Skip to content

AMDGPU: Use helper function for use/def chain walk #129052

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 27, 2025
Merged

AMDGPU: Use helper function for use/def chain walk #129052

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
55 changes: 37 additions & 18 deletions llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -781,6 +781,27 @@ bool SIFoldOperandsImpl::isUseSafeToFold(const MachineInstr &MI,
return !TII->isSDWA(MI);
}

static MachineOperand *lookUpCopyChain(const SIInstrInfo &TII,
const MachineRegisterInfo &MRI,
Register SrcReg) {
MachineOperand *Sub = nullptr;
for (MachineInstr *SubDef = MRI.getVRegDef(SrcReg);
SubDef && TII.isFoldableCopy(*SubDef);
SubDef = MRI.getVRegDef(Sub->getReg())) {
MachineOperand &SrcOp = SubDef->getOperand(1);
if (SrcOp.isImm())
return &SrcOp;
if (!SrcOp.isReg() || SrcOp.getReg().isPhysical())
break;
Sub = &SrcOp;
// TODO: Support compose
if (SrcOp.getSubReg())
break;
}

return Sub;
}

// Find a def of the UseReg, check if it is a reg_sequence and find initializers
// for each subreg, tracking it to foldable inline immediate if possible.
// Returns true on success.
Expand All @@ -791,26 +812,24 @@ bool SIFoldOperandsImpl::getRegSeqInit(
if (!Def || !Def->isRegSequence())
return false;

for (unsigned I = 1, E = Def->getNumExplicitOperands(); I < E; I += 2) {
MachineOperand *Sub = &Def->getOperand(I);
assert(Sub->isReg());

for (MachineInstr *SubDef = MRI->getVRegDef(Sub->getReg());
SubDef && Sub->isReg() && Sub->getReg().isVirtual() &&
!Sub->getSubReg() && TII->isFoldableCopy(*SubDef);
SubDef = MRI->getVRegDef(Sub->getReg())) {
MachineOperand *Op = &SubDef->getOperand(1);
if (Op->isImm()) {
if (TII->isInlineConstant(*Op, OpTy))
Sub = Op;
break;
}
if (!Op->isReg() || Op->getReg().isPhysical())
break;
Sub = Op;
for (unsigned I = 1, E = Def->getNumExplicitOperands(); I != E; I += 2) {
MachineOperand &SrcOp = Def->getOperand(I);
unsigned SubRegIdx = Def->getOperand(I + 1).getImm();

if (SrcOp.getSubReg()) {
// TODO: Handle subregister compose
Defs.emplace_back(&SrcOp, SubRegIdx);
continue;
}

MachineOperand *DefSrc = lookUpCopyChain(*TII, *MRI, SrcOp.getReg());
if (DefSrc && (DefSrc->isReg() ||
(DefSrc->isImm() && TII->isInlineConstant(*DefSrc, OpTy)))) {
Defs.emplace_back(DefSrc, SubRegIdx);
continue;
}

Defs.emplace_back(Sub, Def->getOperand(I + 1).getImm());
Defs.emplace_back(&SrcOp, SubRegIdx);
}

return true;
Expand Down