maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/lib/Target/R600/AMDGPUISelDAGToDAG.cpp

552 lines
19 KiB
C++
Raw Blame History

//===-- AMDILISelDAGToDAG.cpp - A dag to dag inst selector for AMDIL ------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//==-----------------------------------------------------------------------===//
//
/// \file
/// \brief Defines an instruction selector for the AMDGPU target.
//
//===----------------------------------------------------------------------===//
#include "AMDGPUInstrInfo.h"
#include "AMDGPUISelLowering.h" // For AMDGPUISD
#include "AMDGPURegisterInfo.h"
#include "R600InstrInfo.h"
#include "SIISelLowering.h"
#include "llvm/ADT/ValueMap.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/PseudoSourceValue.h"
#include "llvm/CodeGen/SelectionDAG.h"
#include "llvm/CodeGen/SelectionDAGISel.h"
#include "llvm/Support/Compiler.h"
#include <list>
#include <queue>
using namespace llvm;
//===----------------------------------------------------------------------===//
// Instruction Selector Implementation
//===----------------------------------------------------------------------===//
namespace {
/// AMDGPU specific code to select AMDGPU machine instructions for
/// SelectionDAG operations.
class AMDGPUDAGToDAGISel : public SelectionDAGISel {
// Subtarget - Keep a pointer to the AMDGPU Subtarget around so that we can
// make the right decision when generating code for different targets.
const AMDGPUSubtarget &Subtarget;
public:
AMDGPUDAGToDAGISel(TargetMachine &TM);
virtual ~AMDGPUDAGToDAGISel();
SDNode *Select(SDNode *N);
virtual const char *getPassName() const;
virtual void PostprocessISelDAG();
private:
inline SDValue getSmallIPtrImm(unsigned Imm);
bool FoldOperand(SDValue &Src, SDValue &Sel, SDValue &Neg, SDValue &Abs,
const R600InstrInfo *TII);
bool FoldOperands(unsigned, const R600InstrInfo *, std::vector<SDValue> &);
bool FoldDotOperands(unsigned, const R600InstrInfo *, std::vector<SDValue> &);
// Complex pattern selectors
bool SelectADDRParam(SDValue Addr, SDValue& R1, SDValue& R2);
bool SelectADDR(SDValue N, SDValue &R1, SDValue &R2);
bool SelectADDR64(SDValue N, SDValue &R1, SDValue &R2);
SDValue SimplifyI24(SDValue &Op);
bool SelectI24(SDValue Addr, SDValue &Op);
bool SelectU24(SDValue Addr, SDValue &Op);
static bool checkType(const Value *ptr, unsigned int addrspace);
static bool isGlobalStore(const StoreSDNode *N);
static bool isPrivateStore(const StoreSDNode *N);
static bool isLocalStore(const StoreSDNode *N);
static bool isRegionStore(const StoreSDNode *N);
bool isCPLoad(const LoadSDNode *N) const;
bool isConstantLoad(const LoadSDNode *N, int cbID) const;
bool isGlobalLoad(const LoadSDNode *N) const;
bool isParamLoad(const LoadSDNode *N) const;
bool isPrivateLoad(const LoadSDNode *N) const;
bool isLocalLoad(const LoadSDNode *N) const;
bool isRegionLoad(const LoadSDNode *N) const;
const TargetRegisterClass *getOperandRegClass(SDNode *N, unsigned OpNo) const;
bool SelectGlobalValueConstantOffset(SDValue Addr, SDValue& IntPtr);
bool SelectGlobalValueVariableOffset(SDValue Addr,
SDValue &BaseReg, SDValue& Offset);
bool SelectADDRVTX_READ(SDValue Addr, SDValue &Base, SDValue &Offset);
bool SelectADDRIndirect(SDValue Addr, SDValue &Base, SDValue &Offset);
// Include the pieces autogenerated from the target description.
#include "AMDGPUGenDAGISel.inc"
};
} // end anonymous namespace
/// \brief This pass converts a legalized DAG into a AMDGPU-specific
// DAG, ready for instruction scheduling.
