
cl::init(true));
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 Triple &T) {
bool is64Bit = T.getArch() == Triple::ppc64 || T.getArch() == Triple::ppc64le;
std::string Ret;
// Most PPC* platforms are big endian, PPC64LE is little endian.
if (T.getArch() == Triple::ppc64le)
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 (!is64Bit || 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 (is64Bit || !T.isOSDarwin())
Ret += "-i64:64";
else
Ret += "-f64:32:64";
// PPC64 has 32 and 64 bit registers, PPC32 has only 32 bit ones.
if (is64Bit)
Ret += "-n32:64";
else
Ret += "-n32";
return Ret;
}
static std::string computeFSAdditions(StringRef FS, CodeGenOpt::Level OL, StringRef TT) {
std::string FullFS = FS;
Triple TargetTriple(TT);
// Make sure 64-bit features are available when CPUname is generic
if (TargetTriple.getArch() == Triple::ppc64 ||
TargetTriple.getArch() == Triple::ppc64le) {
if (!FullFS.empty())
FullFS = "+64bit," + FullFS;
else
FullFS = "+64bit";
}
if (OL >= CodeGenOpt::Default) {
if (!FullFS.empty())
FullFS = "+crbits," + FullFS;
else
FullFS = "+crbits";
}
if (OL != CodeGenOpt::None) {
if (!FullFS.empty())
FullFS = "+invariant-function-descriptors," + FullFS;
else
FullFS = "+invariant-function-descriptors";
}
return FullFS;
}
static std::unique_ptr<TargetLoweringObjectFile> createTLOF(const Triple &TT) {
// If it isn't a Mach-O file then it's going to be a linux ELF
// object file.
if (TT.isOSDarwin())
return make_unique<TargetLoweringObjectFileMachO>();
return make_unique<PPC64LinuxTargetObjectFile>();
}
// The FeatureString here is a little subtle. We are modifying the feature string
// with what are (currently) non-function specific overrides as it goes into the
// LLVMTargetMachine constructor and then using the stored value in the
// Subtarget constructor below it.
PPCTargetMachine::PPCTargetMachine(const Target &T, StringRef TT, StringRef CPU,
StringRef FS, const TargetOptions &Options,
Reloc::Model RM, CodeModel::Model CM,
CodeGenOpt::Level OL)
: LLVMTargetMachine(T, TT, CPU, computeFSAdditions(FS, OL, TT), Options, RM,
CM, OL),
TLOF(createTLOF(Triple(getTargetTriple()))),
DL(getDataLayoutString(Triple(TT))), Subtarget(TT, CPU, TargetFS, *this) {
initAsmInfo();
}
PPCTargetMachine::~PPCTargetMachine() {}
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) {
}
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) {
}
const PPCSubtarget *
PPCTargetMachine::getSubtargetImpl(const Function &F) const {
AttributeSet FnAttrs = F.getAttributes();
Attribute CPUAttr =
FnAttrs.getAttribute(AttributeSet::FunctionIndex, "target-cpu");
Attribute FSAttr =
FnAttrs.getAttribute(AttributeSet::FunctionIndex, "target-features");
std::string CPU = !CPUAttr.hasAttribute(Attribute::None)
? CPUAttr.getValueAsString().str()
: TargetCPU;
std::string FS = !FSAttr.hasAttribute(Attribute::None)
? FSAttr.getValueAsString().str()
: TargetFS;
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<PPCSubtarget>(TargetTriple, CPU, FS, *this);
}
return I.get();
}
//===----------------------------------------------------------------------===//
// 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>();
}
void addIRPasses() override;
bool addPreISel() override;
bool addILPOpts() override;
bool addInstSelector() override;
void addPreRegAlloc() override;
void addPreSched2() override;
void addPreEmitPass() override;
};
} // namespace
TargetPassConfig *PPCTargetMachine::createPassConfig(PassManagerBase &PM) {
return new PPCPassConfig(this, PM);
}
void PPCPassConfig::addIRPasses() {
addPass(createAtomicExpandPass(&getPPCTargetMachine()));
if (TM->getOptLevel() == CodeGenOpt::Aggressive && EnableGEPOpt) {
// Call SeparateConstOffsetFromGEP pass to extract constants within indices
// and lower a GEP with multiple indices to either arithmetic operations or
// multiple GEPs with single index.
addPass(createSeparateConstOffsetFromGEPPass(TM, true));
// Call EarlyCSE pass to find and remove subexpressions in the lowered
// result.
addPass(createEarlyCSEPass());
// Do loop invariant code motion in case part of the lowered result is
// invariant.
addPass(createLICMPass());
}
TargetPassConfig::addIRPasses();
}
bool PPCPassConfig::addPreISel() {
if (!DisablePreIncPrep && getOptLevel() != CodeGenOpt::None)
addPass(createPPCLoopPreIncPrepPass(getPPCTargetMachine()));
if (!DisableCTRLoops && getOptLevel() != CodeGenOpt::None)
addPass(createPPCCTRLoops(getPPCTargetMachine()));
return false;
}
bool PPCPassConfig::addILPOpts() {
addPass(&EarlyIfConverterID);
return true;
}
bool PPCPassConfig::addInstSelector() {
// Install an instruction selector.
addPass(createPPCISelDag(getPPCTargetMachine()));
#ifndef NDEBUG
if (!DisableCTRLoops && getOptLevel() != CodeGenOpt::None)
addPass(createPPCCTRLoopsVerify());
#endif
addPass(createPPCVSXCopyPass());
return false;
}
void PPCPassConfig::addPreRegAlloc() {
initializePPCVSXFMAMutatePass(*PassRegistry::getPassRegistry());
insertPass(VSXFMAMutateEarly ? &RegisterCoalescerID : &MachineSchedulerID,
&PPCVSXFMAMutateID);
addPass(createPPCTLSDynamicCallPass());
}
void PPCPassConfig::addPreSched2() {
if (getOptLevel() != CodeGenOpt::None)
addPass(&IfConverterID);
}
void PPCPassConfig::addPreEmitPass() {
if (getOptLevel() != CodeGenOpt::None)
addPass(createPPCEarlyReturnPass(), false);
// Must run branch selection immediately preceding the asm printer.
addPass(createPPCBranchSelectionPass(), false);
}
TargetIRAnalysis PPCTargetMachine::getTargetIRAnalysis() {
return TargetIRAnalysis(
[this](Function &F) { return TargetTransformInfo(PPCTTIImpl(this, F)); });
}