1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-25 05:52:53 +02:00
llvm-mirror/lib/Target/PowerPC/PPCTargetMachine.cpp
Hal Finkel d380588a20 [PowerPC] Add extra r2 read deps on @toc@l relocations
If some commits are happy, and some commits are sad, this is a sad commit. It
is sad because it restricts instruction scheduling to work around a binutils
linker bug, and moreover, one that may never be fixed. On 2012-05-21, GCC was
updated not to produce code triggering this bug, and now we'll do the same...

When resolving an address using the ELF ABI TOC pointer, two relocations are
generally required: one for the high part and one for the low part. Only
the high part generally explicitly depends on r2 (the TOC pointer). And, so,
we might produce code like this:

.Ltmp526:
        addis 3, 2, .LC12@toc@ha
.Ltmp1628:
        std 2, 40(1)
        ld 5, 0(27)
        ld 2, 8(27)
        ld 11, 16(27)
        ld 3, .LC12@toc@l(3)
        rldicl 4, 4, 0, 32
        mtctr 5
        bctrl
        ld 2, 40(1)

And there is nothing wrong with this code, as such, but there is a linker bug
in binutils (https://sourceware.org/bugzilla/show_bug.cgi?id=18414) that will
misoptimize this code sequence to this:
        nop
        std     r2,40(r1)
        ld      r5,0(r27)
        ld      r2,8(r27)
        ld      r11,16(r27)
        ld      r3,-32472(r2)
        clrldi  r4,r4,32
        mtctr   r5
        bctrl
        ld      r2,40(r1)
because the linker does not know (and does not check) that the value in r2
changed in between the instruction using the .LC12@toc@ha (TOC-relative)
relocation and the instruction using the .LC12@toc@l(3) relocation.
Because it finds these instructions using the relocations (and not by
scanning the instructions), it has been asserted that there is no good way
to detect the change of r2 in between. As a result, this bug may never be
fixed (i.e. it may become part of the definition of the ABI). GCC was
updated to add extra dependencies on r2 to instructions using the @toc@l
relocations to avoid this problem, and we'll do the same here.

This is done as a separate pass because:
 1. These extra r2 dependencies are not really properties of the
    instructions, but rather due to a linker bug, and maybe one day we'll be
    able to get rid of them when targeting linkers without this bug (and,
    thus, keeping the logic centralized here will make that
    straightforward).
 2. There are ISel-level peephole optimizations that propagate the @toc@l
    relocations to some user instructions, and so the exta dependencies do
    not apply only to a fixed set of instructions (without undesirable
    definition replication).

The test case was reduced with the help of bugpoint, with minimal cleaning. I'm
looking forward to our upcoming MI serialization support, and with that, much
better tests can be created.

llvm-svn: 237556
2015-05-18 06:25:59 +00:00

354 lines
12 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/IR/LegacyPassManager.h"
#include "llvm/MC/MCStreamer.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> DisableVSXSwapRemoval("disable-ppc-vsx-swap-removal", cl::Hidden,
cl::desc("Disable VSX Swap Removal for PPC"));
static cl::opt<bool>
EnableGEPOpt("ppc-gep-opt", cl::Hidden,
cl::desc("Enable optimizations on complex GEPs"),
cl::init(true));
static cl::opt<bool>
EnablePrefetch("enable-ppc-prefetching",
cl::desc("disable software prefetching on PPC"),
cl::init(false), cl::Hidden);
static cl::opt<bool>
EnableExtraTOCRegDeps("enable-ppc-extra-toc-reg-deps",
cl::desc("Add extra TOC register dependencies"),
cl::init(true), cl::Hidden);
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>();
}
static PPCTargetMachine::PPCABI computeTargetABI(const Triple &TT,
const TargetOptions &Options) {
if (Options.MCOptions.getABIName().startswith("elfv1"))
return PPCTargetMachine::PPC_ABI_ELFv1;
else if (Options.MCOptions.getABIName().startswith("elfv2"))
return PPCTargetMachine::PPC_ABI_ELFv2;
assert(Options.MCOptions.getABIName().empty() &&
"Unknown target-abi option!");
if (!TT.isMacOSX()) {
switch (TT.getArch()) {
case Triple::ppc64le:
return PPCTargetMachine::PPC_ABI_ELFv2;
case Triple::ppc64:
return PPCTargetMachine::PPC_ABI_ELFv1;
default:
// Fallthrough.
;
}
}
return PPCTargetMachine::PPC_ABI_UNKNOWN;
}
// 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, getDataLayoutString(Triple(TT)), TT, CPU,
computeFSAdditions(FS, OL, TT), Options, RM, CM, OL),
TLOF(createTLOF(Triple(getTargetTriple()))),
TargetABI(computeTargetABI(Triple(TT), Options)) {
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 {
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;
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,
// FIXME: It would be good to have the subtarget additions here
// not necessary. Anything that turns them on/off (overrides) ends
// up being put at the end of the feature string, but the defaults
// shouldn't require adding them. Fixing this means pulling Feature64Bit
// out of most of the target cpus in the .td file and making it set only
// as part of initialization via the TargetTriple.
computeFSAdditions(FS, getOptLevel(), getTargetTriple()), *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 addMachineSSAOptimization() 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()));
// For the BG/Q (or if explicitly requested), add explicit data prefetch
// intrinsics.
bool UsePrefetching =
Triple(TM->getTargetTriple()).getVendor() == Triple::BGQ &&
getOptLevel() != CodeGenOpt::None;
if (EnablePrefetch.getNumOccurrences() > 0)
UsePrefetching = EnablePrefetch;
if (UsePrefetching)
addPass(createPPCLoopDataPrefetchPass());
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::addMachineSSAOptimization() {
TargetPassConfig::addMachineSSAOptimization();
// For little endian, remove where possible the vector swap instructions
// introduced at code generation to normalize vector element order.
if (Triple(TM->getTargetTriple()).getArch() == Triple::ppc64le &&
!DisableVSXSwapRemoval)
addPass(createPPCVSXSwapRemovalPass());
}
void PPCPassConfig::addPreRegAlloc() {
initializePPCVSXFMAMutatePass(*PassRegistry::getPassRegistry());
insertPass(VSXFMAMutateEarly ? &RegisterCoalescerID : &MachineSchedulerID,
&PPCVSXFMAMutateID);
if (getPPCTargetMachine().getRelocationModel() == Reloc::PIC_)
addPass(createPPCTLSDynamicCallPass());
if (EnableExtraTOCRegDeps)
addPass(createPPCTOCRegDepsPass());
}
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)); });
}