================
@@ -25,52 +25,151 @@ using namespace llvm;
namespace {
-struct FoldCandidate {
- MachineInstr *UseMI;
+/// Track a value we may want to fold into downstream users, applying
+/// subregister extracts along the way.
+struct FoldableDef {
union {
- MachineOperand *OpToFold;
+ MachineOperand *OpToFold = nullptr;
uint64_t ImmToFold;
int FrameIndexToFold;
};
- int ShrinkOpcode;
- unsigned UseOpNo;
+
+ /// Register class of the originally defined value.
+ const TargetRegisterClass *DefRC = nullptr;
+
+ /// Track the original defining instruction for the value.
+ const MachineInstr *DefMI = nullptr;
+
+ /// Subregister to apply to the value at the use point.
+ unsigned DefSubReg = AMDGPU::NoSubRegister;
+
+ /// Kind of value stored in the union.
MachineOperand::MachineOperandType Kind;
- bool Commuted;
- FoldCandidate(MachineInstr *MI, unsigned OpNo, MachineOperand *FoldOp,
- bool Commuted_ = false,
- int ShrinkOp = -1) :
- UseMI(MI), OpToFold(nullptr), ShrinkOpcode(ShrinkOp), UseOpNo(OpNo),
- Kind(FoldOp->getType()),
- Commuted(Commuted_) {
- if (FoldOp->isImm()) {
- ImmToFold = FoldOp->getImm();
- } else if (FoldOp->isFI()) {
- FrameIndexToFold = FoldOp->getIndex();
+ FoldableDef() = delete;
+ FoldableDef(MachineOperand &FoldOp, const TargetRegisterClass *DefRC,
+ unsigned DefSubReg = AMDGPU::NoSubRegister)
+ : DefRC(DefRC), DefSubReg(DefSubReg), Kind(FoldOp.getType()) {
+
+ if (FoldOp.isImm()) {
+ ImmToFold = FoldOp.getImm();
+ } else if (FoldOp.isFI()) {
+ FrameIndexToFold = FoldOp.getIndex();
} else {
- assert(FoldOp->isReg() || FoldOp->isGlobal());
- OpToFold = FoldOp;
+ assert(FoldOp.isReg() || FoldOp.isGlobal());
+ OpToFold = &FoldOp;
}
+
+ DefMI = FoldOp.getParent();
}
- FoldCandidate(MachineInstr *MI, unsigned OpNo, int64_t FoldImm,
- bool Commuted_ = false, int ShrinkOp = -1)
- : UseMI(MI), ImmToFold(FoldImm), ShrinkOpcode(ShrinkOp), UseOpNo(OpNo),
- Kind(MachineOperand::MO_Immediate), Commuted(Commuted_) {}
+ FoldableDef(int64_t FoldImm, const TargetRegisterClass *DefRC,
+ unsigned DefSubReg = AMDGPU::NoSubRegister)
+ : ImmToFold(FoldImm), DefRC(DefRC), DefSubReg(DefSubReg),
+ Kind(MachineOperand::MO_Immediate) {}
+
+ /// Copy the current def and apply \p SubReg to the value.
+ FoldableDef getWithSubReg(const SIRegisterInfo &TRI, unsigned SubReg) const {
+ FoldableDef Copy(*this);
+ Copy.DefSubReg = TRI.composeSubRegIndices(DefSubReg, SubReg);
+ return Copy;
+ }
+
+ bool isReg() const { return Kind == MachineOperand::MO_Register; }
+
+ Register getReg() const {
+ assert(isReg());
+ return OpToFold->getReg();
+ }
+
+ unsigned getSubReg() const {
+ assert(isReg());
+ return OpToFold->getSubReg();
+ }
+
+ bool isImm() const { return Kind == MachineOperand::MO_Immediate; }
bool isFI() const {
return Kind == MachineOperand::MO_FrameIndex;
}
- bool isImm() const {
- return Kind == MachineOperand::MO_Immediate;
+ int getFI() const {
+ assert(isFI());
+ return FrameIndexToFold;
}
- bool isReg() const {
- return Kind == MachineOperand::MO_Register;
+ bool isGlobal() const { return OpToFold->isGlobal(); }
----------------
jayfoad wrote:
Not safe to access `OpToFold` unless you check for Imm and FI first:
```suggestion
bool isGlobal() const {
return !isImm() && !isFI() && OpToFold->isGlobal();
}
```
https://github.com/llvm/llvm-project/pull/140608
_______________________________________________
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
