SDValue
AMDGPUTargetLowering::LowerSIGN_EXTEND_INREG(SDValue Op, SelectionDAG &DAG) const
{
SDValue Data = Op.getOperand(0);
VTSDNode *BaseType = cast<VTSDNode>(Op.getOperand(1));
DebugLoc DL = Op.getDebugLoc();
EVT DVT = Data.getValueType();
EVT BVT = BaseType->getVT();
unsigned baseBits = BVT.getScalarType().getSizeInBits();
unsigned srcBits = DVT.isSimple() ? DVT.getScalarType().getSizeInBits() : 1;
unsigned shiftBits = srcBits - baseBits;
if (srcBits < 32) {
// If the op is less than 32 bits, then it needs to extend to 32bits
// so it can properly keep the upper bits valid.
EVT IVT = genIntType(32, DVT.isVector() ? DVT.getVectorNumElements() : 1);
Data = DAG.getNode(ISD::ZERO_EXTEND, DL, IVT, Data);
shiftBits = 32 - baseBits;
DVT = IVT;
}
SDValue Shift = DAG.getConstant(shiftBits, DVT);
// Shift left by 'Shift' bits.
Data = DAG.getNode(ISD::SHL, DL, DVT, Data, Shift);
// Signed shift Right by 'Shift' bits.
Data = DAG.getNode(ISD::SRA, DL, DVT, Data, Shift);
if (srcBits < 32) {
// Once the sign extension is done, the op needs to be converted to
// its original type.
Data = DAG.getSExtOrTrunc(Data, DL, Op.getOperand(0).getValueType());
}
return Data;
}
bool
AMDGPUTargetLowering::ShouldShrinkFPConstant(EVT VT) const {
if (VT.getScalarType().getSimpleVT().SimpleTy == MVT::f32
|| VT.getScalarType().getSimpleVT().SimpleTy == MVT::f64) {
return false;
} else {
return true;
}
}
// The backend supports 32 and 64 bit floating point immediates
bool
AMDGPUTargetLowering::isFPImmLegal(const APFloat &Imm, EVT VT) const {
if (VT.getScalarType().getSimpleVT().SimpleTy == MVT::f32
|| VT.getScalarType().getSimpleVT().SimpleTy == MVT::f64) {
return true;
} else {
return false;
}
}
SDValue
AMDGPUTargetLowering::LowerSDIV(SDValue Op, SelectionDAG &DAG) const {
EVT OVT = Op.getValueType();
SDValue DST;
if (OVT.getScalarType() == MVT::i64) {
DST = LowerSDIV64(Op, DAG);
} else if (OVT.getScalarType() == MVT::i32) {
DST = LowerSDIV32(Op, DAG);
} else if (OVT.getScalarType() == MVT::i16
|| OVT.getScalarType() == MVT::i8) {
DST = LowerSDIV24(Op, DAG);
} else {
DST = SDValue(Op.getNode(), 0);
}
return DST;
}
SDValue
AMDGPUTargetLowering::LowerSDIV24(SDValue Op, SelectionDAG &DAG) const
{
DebugLoc DL = Op.getDebugLoc();
EVT OVT = Op.getValueType();
SDValue LHS = Op.getOperand(0);
SDValue RHS = Op.getOperand(1);
MVT INTTY;
MVT FLTTY;
if (!OVT.isVector()) {
INTTY = MVT::i32;
FLTTY = MVT::f32;
} else if (OVT.getVectorNumElements() == 2) {
INTTY = MVT::v2i32;
FLTTY = MVT::v2f32;
} else if (OVT.getVectorNumElements() == 4) {
INTTY = MVT::v4i32;
FLTTY = MVT::v4f32;
}
unsigned bitsize = OVT.getScalarType().getSizeInBits();
// char|short jq = ia ^ ib;
SDValue jq = DAG.getNode(ISD::XOR, DL, OVT, LHS, RHS);
// jq = jq >> (bitsize - 2)
jq = DAG.getNode(ISD::SRA, DL, OVT, jq, DAG.getConstant(bitsize - 2, OVT));
// jq = jq | 0x1
jq = DAG.getNode(ISD::OR, DL, OVT, jq, DAG.getConstant(1, OVT));
// jq = (int)jq
jq = DAG.getSExtOrTrunc(jq, DL, INTTY);
// int ia = (int)LHS;
SDValue ia = DAG.getSExtOrTrunc(LHS, DL, INTTY);
// int ib, (int)RHS;
SDValue ib = DAG.getSExtOrTrunc(RHS, DL, INTTY);
// float fa = (float)ia;
SDValue fa = DAG.getNode(ISD::SINT_TO_FP, DL, FLTTY, ia);
// float fb = (float)ib;
SDValue fb = DAG.getNode(ISD::SINT_TO_FP, DL, FLTTY, ib);
// float fq = native_divide(fa, fb);
SDValue fq = DAG.getNode(AMDGPUISD::DIV_INF, DL, FLTTY, fa, fb);
// fq = trunc(fq);
fq = DAG.getNode(ISD::FTRUNC, DL, FLTTY, fq);
// float fqneg = -fq;
SDValue fqneg = DAG.getNode(ISD::FNEG, DL, FLTTY, fq);
