X86RegisterInfo::X86RegisterInfo(const Triple &TT)
: X86GenRegisterInfo((TT.isArch64Bit() ? X86::RIP : X86::EIP),
X86_MC::getDwarfRegFlavour(TT, false),
X86_MC::getDwarfRegFlavour(TT, true),
(TT.isArch64Bit() ? X86::RIP : X86::EIP)) {
X86_MC::InitLLVM2SEHRegisterMapping(this);
// Cache some information.
Is64Bit = TT.isArch64Bit();
IsWin64 = Is64Bit && TT.isOSWindows();
// Use a callee-saved register as the base pointer. These registers must
// not conflict with any ABI requirements. For example, in 32-bit mode PIC
// requires GOT in the EBX register before function calls via PLT GOT pointer.
if (Is64Bit) {
SlotSize = 8;
// This matches the simplified 32-bit pointer code in the data layout
// computation.
// FIXME: Should use the data layout?
bool Use64BitReg = TT.getEnvironment() != Triple::GNUX32;
StackPtr = Use64BitReg ? X86::RSP : X86::ESP;
FramePtr = Use64BitReg ? X86::RBP : X86::EBP;
BasePtr = Use64BitReg ? X86::RBX : X86::EBX;
} else {
SlotSize = 4;
StackPtr = X86::ESP;
FramePtr = X86::EBP;
BasePtr = X86::ESI;
}
}
WebAssemblyMCAsmInfo::WebAssemblyMCAsmInfo(const Triple &T) {
PointerSize = CalleeSaveStackSlotSize = T.isArch64Bit();
// TODO: What should MaxInstLength be?
PrivateGlobalPrefix = "";
PrivateLabelPrefix = "";
UseDataRegionDirectives = true;
Data8bitsDirective = "\t.int8\t";
Data16bitsDirective = "\t.int16\t";
Data32bitsDirective = "\t.int32\t";
Data64bitsDirective = "\t.int64\t";
AlignmentIsInBytes = false;
COMMDirectiveAlignmentIsInBytes = false;
LCOMMDirectiveAlignmentType = LCOMM::Log2Alignment;
HasDotTypeDotSizeDirective = false;
HasSingleParameterDotFile = false;
SupportsDebugInformation = true;
// For now, WebAssembly does not support exceptions.
ExceptionsType = ExceptionHandling::None;
// TODO: UseIntegratedAssembler?
}
/// Create an WebAssembly architecture model.
///
WebAssemblyTargetMachine::WebAssemblyTargetMachine(
const Target &T, const Triple &TT, StringRef CPU, StringRef FS,
const TargetOptions &Options, Optional<Reloc::Model> RM,
Optional<CodeModel::Model> CM, CodeGenOpt::Level OL, bool JIT)
: LLVMTargetMachine(T,
TT.isArch64Bit() ? "e-m:e-p:64:64-i64:64-n32:64-S128"
: "e-m:e-p:32:32-i64:64-n32:64-S128",
TT, CPU, FS, Options, getEffectiveRelocModel(RM),
CM ? *CM : CodeModel::Large, OL),
TLOF(TT.isOSBinFormatELF() ?
static_cast<TargetLoweringObjectFile*>(
new WebAssemblyTargetObjectFileELF()) :
static_cast<TargetLoweringObjectFile*>(
new WebAssemblyTargetObjectFile())) {
// WebAssembly type-checks instructions, but a noreturn function with a return
// type that doesn't match the context will cause a check failure. So we lower
// LLVM 'unreachable' to ISD::TRAP and then lower that to WebAssembly's
// 'unreachable' instructions which is meant for that case.
this->Options.TrapUnreachable = true;
// WebAssembly treats each function as an independent unit. Force
// -ffunction-sections, effectively, so that we can emit them independently.
if (!TT.isOSBinFormatELF()) {
this->Options.FunctionSections = true;
this->Options.DataSections = true;
this->Options.UniqueSectionNames = true;
}
initAsmInfo();
// Note that we don't use setRequiresStructuredCFG(true). It disables
// optimizations than we're ok with, and want, such as critical edge
// splitting and tail merging.