FunctionPass *llvm::createAMDGPUISelDag(TargetMachine &TM
) {
return new AMDGPUDAGToDAGISel(TM);
}
AMDGPUDAGToDAGISel::AMDGPUDAGToDAGISel(TargetMachine &TM)
: SelectionDAGISel(TM), Subtarget(TM.getSubtarget<AMDGPUSubtarget>()) {
}
AMDGPUDAGToDAGISel::~AMDGPUDAGToDAGISel() {
}
/// \brief Determine the register class for \p OpNo
/// \returns The register class of the virtual register that will be used for
/// the given operand number \OpNo or NULL if the register class cannot be
/// determined.
const TargetRegisterClass *AMDGPUDAGToDAGISel::getOperandRegClass(SDNode *N,
unsigned OpNo) const {
if (!N->isMachineOpcode()) {
return NULL;
}
switch (N->getMachineOpcode()) {
default: {
const MCInstrDesc &Desc = TM.getInstrInfo()->get(N->getMachineOpcode());
unsigned OpIdx = Desc.getNumDefs() + OpNo;
if (OpIdx >= Desc.getNumOperands())
return NULL;
int RegClass = Desc.OpInfo[OpIdx].RegClass;
if (RegClass == -1) {
return NULL;
}
return TM.getRegisterInfo()->getRegClass(RegClass);
}
case AMDGPU::REG_SEQUENCE: {
const TargetRegisterClass *SuperRC = TM.getRegisterInfo()->getRegClass(
cast<ConstantSDNode>(N->getOperand(0))->getZExtValue());
unsigned SubRegIdx =
dyn_cast<ConstantSDNode>(N->getOperand(OpNo + 1))->getZExtValue();
return TM.getRegisterInfo()->getSubClassWithSubReg(SuperRC, SubRegIdx);
}
}
}
SDValue AMDGPUDAGToDAGISel::getSmallIPtrImm(unsigned int Imm) {
return CurDAG->getTargetConstant(Imm, MVT::i32);
}
bool AMDGPUDAGToDAGISel::SelectADDRParam(
SDValue Addr, SDValue& R1, SDValue& R2) {
if (Addr.getOpcode() == ISD::FrameIndex) {
if (FrameIndexSDNode *FIN = dyn_cast<FrameIndexSDNode>(Addr)) {
R1 = CurDAG->getTargetFrameIndex(FIN->getIndex(), MVT::i32);
R2 = CurDAG->getTargetConstant(0, MVT::i32);
} else {
R1 = Addr;
R2 = CurDAG->getTargetConstant(0, MVT::i32);
}
} else if (Addr.getOpcode() == ISD::ADD) {
R1 = Addr.getOperand(0);
R2 = Addr.getOperand(1);
} else {
R1 = Addr;
R2 = CurDAG->getTargetConstant(0, MVT::i32);
}
return true;
}
bool AMDGPUDAGToDAGISel::SelectADDR(SDValue Addr, SDValue& R1, SDValue& R2) {
if (Addr.getOpcode() == ISD::TargetExternalSymbol ||
Addr.getOpcode() == ISD::TargetGlobalAddress) {
return false;
}
return SelectADDRParam(Addr, R1, R2);
}
bool AMDGPUDAGToDAGISel::SelectADDR64(SDValue Addr, SDValue& R1, SDValue& R2) {
if (Addr.getOpcode() == ISD::TargetExternalSymbol ||
Addr.getOpcode() == ISD::TargetGlobalAddress) {
return false;
}
if (Addr.getOpcode() == ISD::FrameIndex) {
if (FrameIndexSDNode *FIN = dyn_cast<FrameIndexSDNode>(Addr)) {
R1 = CurDAG->getTargetFrameIndex(FIN->getIndex(), MVT::i64);
R2 = CurDAG->getTargetConstant(0, MVT::i64);
} else {
R1 = Addr;
R2 = CurDAG->getTargetConstant(0, MVT::i64);
}
} else if (Addr.getOpcode() == ISD::ADD) {
R1 = Addr.getOperand(0);
R2 = Addr.getOperand(1);
} else {
R1 = Addr;
R2 = CurDAG->getTargetConstant(0, MVT::i64);
}
return true;
}
SDNode *AMDGPUDAGToDAGISel::Select(SDNode *N) {
unsigned int Opc = N->getOpcode();
if (N->isMachineOpcode()) {
N->setNodeId(-1);
return NULL; // Already selected.
