R600/SI: Add a V_MOV_B64 pseudo instruction

[oota-llvm.git] / lib / Target / R600 / SIInstrInfo.cpp

diff --git a/lib/Target/R600/SIInstrInfo.cpp b/lib/Target/R600/SIInstrInfo.cpp
index 08bfc5e142294873158b9e816e9f8c1c6d5e4654..aa9e1a3178238b1ea1c0dba18d73b4d6510a1283 100644 (file)
--- a/lib/Target/R600/SIInstrInfo.cpp
+++ b/lib/Target/R600/SIInstrInfo.cpp
@@ -418,6 +418,18 @@ unsigned SIInstrInfo::commuteOpcode(unsigned Opcode) const {
   return Opcode;
 }
 
+unsigned SIInstrInfo::getMovOpcode(const TargetRegisterClass *DstRC) const {
+
+  if (DstRC->getSize() == 4) {
+    return RI.isSGPRClass(DstRC) ? AMDGPU::S_MOV_B32 : AMDGPU::V_MOV_B32_e32;
+  } else if (DstRC->getSize() == 8 && RI.isSGPRClass(DstRC)) {
+    return AMDGPU::S_MOV_B64;
+  } else if (DstRC->getSize() == 8 && !RI.isSGPRClass(DstRC)) {
+    return  AMDGPU::V_MOV_B64_PSEUDO;
+  }
+  return AMDGPU::COPY;
+}
+
 static bool shouldTryToSpillVGPRs(MachineFunction *MF) {
 
   SIMachineFunctionInfo *MFI = MF->getInfo<SIMachineFunctionInfo>();
@@ -662,6 +674,35 @@ bool SIInstrInfo::expandPostRAPseudo(MachineBasicBlock::iterator MI) const {
     // This is just a placeholder for register allocation.
     MI->eraseFromParent();
     break;
+
+  case AMDGPU::V_MOV_B64_PSEUDO: {
+    unsigned Dst = MI->getOperand(0).getReg();
+    unsigned DstLo = RI.getSubReg(Dst, AMDGPU::sub0);
+    unsigned DstHi = RI.getSubReg(Dst, AMDGPU::sub1);
+
+    const MachineOperand &SrcOp = MI->getOperand(1);
+    // FIXME: Will this work for 64-bit floating point immediates?
+    assert(!SrcOp.isFPImm());
+    if (SrcOp.isImm()) {
+      APInt Imm(64, SrcOp.getImm());
+      BuildMI(MBB, MI, DL, get(AMDGPU::V_MOV_B32_e32), DstLo)
+              .addImm(Imm.getLoBits(32).getZExtValue())
+              .addReg(Dst, RegState::Implicit);
+      BuildMI(MBB, MI, DL, get(AMDGPU::V_MOV_B32_e32), DstHi)
+              .addImm(Imm.getHiBits(32).getZExtValue())
+              .addReg(Dst, RegState::Implicit);
+    } else {
+      assert(SrcOp.isReg());
+      BuildMI(MBB, MI, DL, get(AMDGPU::V_MOV_B32_e32), DstLo)
+              .addReg(RI.getSubReg(SrcOp.getReg(), AMDGPU::sub0))
+              .addReg(Dst, RegState::Implicit);
+      BuildMI(MBB, MI, DL, get(AMDGPU::V_MOV_B32_e32), DstHi)
+              .addReg(RI.getSubReg(SrcOp.getReg(), AMDGPU::sub1))
+              .addReg(Dst, RegState::Implicit);
+    }
+    MI->eraseFromParent();
+    break;
+  }
   }
   return true;
 }
@@ -1405,7 +1446,7 @@ bool SIInstrInfo::isOperandLegal(const MachineInstr *MI, unsigned OpIdx,
   if (!MO)
     MO = &MI->getOperand(OpIdx);
 
-  if (usesConstantBus(MRI, *MO)) {
+  if (isVALU(InstDesc.Opcode) && usesConstantBus(MRI, *MO)) {
     unsigned SGPRUsed =
         MO->isReg() ? MO->getReg() : (unsigned)AMDGPU::NoRegister;
     for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) {