}
/// Create an WebAssembly architecture model.
///
WebAssemblyTargetMachine::WebAssemblyTargetMachine(
const Target &T, const Triple &TT, StringRef CPU, StringRef FS,
const TargetOptions &Options, Optional<Reloc::Model> RM,
Optional<CodeModel::Model> CM, CodeGenOpt::Level OL, bool JIT)
: LLVMTargetMachine(T,
TT.isArch64Bit() ? "e-m:e-p:64:64-i64:64-n32:64-S128"
: "e-m:e-p:32:32-i64:64-n32:64-S128",
TT, CPU, FS, Options, getEffectiveRelocModel(RM),
getEffectiveCodeModel(CM, CodeModel::Large), OL),
TLOF(new WebAssemblyTargetObjectFile()) {
// WebAssembly type-checks instructions, but a noreturn function with a return
// type that doesn't match the context will cause a check failure. So we lower
// LLVM 'unreachable' to ISD::TRAP and then lower that to WebAssembly's
// 'unreachable' instructions which is meant for that case.
this->Options.TrapUnreachable = true;
// WebAssembly treats each function as an independent unit. Force
// -ffunction-sections, effectively, so that we can emit them independently.
this->Options.FunctionSections = true;
this->Options.DataSections = true;
this->Options.UniqueSectionNames = true;
initAsmInfo();
// Create a subtarget using the unmodified target machine features to
// initialize the used feature set with explicitly enabled features.
getSubtargetImpl(getTargetCPU(), getTargetFeatureString());
// Note that we don't use setRequiresStructuredCFG(true). It disables
// optimizations than we're ok with, and want, such as critical edge
// splitting and tail merging.
}
RISCVMCAsmInfo::RISCVMCAsmInfo(const Triple &TT) {
CodePointerSize = CalleeSaveStackSlotSize = TT.isArch64Bit() ? 8 : 4;
CommentString = "#";
AlignmentIsInBytes = false;
SupportsDebugInformation = true;
Data16bitsDirective = "\t.half\t";
Data32bitsDirective = "\t.word\t";
}
static std::string computeDataLayout(const Triple &TT) {
if (TT.isArch64Bit()) {
return "e-m:e-i64:64-n32:64-S128";
} else {
assert(TT.isArch32Bit() && "only RV32 and RV64 are currently supported");
return "e-m:e-p:32:32-i64:64-n32-S128";
}
}
ABI computeTargetABI(const Triple &TT, FeatureBitset FeatureBits,
StringRef ABIName) {
auto TargetABI = StringSwitch<ABI>(ABIName)
.Case("ilp32", ABI_ILP32)
.Case("ilp32f", ABI_ILP32F)
.Case("ilp32d", ABI_ILP32D)
.Case("ilp32e", ABI_ILP32E)
.Case("lp64", ABI_LP64)
.Case("lp64f", ABI_LP64F)
.Case("lp64d", ABI_LP64D)
.Default(ABI_Unknown);
bool IsRV64 = TT.isArch64Bit();
bool IsRV32E = FeatureBits[RISCV::FeatureRV32E];
if (!ABIName.empty() && TargetABI == ABI_Unknown) {
errs()
<< "'" << ABIName
<< "' is not a recognized ABI for this target (ignoring target-abi)\n";
} else if (ABIName.startswith("ilp32") && IsRV64) {
errs() << "32-bit ABIs are not supported for 64-bit targets (ignoring "
"target-abi)\n";
TargetABI = ABI_Unknown;
} else if (ABIName.startswith("lp64") && !IsRV64) {
errs() << "64-bit ABIs are not supported for 32-bit targets (ignoring "
"target-abi)\n";
TargetABI = ABI_Unknown;
} else if (ABIName.endswith("f") && !FeatureBits[RISCV::FeatureStdExtF]) {
errs() << "Hard-float 'f' ABI can't be used for a target that "
"doesn't support the F instruction set extension (ignoring "
"target-abi)\n";
TargetABI = ABI_Unknown;
} else if (ABIName.endswith("d") && !FeatureBits[RISCV::FeatureStdExtD]) {
errs() << "Hard-float 'd' ABI can't be used for a target that "
"doesn't support the D instruction set extension (ignoring "
"target-abi)\n";
TargetABI = ABI_Unknown;
} else if (IsRV32E && TargetABI != ABI_ILP32E && TargetABI != ABI_Unknown) {
errs()
<< "Only the ilp32e ABI is supported for RV32E (ignoring target-abi)\n";
TargetABI = ABI_Unknown;
}
if (TargetABI != ABI_Unknown)
return TargetABI;
// For now, default to the ilp32/ilp32e/lp64 ABI if no explicit ABI is given
// or an invalid/unrecognised string is given. In the future, it might be
// worth changing this to default to ilp32f/lp64f and ilp32d/lp64d when
// hardware support for floating point is present.