}
switch (Opc) {
default: break;
case ISD::BUILD_VECTOR: {
unsigned RegClassID;
const AMDGPUSubtarget &ST = TM.getSubtarget<AMDGPUSubtarget>();
const AMDGPURegisterInfo *TRI =
static_cast<const AMDGPURegisterInfo*>(TM.getRegisterInfo());
const SIRegisterInfo *SIRI =
static_cast<const SIRegisterInfo*>(TM.getRegisterInfo());
EVT VT = N->getValueType(0);
unsigned NumVectorElts = VT.getVectorNumElements();
assert(VT.getVectorElementType().bitsEq(MVT::i32));
if (ST.getGeneration() >= AMDGPUSubtarget::SOUTHERN_ISLANDS) {
bool UseVReg = true;
for (SDNode::use_iterator U = N->use_begin(), E = SDNode::use_end();
U != E; ++U) {
if (!U->isMachineOpcode()) {
continue;
}
const TargetRegisterClass *RC = getOperandRegClass(*U, U.getOperandNo());
if (!RC) {
continue;
}
if (SIRI->isSGPRClass(RC)) {
UseVReg = false;
}
}
switch(NumVectorElts) {
case 1: RegClassID = UseVReg ? AMDGPU::VReg_32RegClassID :
AMDGPU::SReg_32RegClassID;
break;
case 2: RegClassID = UseVReg ? AMDGPU::VReg_64RegClassID :
AMDGPU::SReg_64RegClassID;
break;
case 4: RegClassID = UseVReg ? AMDGPU::VReg_128RegClassID :
AMDGPU::SReg_128RegClassID;
break;
case 8: RegClassID = UseVReg ? AMDGPU::VReg_256RegClassID :
AMDGPU::SReg_256RegClassID;
break;
case 16: RegClassID = UseVReg ? AMDGPU::VReg_512RegClassID :
AMDGPU::SReg_512RegClassID;
break;
default: llvm_unreachable("Do not know how to lower this BUILD_VECTOR");
}
} else {
// BUILD_VECTOR was lowered into an IMPLICIT_DEF + 4 INSERT_SUBREG
// that adds a 128 bits reg copy when going through TwoAddressInstructions
// pass. We want to avoid 128 bits copies as much as possible because they
// can't be bundled by our scheduler.
switch(NumVectorElts) {
case 2: RegClassID = AMDGPU::R600_Reg64RegClassID; break;
case 4: RegClassID = AMDGPU::R600_Reg128RegClassID; break;
default: llvm_unreachable("Do not know how to lower this BUILD_VECTOR");
}
}
SDValue RegClass = CurDAG->getTargetConstant(RegClassID, MVT::i32);
if (NumVectorElts == 1) {
return CurDAG->SelectNodeTo(N, AMDGPU::COPY_TO_REGCLASS,
VT.getVectorElementType(),
N->getOperand(0), RegClass);
}
assert(NumVectorElts <= 16 && "Vectors with more than 16 elements not "
"supported yet");
// 16 = Max Num Vector Elements
// 2 = 2 REG_SEQUENCE operands per element (value, subreg index)
// 1 = Vector Register Class
SDValue RegSeqArgs[16 * 2 + 1];
RegSeqArgs[0] = CurDAG->getTargetConstant(RegClassID, MVT::i32);
bool IsRegSeq = true;
for (unsigned i = 0; i < N->getNumOperands(); i++) {
// XXX: Why is this here?
