diff --git a/lib/Target/R600/MCTargetDesc/R600MCCodeEmitter.cpp b/lib/Target/R600/MCTargetDesc/R600MCCodeEmitter.cpp
index bc5c9d8..7c83d86 100644
--- a/lib/Target/R600/MCTargetDesc/R600MCCodeEmitter.cpp
+++ b/lib/Target/R600/MCTargetDesc/R600MCCodeEmitter.cpp
@@ -143,6 +143,7 @@
     EmitFCInstr(MI, OS);
   } else if (MI.getOpcode() == AMDGPU::RETURN ||
     MI.getOpcode() == AMDGPU::FETCH_CLAUSE ||
+    MI.getOpcode() == AMDGPU::ALU_CLAUSE ||
     MI.getOpcode() == AMDGPU::BUNDLE ||
     MI.getOpcode() == AMDGPU::KILL) {
     return;
@@ -255,7 +256,7 @@
     case AMDGPU::CF_ALU:
     case AMDGPU::CF_ALU_PUSH_BEFORE: {
       uint64_t Inst = getBinaryCodeForInstr(MI, Fixups);
-      EmitByte(INSTR_CFALU, OS);
+      EmitByte(INSTR_NATIVE, OS);
       Emit(Inst, OS);
       break;
     }
@@ -294,7 +295,9 @@
       break;
     }
     default:
-      EmitALUInstr(MI, Fixups, OS);
+      uint64_t Inst = getBinaryCodeForInstr(MI, Fixups);
+      EmitByte(INSTR_NATIVE, OS);
+      Emit(Inst, OS);
       break;
     }
   }
diff --git a/lib/Target/R600/R600ControlFlowFinalizer.cpp b/lib/Target/R600/R600ControlFlowFinalizer.cpp
index e637641..0995795 100644
--- a/lib/Target/R600/R600ControlFlowFinalizer.cpp
+++ b/lib/Target/R600/R600ControlFlowFinalizer.cpp
@@ -165,6 +165,97 @@
     return ClauseFile(MIb, ClauseContent);
   }
 
+  void getLiteral(MachineInstr *MI, std::vector<unsigned> &Lits) const {
+    unsigned LiteralRegs[] = {
+      AMDGPU::ALU_LITERAL_X,
+      AMDGPU::ALU_LITERAL_Y,
+      AMDGPU::ALU_LITERAL_Z,
+      AMDGPU::ALU_LITERAL_W
+    };
+    for (unsigned i = 0, e = MI->getNumOperands(); i < e; ++i) {
+      MachineOperand &MO = MI->getOperand(i);
+      if (!MO.isReg())
+        continue;
+      if (MO.getReg() != AMDGPU::ALU_LITERAL_X)
+        continue;
+      unsigned ImmIdx = TII->getOperandIdx(MI->getOpcode(), R600Operands::IMM);
+      int64_t Imm = MI->getOperand(ImmIdx).getImm();
+      std::vector<unsigned>::iterator It =
+          std::find(Lits.begin(), Lits.end(), Imm);
+      if (It != Lits.end()) {
+        unsigned Index = It - Lits.begin();
+        MO.setReg(LiteralRegs[Index]);
+      } else {
+        assert(Lits.size() < 4 && "Too many literals in Instruction Group");
+        MO.setReg(LiteralRegs[Lits.size()]);
+        Lits.push_back(Imm);
+      }
+    }
+  }
+
+  MachineBasicBlock::iterator insertLiterals(
+      MachineBasicBlock::iterator InsertPos,
+      const std::vector<unsigned> &Literals) const {
+    MachineBasicBlock *MBB = InsertPos->getParent();
+    for (unsigned i = 0, e = Literals.size(); i < e; i+=2) {
+      unsigned LiteralPair0 = Literals[i];
+      unsigned LiteralPair1 = (i + 1 < e)?Literals[i + 1]:0;
+      InsertPos = BuildMI(MBB, InsertPos->getDebugLoc(),
+          TII->get(AMDGPU::LITERALS))
+          .addImm(LiteralPair0)
+          .addImm(LiteralPair1);
+    }
+    return InsertPos;
+  }
+
+  ClauseFile
+  MakeALUClause(MachineBasicBlock &MBB, MachineBasicBlock::iterator &I)
+      const {
+    MachineBasicBlock::iterator ClauseHead = I;
+    std::vector<MachineInstr *> ClauseContent;
+    I++;
+    for (MachineBasicBlock::instr_iterator E = MBB.instr_end(); I != E;) {
+      if (IsTrivialInst(I)) {
+        ++I;
+        continue;
+      }
+      if (!I->isBundle() && !TII->isALUInstr(I->getOpcode()))
+        break;
+      std::vector<unsigned> Literals;
+      if (I->isBundle()) {
+        MachineInstr *DeleteMI = I;
+        MachineBasicBlock::instr_iterator BI = I.getInstrIterator();
+        while (++BI != E && BI->isBundledWithPred()) {
+          BI->unbundleFromPred();
+          for (unsigned i = 0, e = BI->getNumOperands(); i != e; ++i) {
+            MachineOperand &MO = BI->getOperand(i);
+            if (MO.isReg() && MO.isInternalRead())
+              MO.setIsInternalRead(false);
+          }
+          getLiteral(BI, Literals);
+          ClauseContent.push_back(BI);
+        }
+        I = BI;
+        DeleteMI->eraseFromParent();
+      } else {
+        getLiteral(I, Literals);
+        ClauseContent.push_back(I);
+        I++;
+      }
+      for (unsigned i = 0, e = Literals.size(); i < e; i+=2) {
+        unsigned literal0 = Literals[i];
+        unsigned literal2 = (i + 1 < e)?Literals[i + 1]:0;
+        MachineInstr *MILit = BuildMI(MBB, I, I->getDebugLoc(),
+            TII->get(AMDGPU::LITERALS))
+            .addImm(literal0)
+            .addImm(literal2);
+        ClauseContent.push_back(MILit);
+      }
+    }
+    ClauseHead->getOperand(7).setImm(ClauseContent.size() - 1);
+    return ClauseFile(ClauseHead, ClauseContent);
+  }
+
   void
   EmitFetchClause(MachineBasicBlock::iterator InsertPos, ClauseFile &Clause,
       unsigned &CfCount) {
@@ -178,6 +269,19 @@
     CfCount += 2 * Clause.second.size();
   }
 