if (IsRV32E)
return ABI_ILP32E;
if (IsRV64)
return ABI_LP64;
return ABI_ILP32;
}
/// Create an WebAssembly architecture model.
///
WebAssemblyTargetMachine::WebAssemblyTargetMachine(
const Target &T, const Triple &TT, StringRef CPU, StringRef FS,
const TargetOptions &Options, Reloc::Model RM, CodeModel::Model CM,
CodeGenOpt::Level OL)
: LLVMTargetMachine(T, TT.isArch64Bit()
? "e-p:64:64-i64:64-v128:8:128-n32:64-S128"
: "e-p:32:32-i64:64-v128:8:128-n32:64-S128",
TT, CPU, FS, Options, RM, CM, OL),
TLOF(make_unique<WebAssemblyTargetObjectFile>()) {
initAsmInfo();
// We need a reducible CFG, so disable some optimizations which tend to
// introduce irreducibility.
setRequiresStructuredCFG(true);
}
/// Create an WebAssembly architecture model.
///
WebAssemblyTargetMachine::WebAssemblyTargetMachine(
const Target &T, const Triple &TT, StringRef CPU, StringRef FS,
const TargetOptions &Options, Reloc::Model RM, CodeModel::Model CM,
CodeGenOpt::Level OL)
: LLVMTargetMachine(T, TT.isArch64Bit() ? "e-p:64:64-i64:64-n32:64-S128"
: "e-p:32:32-i64:64-n32:64-S128",
TT, CPU, FS, Options, RM, CM, OL),
TLOF(make_unique<WebAssemblyTargetObjectFile>()) {
// WebAssembly type-checks expressions, but a noreturn function with a return
// type that doesn't match the context will cause a check failure. So we lower
// LLVM 'unreachable' to ISD::TRAP and then lower that to WebAssembly's
// 'unreachable' expression which is meant for that case.
this->Options.TrapUnreachable = true;
initAsmInfo();
// We need a reducible CFG, so disable some optimizations which tend to
// introduce irreducibility.
setRequiresStructuredCFG(true);
}
/// Create an WebAssembly architecture model.
///
WebAssemblyTargetMachine::WebAssemblyTargetMachine(
const Target &T, const Triple &TT, StringRef CPU, StringRef FS,
const TargetOptions &Options, Reloc::Model RM, CodeModel::Model CM,
CodeGenOpt::Level OL)
: LLVMTargetMachine(T,
TT.isArch64Bit() ? "e-m:e-p:64:64-i64:64-n32:64-S128"
: "e-m:e-p:32:32-i64:64-n32:64-S128",
TT, CPU, FS, Options, RM, CM, OL),
TLOF(make_unique<WebAssemblyTargetObjectFile>()) {
// WebAssembly type-checks expressions, but a noreturn function with a return
// type that doesn't match the context will cause a check failure. So we lower
// LLVM 'unreachable' to ISD::TRAP and then lower that to WebAssembly's
// 'unreachable' expression which is meant for that case.
this->Options.TrapUnreachable = true;
initAsmInfo();
// Note that we don't use setRequiresStructuredCFG(true). It disables
// optimizations than we're ok with, and want, such as critical edge
// splitting and tail merging.