if (dyn_cast<RegisterSDNode>(N->getOperand(i))) {
IsRegSeq = false;
break;
}
RegSeqArgs[1 + (2 * i)] = N->getOperand(i);
RegSeqArgs[1 + (2 * i) + 1] =
CurDAG->getTargetConstant(TRI->getSubRegFromChannel(i), MVT::i32);
}
if (!IsRegSeq)
break;
return CurDAG->SelectNodeTo(N, AMDGPU::REG_SEQUENCE, N->getVTList(),
RegSeqArgs, 2 * N->getNumOperands() + 1);
}
case ISD::BUILD_PAIR: {
SDValue RC, SubReg0, SubReg1;
const AMDGPUSubtarget &ST = TM.getSubtarget<AMDGPUSubtarget>();
if (ST.getGeneration() <= AMDGPUSubtarget::NORTHERN_ISLANDS) {
break;
}
if (N->getValueType(0) == MVT::i128) {
RC = CurDAG->getTargetConstant(AMDGPU::SReg_128RegClassID, MVT::i32);
SubReg0 = CurDAG->getTargetConstant(AMDGPU::sub0_sub1, MVT::i32);
SubReg1 = CurDAG->getTargetConstant(AMDGPU::sub2_sub3, MVT::i32);
} else if (N->getValueType(0) == MVT::i64) {
RC = CurDAG->getTargetConstant(AMDGPU::VSrc_64RegClassID, MVT::i32);
SubReg0 = CurDAG->getTargetConstant(AMDGPU::sub0, MVT::i32);
SubReg1 = CurDAG->getTargetConstant(AMDGPU::sub1, MVT::i32);
} else {
llvm_unreachable("Unhandled value type for BUILD_PAIR");
}
const SDValue Ops[] = { RC, N->getOperand(0), SubReg0,
N->getOperand(1), SubReg1 };
return CurDAG->getMachineNode(TargetOpcode::REG_SEQUENCE,
SDLoc(N), N->getValueType(0), Ops);
}
}
return SelectCode(N);
}
bool AMDGPUDAGToDAGISel::checkType(const Value *ptr, unsigned int addrspace) {
if (!ptr) {
return false;
}
Type *ptrType = ptr->getType();
return dyn_cast<PointerType>(ptrType)->getAddressSpace() == addrspace;
}
bool AMDGPUDAGToDAGISel::isGlobalStore(const StoreSDNode *N) {
return checkType(N->getSrcValue(), AMDGPUAS::GLOBAL_ADDRESS);
}
bool AMDGPUDAGToDAGISel::isPrivateStore(const StoreSDNode *N) {
return (!checkType(N->getSrcValue(), AMDGPUAS::LOCAL_ADDRESS)
&& !checkType(N->getSrcValue(), AMDGPUAS::GLOBAL_ADDRESS)
&& !checkType(N->getSrcValue(), AMDGPUAS::REGION_ADDRESS));
}
bool AMDGPUDAGToDAGISel::isLocalStore(const StoreSDNode *N) {
return checkType(N->getSrcValue(), AMDGPUAS::LOCAL_ADDRESS);
}
bool AMDGPUDAGToDAGISel::isRegionStore(const StoreSDNode *N) {
return checkType(N->getSrcValue(), AMDGPUAS::REGION_ADDRESS);
}
bool AMDGPUDAGToDAGISel::isConstantLoad(const LoadSDNode *N, int CbId) const {
if (CbId == -1) {
return checkType(N->getSrcValue(), AMDGPUAS::CONSTANT_ADDRESS);
}
return checkType(N->getSrcValue(), AMDGPUAS::CONSTANT_BUFFER_0 + CbId);
}
bool AMDGPUDAGToDAGISel::isGlobalLoad(const LoadSDNode *N) const {
if (N->getAddressSpace() == AMDGPUAS::CONSTANT_ADDRESS) {
const AMDGPUSubtarget &ST = TM.getSubtarget<AMDGPUSubtarget>();
if (ST.getGeneration() < AMDGPUSubtarget::SOUTHERN_ISLANDS ||
N->getMemoryVT().bitsLT(MVT::i32)) {
return true;
}
}
return checkType(N->getSrcValue(), AMDGPUAS::GLOBAL_ADDRESS);
