AMDGPU/SI: Test commit

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

diff --git a/lib/Target/AMDGPU/SIInstrInfo.cpp b/lib/Target/AMDGPU/SIInstrInfo.cpp
index a3a2d8c01eb570a256d7e136c0e5f18f4a23d46d..6c4cb011ef26eb4820eb93a4658eba181bb35d8a 100644 (file)
--- a/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -742,8 +742,8 @@ unsigned SIInstrInfo::calculateLDSSpillAddress(MachineBasicBlock &MBB,
   return TmpReg;
 }
 
-void SIInstrInfo::insertNOPs(MachineBasicBlock::iterator MI,
-                             int Count) const {
+void SIInstrInfo::insertWaitStates(MachineBasicBlock::iterator MI,
+                                   int Count) const {
   while (Count > 0) {
     int Arg;
     if (Count >= 8)
@@ -762,26 +762,6 @@ bool SIInstrInfo::expandPostRAPseudo(MachineBasicBlock::iterator MI) const {
   switch (MI->getOpcode()) {
   default: return AMDGPUInstrInfo::expandPostRAPseudo(MI);
 
-  case AMDGPU::SI_CONSTDATA_PTR: {
-    unsigned Reg = MI->getOperand(0).getReg();
-    unsigned RegLo = RI.getSubReg(Reg, AMDGPU::sub0);
-    unsigned RegHi = RI.getSubReg(Reg, AMDGPU::sub1);
-
-    BuildMI(MBB, MI, DL, get(AMDGPU::S_GETPC_B64), Reg);
-
-    // Add 32-bit offset from this instruction to the start of the constant data.
-    BuildMI(MBB, MI, DL, get(AMDGPU::S_ADD_U32), RegLo)
-            .addReg(RegLo)
-            .addTargetIndex(AMDGPU::TI_CONSTDATA_START)
-            .addReg(AMDGPU::SCC, RegState::Define | RegState::Implicit);
-    BuildMI(MBB, MI, DL, get(AMDGPU::S_ADDC_U32), RegHi)
-            .addReg(RegHi)
-            .addImm(0)
-            .addReg(AMDGPU::SCC, RegState::Define | RegState::Implicit)
-            .addReg(AMDGPU::SCC, RegState::Implicit);
-    MI->eraseFromParent();
-    break;
-  }
   case AMDGPU::SGPR_USE:
     // This is just a placeholder for register allocation.
     MI->eraseFromParent();
@@ -835,6 +815,34 @@ bool SIInstrInfo::expandPostRAPseudo(MachineBasicBlock::iterator MI) const {
     MI->eraseFromParent();
     break;
   }
+
+  case AMDGPU::SI_CONSTDATA_PTR: {
+    const SIRegisterInfo *TRI =
+        static_cast<const SIRegisterInfo *>(ST.getRegisterInfo());
+    MachineFunction &MF = *MBB.getParent();
+    unsigned Reg = MI->getOperand(0).getReg();
+    unsigned RegLo = TRI->getSubReg(Reg, AMDGPU::sub0);
+    unsigned RegHi = TRI->getSubReg(Reg, AMDGPU::sub1);
+
+    // Create a bundle so these instructions won't be re-ordered by the
+    // post-RA scheduler.
+    MIBundleBuilder Bundler(MBB, MI);
+    Bundler.append(BuildMI(MF, DL, get(AMDGPU::S_GETPC_B64), Reg));
+
+    // Add 32-bit offset from this instruction to the start of the
+    // constant data.
+    Bundler.append(BuildMI(MF, DL, get(AMDGPU::S_ADD_U32), RegLo)
+                           .addReg(RegLo)
+                           .addOperand(MI->getOperand(1)));
+    Bundler.append(BuildMI(MF, DL, get(AMDGPU::S_ADDC_U32), RegHi)
+                           .addReg(RegHi)
+                           .addImm(0));
+
+    llvm::finalizeBundle(MBB, Bundler.begin());
+
+    MI->eraseFromParent();
+    break;
+  }
   }
   return true;
 }
@@ -1425,7 +1433,7 @@ bool SIInstrInfo::verifyInstruction(const MachineInstr *MI,
      return false;
   }
 
-  // Make sure the register classes are correct
+  // Make sure the register classes are correct.
   for (int i = 0, e = Desc.getNumOperands(); i != e; ++i) {
     if (MI->getOperand(i).isFPImm()) {
       ErrInfo = "FPImm Machine Operands are not supported. ISel should bitcast "