// float fr = mad(fqneg, fb, fa);
SDValue fr = DAG.getNode(AMDGPUISD::MAD, DL, FLTTY, fqneg, fb, fa);
// int iq = (int)fq;
SDValue iq = DAG.getNode(ISD::FP_TO_SINT, DL, INTTY, fq);
// fr = fabs(fr);
fr = DAG.getNode(ISD::FABS, DL, FLTTY, fr);
// fb = fabs(fb);
fb = DAG.getNode(ISD::FABS, DL, FLTTY, fb);
// int cv = fr >= fb;
SDValue cv;
if (INTTY == MVT::i32) {
cv = DAG.getSetCC(DL, INTTY, fr, fb, ISD::SETOGE);
} else {
cv = DAG.getSetCC(DL, INTTY, fr, fb, ISD::SETOGE);
}
// jq = (cv ? jq : 0);
jq = DAG.getNode(ISD::SELECT, DL, OVT, cv, jq,
DAG.getConstant(0, OVT));
// dst = iq + jq;
iq = DAG.getSExtOrTrunc(iq, DL, OVT);
iq = DAG.getNode(ISD::ADD, DL, OVT, iq, jq);
return iq;
}
bool PPCCTRLoops::mightUseCTR(BasicBlock *BB) {
for (BasicBlock::iterator J = BB->begin(), JE = BB->end();
J != JE; ++J) {
if (CallInst *CI = dyn_cast<CallInst>(J)) {
// Inline ASM is okay, unless it clobbers the ctr register.
if (InlineAsm *IA = dyn_cast<InlineAsm>(CI->getCalledValue())) {
if (asmClobbersCTR(IA))
return true;
continue;
}
if (Function *F = CI->getCalledFunction()) {
// Most intrinsics don't become function calls, but some might.
// sin, cos, exp and log are always calls.
unsigned Opcode = 0;
if (F->getIntrinsicID() != Intrinsic::not_intrinsic) {
switch (F->getIntrinsicID()) {
default: continue;
// If we have a call to ppc_is_decremented_ctr_nonzero, or ppc_mtctr
// we're definitely using CTR.
case Intrinsic::ppc_is_decremented_ctr_nonzero:
case Intrinsic::ppc_mtctr:
return true;
// VisualStudio defines setjmp as _setjmp
#if defined(_MSC_VER) && defined(setjmp) && \
!defined(setjmp_undefined_for_msvc)
# pragma push_macro("setjmp")
# undef setjmp
# define setjmp_undefined_for_msvc
#endif
case Intrinsic::setjmp:
#if defined(_MSC_VER) && defined(setjmp_undefined_for_msvc)
// let's return it to _setjmp state
# pragma pop_macro("setjmp")
# undef setjmp_undefined_for_msvc
#endif
case Intrinsic::longjmp:
// Exclude eh_sjlj_setjmp; we don't need to exclude eh_sjlj_longjmp
// because, although it does clobber the counter register, the
// control can't then return to inside the loop unless there is also
// an eh_sjlj_setjmp.
case Intrinsic::eh_sjlj_setjmp:
case Intrinsic::memcpy:
case Intrinsic::memmove:
case Intrinsic::memset:
case Intrinsic::powi:
case Intrinsic::log:
case Intrinsic::log2:
case Intrinsic::log10:
case Intrinsic::exp:
case Intrinsic::exp2:
case Intrinsic::pow:
case Intrinsic::sin:
case Intrinsic::cos:
return true;
case Intrinsic::copysign:
if (CI->getArgOperand(0)->getType()->getScalarType()->
isPPC_FP128Ty())
return true;
else
continue; // ISD::FCOPYSIGN is never a library call.
case Intrinsic::sqrt: Opcode = ISD::FSQRT; break;
case Intrinsic::floor: Opcode = ISD::FFLOOR; break;
case Intrinsic::ceil: Opcode = ISD::FCEIL; break;
case Intrinsic::trunc: Opcode = ISD::FTRUNC; break;
case Intrinsic::rint: Opcode = ISD::FRINT; break;
case Intrinsic::nearbyint: Opcode = ISD::FNEARBYINT; break;
case Intrinsic::round: Opcode = ISD::FROUND; break;
case Intrinsic::minnum: Opcode = ISD::FMINNUM; break;
case Intrinsic::maxnum: Opcode = ISD::FMAXNUM; break;
case Intrinsic::umul_with_overflow: Opcode = ISD::UMULO; break;
case Intrinsic::smul_with_overflow: Opcode = ISD::SMULO; break;
}
}
// PowerPC does not use [US]DIVREM or other library calls for
// operations on regular types which are not otherwise library calls
// (i.e. soft float or atomics). If adapting for targets that do,
// additional care is required here.