}
bool AMDGPUDAGToDAGISel::isParamLoad(const LoadSDNode *N) const {
return checkType(N->getSrcValue(), AMDGPUAS::PARAM_I_ADDRESS);
}
bool AMDGPUDAGToDAGISel::isLocalLoad(const LoadSDNode *N) const {
return checkType(N->getSrcValue(), AMDGPUAS::LOCAL_ADDRESS);
}
bool AMDGPUDAGToDAGISel::isRegionLoad(const LoadSDNode *N) const {
return checkType(N->getSrcValue(), AMDGPUAS::REGION_ADDRESS);
}
bool AMDGPUDAGToDAGISel::isCPLoad(const LoadSDNode *N) const {
MachineMemOperand *MMO = N->getMemOperand();
if (checkType(N->getSrcValue(), AMDGPUAS::PRIVATE_ADDRESS)) {
if (MMO) {
const Value *V = MMO->getValue();
const PseudoSourceValue *PSV = dyn_cast<PseudoSourceValue>(V);
if (PSV && PSV == PseudoSourceValue::getConstantPool()) {
return true;
}
}
}
return false;
}
bool AMDGPUDAGToDAGISel::isPrivateLoad(const LoadSDNode *N) const {
if (checkType(N->getSrcValue(), AMDGPUAS::PRIVATE_ADDRESS)) {
// Check to make sure we are not a constant pool load or a constant load
// that is marked as a private load
if (isCPLoad(N) || isConstantLoad(N, -1)) {
return false;
}
}
if (!checkType(N->getSrcValue(), AMDGPUAS::LOCAL_ADDRESS)
&& !checkType(N->getSrcValue(), AMDGPUAS::GLOBAL_ADDRESS)
&& !checkType(N->getSrcValue(), AMDGPUAS::REGION_ADDRESS)
&& !checkType(N->getSrcValue(), AMDGPUAS::CONSTANT_ADDRESS)
&& !checkType(N->getSrcValue(), AMDGPUAS::PARAM_D_ADDRESS)
&& !checkType(N->getSrcValue(), AMDGPUAS::PARAM_I_ADDRESS)) {
return true;
}
return false;
}
const char *AMDGPUDAGToDAGISel::getPassName() const {
return "AMDGPU DAG->DAG Pattern Instruction Selection";
}
#ifdef DEBUGTMP
#undef INT64_C
#endif
#undef DEBUGTMP
//===----------------------------------------------------------------------===//
// Complex Patterns
//===----------------------------------------------------------------------===//
bool AMDGPUDAGToDAGISel::SelectGlobalValueConstantOffset(SDValue Addr,
SDValue& IntPtr) {
if (ConstantSDNode *Cst = dyn_cast<ConstantSDNode>(Addr)) {
IntPtr = CurDAG->getIntPtrConstant(Cst->getZExtValue() / 4, true);
return true;
}
return false;
}
bool AMDGPUDAGToDAGISel::SelectGlobalValueVariableOffset(SDValue Addr,
SDValue& BaseReg, SDValue &Offset) {
if (!dyn_cast<ConstantSDNode>(Addr)) {
BaseReg = Addr;
Offset = CurDAG->getIntPtrConstant(0, true);
return true;
}
return false;
}
bool AMDGPUDAGToDAGISel::SelectADDRVTX_READ(SDValue Addr, SDValue &Base,
SDValue &Offset) {
ConstantSDNode * IMMOffset;
if (Addr.getOpcode() == ISD::ADD
&& (IMMOffset = dyn_cast<ConstantSDNode>(Addr.getOperand(1)))
&& isInt<16>(IMMOffset->getZExtValue())) {
Base = Addr.getOperand(0);
Offset = CurDAG->getTargetConstant(IMMOffset->getZExtValue(), MVT::i32);
return true;
// If the pointer address is constant, we can move it to the offset field.
