[llvm] 87b1d35 - [AMDGPU][NFC] Avoid copying MachineOperands (#166293)

[via llvm-commits]

Author: LU-JOHN
Date: 2025-11-04T23:18:40-06:00
New Revision: 87b1d3537ae6adcb0a16cc0fa2749862d01009d3

URL: https://github.com/llvm/llvm-project/commit/87b1d3537ae6adcb0a16cc0fa2749862d01009d3
DIFF: https://github.com/llvm/llvm-project/commit/87b1d3537ae6adcb0a16cc0fa2749862d01009d3.diff

LOG: [AMDGPU][NFC] Avoid copying MachineOperands (#166293)

Avoid copying machine operands.

Signed-off-by: John Lu <John.Lu at amd.com>

Added: 
    

Modified: 
    llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
    llvm/lib/Target/AMDGPU/GCNPreRAOptimizations.cpp
    llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
    llvm/lib/Target/AMDGPU/SIInstrInfo.h
    llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp b/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
index 957d7164b686e..15ed60b46a9c0 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
@@ -6764,7 +6764,7 @@ bool AMDGPUInstructionSelector::selectSGetBarrierState(
     MachineInstr &I, Intrinsic::ID IntrID) const {
   MachineBasicBlock *MBB = I.getParent();
   const DebugLoc &DL = I.getDebugLoc();
-  MachineOperand BarOp = I.getOperand(2);
+  const MachineOperand &BarOp = I.getOperand(2);
   std::optional<int64_t> BarValImm =
       getIConstantVRegSExtVal(BarOp.getReg(), *MRI);
 
@@ -6817,8 +6817,8 @@ bool AMDGPUInstructionSelector::selectNamedBarrierInit(
     MachineInstr &I, Intrinsic::ID IntrID) const {
   MachineBasicBlock *MBB = I.getParent();
   const DebugLoc &DL = I.getDebugLoc();
-  MachineOperand BarOp = I.getOperand(1);
-  MachineOperand CntOp = I.getOperand(2);
+  const MachineOperand &BarOp = I.getOperand(1);
+  const MachineOperand &CntOp = I.getOperand(2);
 
   // BarID = (BarOp >> 4) & 0x3F
   Register TmpReg0 = MRI->createVirtualRegister(&AMDGPU::SReg_32RegClass);

diff  --git a/llvm/lib/Target/AMDGPU/GCNPreRAOptimizations.cpp b/llvm/lib/Target/AMDGPU/GCNPreRAOptimizations.cpp
index 4deb2a9485e4d..62172a0bb89db 100644
--- a/llvm/lib/Target/AMDGPU/GCNPreRAOptimizations.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNPreRAOptimizations.cpp
@@ -136,7 +136,7 @@ bool GCNPreRAOptimizationsImpl::processReg(Register Reg) {
           continue;
 
         if (Def.getOpcode() == AMDGPU::V_ACCVGPR_WRITE_B32_e64) {
-          MachineOperand DefSrcMO = Def.getOperand(1);
+          const MachineOperand &DefSrcMO = Def.getOperand(1);
 
           // Immediates are not an issue and can be propagated in
           // postrapseudos pass. Only handle cases where defining

diff  --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
index 45f591927b86e..9460145d47111 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -7945,7 +7945,7 @@ void SIInstrInfo::moveToVALUImpl(SIInstrWorklist &Worklist,
     }
     legalizeOperands(*NewInstr, MDT);
     int SCCIdx = Inst.findRegisterDefOperandIdx(AMDGPU::SCC, /*TRI=*/nullptr);
-    MachineOperand SCCOp = Inst.getOperand(SCCIdx);
+    const MachineOperand &SCCOp = Inst.getOperand(SCCIdx);
     addSCCDefUsersToVALUWorklist(SCCOp, Inst, Worklist, CondReg);
     Inst.eraseFromParent();
     return;
@@ -7985,7 +7985,7 @@ void SIInstrInfo::moveToVALUImpl(SIInstrWorklist &Worklist,
     legalizeOperandsVALUt16(*NewInstr, MRI);
     legalizeOperands(*NewInstr, MDT);
     int SCCIdx = Inst.findRegisterDefOperandIdx(AMDGPU::SCC, /*TRI=*/nullptr);
-    MachineOperand SCCOp = Inst.getOperand(SCCIdx);
+    const MachineOperand &SCCOp = Inst.getOperand(SCCIdx);
     addSCCDefUsersToVALUWorklist(SCCOp, Inst, Worklist, CondReg);
     Inst.eraseFromParent();
     return;
@@ -8183,7 +8183,7 @@ void SIInstrInfo::moveToVALUImpl(SIInstrWorklist &Worklist,
                                    AMDGPU::OpName::src0_modifiers) >= 0)
       NewInstr.addImm(0);
     if (AMDGPU::hasNamedOperand(NewOpcode, AMDGPU::OpName::src0)) {
-      MachineOperand Src = Inst.getOperand(1);
+      const MachineOperand &Src = Inst.getOperand(1);
       NewInstr->addOperand(Src);
     }
 
@@ -9199,7 +9199,7 @@ void SIInstrInfo::movePackToVALU(SIInstrWorklist &Worklist,
   addUsersToMoveToVALUWorklist(ResultReg, MRI, Worklist);
 }
 
-void SIInstrInfo::addSCCDefUsersToVALUWorklist(MachineOperand &Op,
+void SIInstrInfo::addSCCDefUsersToVALUWorklist(const MachineOperand &Op,
                                                MachineInstr &SCCDefInst,
                                                SIInstrWorklist &Worklist,
                                                Register NewCond) const {

diff  --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.h b/llvm/lib/Target/AMDGPU/SIInstrInfo.h
index dc23a21f959ce..0643b532ea04c 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.h
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.h
@@ -172,7 +172,7 @@ class SIInstrInfo final : public AMDGPUGenInstrInfo {
   void addUsersToMoveToVALUWorklist(Register Reg, MachineRegisterInfo &MRI,
                                     SIInstrWorklist &Worklist) const;
 
-  void addSCCDefUsersToVALUWorklist(MachineOperand &Op,
+  void addSCCDefUsersToVALUWorklist(const MachineOperand &Op,
                                     MachineInstr &SCCDefInst,
                                     SIInstrWorklist &Worklist,
                                     Register NewCond = Register()) const;

diff  --git a/llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp b/llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp
index abefa32b8f802..8785968569d92 100644
--- a/llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp
+++ b/llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp
@@ -640,7 +640,7 @@ void SIPreEmitPeephole::collectUnpackingCandidates(
 }
 
 void SIPreEmitPeephole::performF32Unpacking(MachineInstr &I) {
-  MachineOperand DstOp = I.getOperand(0);
+  const MachineOperand &DstOp = I.getOperand(0);
 
   uint16_t UnpackedOpcode = mapToUnpackedOpcode(I);
   assert(UnpackedOpcode != std::numeric_limits<uint16_t>::max() &&