LibFunc Func;
if (!F->hasLocalLinkage() && F->hasName() && LibInfo &&
LibInfo->getLibFunc(F->getName(), Func) &&
LibInfo->hasOptimizedCodeGen(Func)) {
// Non-read-only functions are never treated as intrinsics.
if (!CI->onlyReadsMemory())
return true;
// Conversion happens only for FP calls.
if (!CI->getArgOperand(0)->getType()->isFloatingPointTy())
return true;
switch (Func) {
default: return true;
case LibFunc_copysign:
case LibFunc_copysignf:
continue; // ISD::FCOPYSIGN is never a library call.
case LibFunc_copysignl:
return true;
case LibFunc_fabs:
case LibFunc_fabsf:
case LibFunc_fabsl:
continue; // ISD::FABS is never a library call.
case LibFunc_sqrt:
case LibFunc_sqrtf:
case LibFunc_sqrtl:
Opcode = ISD::FSQRT; break;
case LibFunc_floor:
case LibFunc_floorf:
case LibFunc_floorl:
Opcode = ISD::FFLOOR; break;
case LibFunc_nearbyint:
case LibFunc_nearbyintf:
case LibFunc_nearbyintl:
Opcode = ISD::FNEARBYINT; break;
case LibFunc_ceil:
case LibFunc_ceilf:
case LibFunc_ceill:
Opcode = ISD::FCEIL; break;
case LibFunc_rint:
case LibFunc_rintf:
case LibFunc_rintl:
Opcode = ISD::FRINT; break;
case LibFunc_round:
case LibFunc_roundf:
case LibFunc_roundl:
Opcode = ISD::FROUND; break;
case LibFunc_trunc:
case LibFunc_truncf:
case LibFunc_truncl:
Opcode = ISD::FTRUNC; break;
case LibFunc_fmin:
case LibFunc_fminf:
case LibFunc_fminl:
Opcode = ISD::FMINNUM; break;
case LibFunc_fmax:
case LibFunc_fmaxf:
case LibFunc_fmaxl:
Opcode = ISD::FMAXNUM; break;
}
}
if (Opcode) {
EVT EVTy =
TLI->getValueType(*DL, CI->getArgOperand(0)->getType(), true);
if (EVTy == MVT::Other)
return true;
if (TLI->isOperationLegalOrCustom(Opcode, EVTy))
continue;
else if (EVTy.isVector() &&
TLI->isOperationLegalOrCustom(Opcode, EVTy.getScalarType()))
continue;
return true;
}
}
return true;
} else if (isa<BinaryOperator>(J) &&
J->getType()->getScalarType()->isPPC_FP128Ty()) {
// Most operations on ppc_f128 values become calls.
return true;
} else if (isa<UIToFPInst>(J) || isa<SIToFPInst>(J) ||
isa<FPToUIInst>(J) || isa<FPToSIInst>(J)) {
CastInst *CI = cast<CastInst>(J);
if (CI->getSrcTy()->getScalarType()->isPPC_FP128Ty() ||
CI->getDestTy()->getScalarType()->isPPC_FP128Ty() ||
isLargeIntegerTy(!TM->isPPC64(), CI->getSrcTy()->getScalarType()) ||
isLargeIntegerTy(!TM->isPPC64(), CI->getDestTy()->getScalarType()))
return true;
} else if (isLargeIntegerTy(!TM->isPPC64(),
J->getType()->getScalarType()) &&
(J->getOpcode() == Instruction::UDiv ||
J->getOpcode() == Instruction::SDiv ||
J->getOpcode() == Instruction::URem ||
J->getOpcode() == Instruction::SRem)) {
return true;
} else if (!TM->isPPC64() &&
isLargeIntegerTy(false, J->getType()->getScalarType()) &&
(J->getOpcode() == Instruction::Shl ||
J->getOpcode() == Instruction::AShr ||
J->getOpcode() == Instruction::LShr)) {
// Only on PPC32, for 128-bit integers (specifically not 64-bit
// integers), these might be runtime calls.
return true;
} else if (isa<IndirectBrInst>(J) || isa<InvokeInst>(J)) {
// On PowerPC, indirect jumps use the counter register.
return true;
} else if (SwitchInst *SI = dyn_cast<SwitchInst>(J)) {
if (SI->getNumCases() + 1 >= (unsigned)TLI->getMinimumJumpTableEntries())
return true;
}
// FREM is always a call.
if (J->getOpcode() == Instruction::FRem)
return true;
if (STI->useSoftFloat()) {
switch(J->getOpcode()) {
case Instruction::FAdd:
case Instruction::FSub:
case Instruction::FMul:
case Instruction::FDiv:
case Instruction::FPTrunc:
case Instruction::FPExt:
case Instruction::FPToUI:
case Instruction::FPToSI:
case Instruction::UIToFP:
case Instruction::SIToFP:
case Instruction::FCmp:
return true;
}
}
for (Value *Operand : J->operands())
if (memAddrUsesCTR(*TM, Operand))
return true;
}
return false;
}