}
static std::string computeDataLayout(const Triple &TT) {
// X86 is little endian
std::string Ret = "e";
Ret += DataLayout::getManglingComponent(TT);
// X86 and x32 have 32 bit pointers.
if ((TT.isArch64Bit() &&
(TT.getEnvironment() == Triple::GNUX32 || TT.isOSNaCl())) ||
!TT.isArch64Bit())
Ret += "-p:32:32";
// Some ABIs align 64 bit integers and doubles to 64 bits, others to 32.
if (TT.isArch64Bit() || TT.isOSWindows() || TT.isOSNaCl())
Ret += "-i64:64";
else if (TT.isOSIAMCU())
Ret += "-i64:32-f64:32";
else
Ret += "-f64:32:64";
// Some ABIs align long double to 128 bits, others to 32.
if (TT.isOSNaCl() || TT.isOSIAMCU())
; // No f80
else if (TT.isArch64Bit() || TT.isOSDarwin())
Ret += "-f80:128";
else
Ret += "-f80:32";
if (TT.isOSIAMCU())
Ret += "-f128:32";
// The registers can hold 8, 16, 32 or, in x86-64, 64 bits.
if (TT.isArch64Bit())
Ret += "-n8:16:32:64";
else
Ret += "-n8:16:32";
// The stack is aligned to 32 bits on some ABIs and 128 bits on others.
if ((!TT.isArch64Bit() && TT.isOSWindows()) || TT.isOSIAMCU())
Ret += "-a:0:32-S32";
else
Ret += "-S128";
return Ret;
}
bool PPCCTRLoops::convertToCTRLoop(Loop *L) {
bool MadeChange = false;
Triple TT = Triple(L->getHeader()->getParent()->getParent()->
getTargetTriple());
if (!TT.isArch32Bit() && !TT.isArch64Bit())
return MadeChange; // Unknown arch. type.
// Process nested loops first.
for (Loop::iterator I = L->begin(), E = L->end(); I != E; ++I) {
MadeChange |= convertToCTRLoop(*I);
}
// If a nested loop has been converted, then we can't convert this loop.
if (MadeChange)
return MadeChange;
#ifndef NDEBUG
// Stop trying after reaching the limit (if any).
int Limit = CTRLoopLimit;
if (Limit >= 0) {
if (Counter >= CTRLoopLimit)
return false;
Counter++;
}
#endif
// We don't want to spill/restore the counter register, and so we don't
// want to use the counter register if the loop contains calls.
for (Loop::block_iterator I = L->block_begin(), IE = L->block_end();
I != IE; ++I)
if (mightUseCTR(TT, *I))
return MadeChange;
SmallVector<BasicBlock*, 4> ExitingBlocks;
L->getExitingBlocks(ExitingBlocks);
BasicBlock *CountedExitBlock = 0;
const SCEV *ExitCount = 0;
BranchInst *CountedExitBranch = 0;
for (SmallVectorImpl<BasicBlock *>::iterator I = ExitingBlocks.begin(),
IE = ExitingBlocks.end(); I != IE; ++I) {
const SCEV *EC = SE->getExitCount(L, *I);
DEBUG(dbgs() << "Exit Count for " << *L << " from block " <<
(*I)->getName() << ": " << *EC << "\n");
if (isa<SCEVCouldNotCompute>(EC))
continue;
if (const SCEVConstant *ConstEC = dyn_cast<SCEVConstant>(EC)) {
if (ConstEC->getValue()->isZero())
continue;
} else if (!SE->isLoopInvariant(EC, L))
continue;
if (SE->getTypeSizeInBits(EC->getType()) > (TT.isArch64Bit() ? 64 : 32))
continue;
// We now have a loop-invariant count of loop iterations (which is not the
// constant zero) for which we know that this loop will not exit via this
// exisiting block.
// We need to make sure that this block will run on every loop iteration.
