static bool isSendMsgTraceDataOrGDS(const SIInstrInfo &TII,
const MachineInstr &MI) {
if (TII.isAlwaysGDS(MI.getOpcode()))
return true;
switch (MI.getOpcode()) {
case AMDGPU::S_SENDMSG:
case AMDGPU::S_SENDMSGHALT:
case AMDGPU::S_TTRACEDATA:
return true;
// These DS opcodes don't support GDS.
case AMDGPU::DS_NOP:
case AMDGPU::DS_PERMUTE_B32:
case AMDGPU::DS_BPERMUTE_B32:
return false;
default:
if (TII.isDS(MI.getOpcode())) {
int GDS = AMDGPU::getNamedOperandIdx(MI.getOpcode(),
AMDGPU::OpName::gds);
if (MI.getOperand(GDS).getImm())
return true;
}
return false;
}
}
static bool hasAnyNonFlatUseOfReg(const MachineRegisterInfo &MRI,
const SIInstrInfo &TII,
unsigned Reg) {
for (const MachineOperand &UseOp : MRI.reg_operands(Reg)) {
if (!UseOp.isImplicit() || !TII.isFLAT(*UseOp.getParent()))
return true;
}
return false;
}
// These are only terminators to get correct spill code placement during
// register allocation, so turn them back into normal instructions. Only one of
// these is expected per block.
static bool removeTerminatorBit(const SIInstrInfo &TII, MachineInstr &MI) {
switch (MI.getOpcode()) {
case AMDGPU::S_MOV_B64_term: {
MI.setDesc(TII.get(AMDGPU::COPY));
return true;
}
case AMDGPU::S_XOR_B64_term: {
// This is only a terminator to get the correct spill code placement during
// register allocation.
MI.setDesc(TII.get(AMDGPU::S_XOR_B64));
return true;
}
case AMDGPU::S_ANDN2_B64_term: {
// This is only a terminator to get the correct spill code placement during
// register allocation.
MI.setDesc(TII.get(AMDGPU::S_ANDN2_B64));
return true;
}
default:
return false;
}
}
void apply(ScheduleDAGInstrs *DAGInstrs) override {
ScheduleDAGMI *DAG = static_cast<ScheduleDAGMI*>(DAGInstrs);
SUnit *SUa = nullptr;
// Search for two consequent memory operations and link them
// to prevent scheduler from moving them apart.
// In DAG pre-process SUnits are in the original order of
// the instructions before scheduling.
for (SUnit &SU : DAG->SUnits) {
MachineInstr &MI2 = *SU.getInstr();
if (!MI2.mayLoad() && !MI2.mayStore()) {
SUa = nullptr;
continue;
}
if (!SUa) {
SUa = &SU;
continue;
}
MachineInstr &MI1 = *SUa->getInstr();
if ((TII->isVMEM(MI1) && TII->isVMEM(MI2)) ||
(TII->isFLAT(MI1) && TII->isFLAT(MI2)) ||
(TII->isSMRD(MI1) && TII->isSMRD(MI2)) ||
(TII->isDS(MI1) && TII->isDS(MI2))) {
SU.addPredBarrier(SUa);
for (const SDep &SI : SU.Preds) {
if (SI.getSUnit() != SUa)
SUa->addPred(SDep(SI.getSUnit(), SDep::Artificial));
}
if (&SU != &DAG->ExitSU) {
for (const SDep &SI : SUa->Succs) {
if (SI.getSUnit() != &SU)
SI.getSUnit()->addPred(SDep(&SU, SDep::Artificial));
}
}
}
SUa = &SU;
}
}