} else if ((IMMOffset = dyn_cast<ConstantSDNode>(Addr))
&& isInt<16>(IMMOffset->getZExtValue())) {
Base = CurDAG->getCopyFromReg(CurDAG->getEntryNode(),
SDLoc(CurDAG->getEntryNode()),
AMDGPU::ZERO, MVT::i32);
Offset = CurDAG->getTargetConstant(IMMOffset->getZExtValue(), MVT::i32);
return true;
}
// Default case, no offset
Base = Addr;
Offset = CurDAG->getTargetConstant(0, MVT::i32);
return true;
}
bool AMDGPUDAGToDAGISel::SelectADDRIndirect(SDValue Addr, SDValue &Base,
SDValue &Offset) {
ConstantSDNode *C;
if ((C = dyn_cast<ConstantSDNode>(Addr))) {
Base = CurDAG->getRegister(AMDGPU::INDIRECT_BASE_ADDR, MVT::i32);
Offset = CurDAG->getTargetConstant(C->getZExtValue(), MVT::i32);
} else if ((Addr.getOpcode() == ISD::ADD || Addr.getOpcode() == ISD::OR) &&
(C = dyn_cast<ConstantSDNode>(Addr.getOperand(1)))) {
Base = Addr.getOperand(0);
Offset = CurDAG->getTargetConstant(C->getZExtValue(), MVT::i32);
} else {
Base = Addr;
Offset = CurDAG->getTargetConstant(0, MVT::i32);
}
return true;
}
SDValue AMDGPUDAGToDAGISel::SimplifyI24(SDValue &Op) {
APInt Demanded = APInt(32, 0x00FFFFFF);
APInt KnownZero, KnownOne;
TargetLowering::TargetLoweringOpt TLO(*CurDAG, true, true);
const TargetLowering *TLI = getTargetLowering();
if (TLI->SimplifyDemandedBits(Op, Demanded, KnownZero, KnownOne, TLO)) {
CurDAG->ReplaceAllUsesWith(Op, TLO.New);
CurDAG->RepositionNode(Op.getNode(), TLO.New.getNode());
return SimplifyI24(TLO.New);
} else {
return Op;
}
}
bool AMDGPUDAGToDAGISel::SelectI24(SDValue Op, SDValue &I24) {
assert(Op.getValueType() == MVT::i32);
if (CurDAG->ComputeNumSignBits(Op) == 9) {
I24 = SimplifyI24(Op);
return true;
}
return false;
}
bool AMDGPUDAGToDAGISel::SelectU24(SDValue Op, SDValue &U24) {
APInt KnownZero;
APInt KnownOne;
CurDAG->ComputeMaskedBits(Op, KnownZero, KnownOne);
assert (Op.getValueType() == MVT::i32);
// ANY_EXTEND and EXTLOAD operations can only be done on types smaller than
// i32. These smaller types are legal to use with the i24 instructions.
if ((KnownZero & APInt(KnownZero.getBitWidth(), 0xFF000000)) == 0xFF000000 ||
Op.getOpcode() == ISD::ANY_EXTEND ||
ISD::isEXTLoad(Op.getNode())) {
U24 = SimplifyI24(Op);
return true;
}
return false;
}
void AMDGPUDAGToDAGISel::PostprocessISelDAG() {
const AMDGPUTargetLowering& Lowering =
(*(const AMDGPUTargetLowering*)getTargetLowering());
bool IsModified = false;
do {
IsModified = false;
// Go over all selected nodes and try to fold them a bit more
for (SelectionDAG::allnodes_iterator I = CurDAG->allnodes_begin(),
E = CurDAG->allnodes_end(); I != E; ++I) {
SDNode *Node = I;
MachineSDNode *MachineNode = dyn_cast<MachineSDNode>(I);
if (!MachineNode)
continue;
SDNode *ResNode = Lowering.PostISelFolding(MachineNode, *CurDAG);
if (ResNode != Node) {
ReplaceUses(Node, ResNode);
IsModified = true;
}
}
CurDAG->RemoveDeadNodes();
} while (IsModified);
}
Reference in New Issue View Git Blame Copy Permalink