// For this to be true, we must dominate all blocks with backedges. Such
// blocks are in-loop predecessors to the header block.
bool NotAlways = false;
for (pred_iterator PI = pred_begin(L->getHeader()),
PIE = pred_end(L->getHeader()); PI != PIE; ++PI) {
if (!L->contains(*PI))
continue;
if (!DT->dominates(*I, *PI)) {
NotAlways = true;
break;
}
}
if (NotAlways)
continue;
// Make sure this blocks ends with a conditional branch.
Instruction *TI = (*I)->getTerminator();
if (!TI)
continue;
if (BranchInst *BI = dyn_cast<BranchInst>(TI)) {
if (!BI->isConditional())
continue;
CountedExitBranch = BI;
} else
continue;
// Note that this block may not be the loop latch block, even if the loop
// has a latch block.
CountedExitBlock = *I;
ExitCount = EC;
break;
}
if (!CountedExitBlock)
return MadeChange;
BasicBlock *Preheader = L->getLoopPreheader();
// If we don't have a preheader, then insert one. If we already have a
// preheader, then we can use it (except if the preheader contains a use of
// the CTR register because some such uses might be reordered by the
// selection DAG after the mtctr instruction).
if (!Preheader || mightUseCTR(TT, Preheader))
Preheader = InsertPreheaderForLoop(L, this);
if (!Preheader)
return MadeChange;
DEBUG(dbgs() << "Preheader for exit count: " << Preheader->getName() << "\n");
// Insert the count into the preheader and replace the condition used by the
// selected branch.
MadeChange = true;
SCEVExpander SCEVE(*SE, "loopcnt");
LLVMContext &C = SE->getContext();
Type *CountType = TT.isArch64Bit() ? Type::getInt64Ty(C) :
Type::getInt32Ty(C);
if (!ExitCount->getType()->isPointerTy() &&
ExitCount->getType() != CountType)
ExitCount = SE->getZeroExtendExpr(ExitCount, CountType);
ExitCount = SE->getAddExpr(ExitCount,
SE->getConstant(CountType, 1));
Value *ECValue = SCEVE.expandCodeFor(ExitCount, CountType,
Preheader->getTerminator());
IRBuilder<> CountBuilder(Preheader->getTerminator());
Module *M = Preheader->getParent()->getParent();
Value *MTCTRFunc = Intrinsic::getDeclaration(M, Intrinsic::ppc_mtctr,
CountType);
CountBuilder.CreateCall(MTCTRFunc, ECValue);
IRBuilder<> CondBuilder(CountedExitBranch);
Value *DecFunc =
Intrinsic::getDeclaration(M, Intrinsic::ppc_is_decremented_ctr_nonzero);
Value *NewCond = CondBuilder.CreateCall(DecFunc);
Value *OldCond = CountedExitBranch->getCondition();
CountedExitBranch->setCondition(NewCond);
// The false branch must exit the loop.
if (!L->contains(CountedExitBranch->getSuccessor(0)))
CountedExitBranch->swapSuccessors();
// The old condition may be dead now, and may have even created a dead PHI
// (the original induction variable).
RecursivelyDeleteTriviallyDeadInstructions(OldCond);
DeleteDeadPHIs(CountedExitBlock);
++NumCTRLoops;
return MadeChange;
}
void validate(const Triple &TT, const FeatureBitset &FeatureBits) {
if (TT.isArch64Bit() && FeatureBits[RISCV::FeatureRV32E])
report_fatal_error("RV32E can't be enabled for an RV64 target");
}
RISCVMCAsmInfo::RISCVMCAsmInfo(const Triple &TT) {
PointerSize = CalleeSaveStackSlotSize = TT.isArch64Bit() ? 8 : 4;
CommentString = "#";
AlignmentIsInBytes = false;
SupportsDebugInformation = true;
}
static ELFKind getBitcodeELFKind(const Triple &T) {
if (T.isLittleEndian())
return T.isArch64Bit() ? ELF64LEKind : ELF32LEKind;
return T.isArch64Bit() ? ELF64BEKind : ELF32BEKind;
}