+  void
+  EmitALUClause(MachineBasicBlock::iterator InsertPos, ClauseFile &Clause,
+      unsigned &CfCount) {
+    CounterPropagateAddr(Clause.first, CfCount);
+    MachineBasicBlock *BB = Clause.first->getParent();
+    BuildMI(BB, InsertPos->getDebugLoc(), TII->get(AMDGPU::ALU_CLAUSE))
+        .addImm(CfCount);
+    for (unsigned i = 0, e = Clause.second.size(); i < e; ++i) {
+      BB->splice(InsertPos, BB, Clause.second[i]);
+    }
+    CfCount += Clause.second.size();
+  }
+
   void CounterPropagateAddr(MachineInstr *MI, unsigned Addr) const {
     MI->getOperand(0).setImm(Addr + MI->getOperand(0).getImm());
   }
@@ -234,7 +338,7 @@
             getHWInstrDesc(CF_CALL_FS));
         CfCount++;
       }
-      std::vector<ClauseFile> FetchClauses;
+      std::vector<ClauseFile> FetchClauses, AluClauses;
       for (MachineBasicBlock::iterator I = MBB.begin(), E = MBB.end();
           I != E;) {
         if (TII->usesTextureCache(I) || TII->usesVertexCache(I)) {
@@ -252,6 +356,8 @@
           MaxStack = std::max(MaxStack, CurrentStack);
           hasPush = true;
         case AMDGPU::CF_ALU:
+          I = MI;
+          AluClauses.push_back(MakeALUClause(MBB, I));
         case AMDGPU::EG_ExportBuf:
         case AMDGPU::EG_ExportSwz:
         case AMDGPU::R600_ExportBuf:
@@ -362,6 +468,8 @@
           }
           for (unsigned i = 0, e = FetchClauses.size(); i < e; i++)
             EmitFetchClause(I, FetchClauses[i], CfCount);
+          for (unsigned i = 0, e = AluClauses.size(); i < e; i++)
+            EmitALUClause(I, AluClauses[i], CfCount);
         }
         default:
           break;
diff --git a/lib/Target/R600/R600Instructions.td b/lib/Target/R600/R600Instructions.td
index 3426831..1d25da3 100644
--- a/lib/Target/R600/R600Instructions.td
+++ b/lib/Target/R600/R600Instructions.td
@@ -944,6 +944,23 @@
   let Inst = num;
 }
 
+def ALU_CLAUSE : AMDGPUInst <(outs),
+(ins i32imm:$addr), "ALU clause starting at $addr:", [] > {
+  field bits<8> Inst;
+  bits<8> num;
+  let Inst = num;
+}
+
+def LITERALS : AMDGPUInst <(outs),
+(ins LITERAL:$literal1, LITERAL:$literal2), "$literal1, $literal2", [] > {
+  field bits<64> Inst;
+  bits<32> literal1;
+  bits<32> literal2;
+
+  let Inst{31-0} = literal1;
+  let Inst{63-32} = literal2;
+}
+
 def PAD : AMDGPUInst <(outs), (ins), "PAD", [] > {
   field bits<64> Inst;
 }
diff --git a/lib/Target/R600/R600RegisterInfo.td b/lib/Target/R600/R600RegisterInfo.td
index 6944319..5a2e65c 100644
--- a/lib/Target/R600/R600RegisterInfo.td
+++ b/lib/Target/R600/R600RegisterInfo.td
@@ -88,7 +88,10 @@
 def ONE_INT : R600Reg<"1", 250>;
 def HALF : R600Reg<"0.5", 252>;
 def NEG_HALF : R600Reg<"-0.5", 252>;
-def ALU_LITERAL_X : R600Reg<"literal.x", 253>;
+def ALU_LITERAL_X : R600RegWithChan<"literal.x", 253, "X">;
+def ALU_LITERAL_Y : R600RegWithChan<"literal.x", 253, "Y">;
+def ALU_LITERAL_Z : R600RegWithChan<"literal.x", 253, "Z">;
+def ALU_LITERAL_W : R600RegWithChan<"literal.x", 253, "W">;
 def PV_X : R600RegWithChan<"PV.x", 254, "X">;
 def PV_Y : R600RegWithChan<"PV.y", 254, "Y">;
 def PV_Z : R600RegWithChan<"PV.z", 254, "Z">;
diff --git a/test/CodeGen/R600/alu-split.ll b/test/CodeGen/R600/alu-split.ll
index afefcd9..48496f6 100644
--- a/test/CodeGen/R600/alu-split.ll
+++ b/test/CodeGen/R600/alu-split.ll
@@ -4,6 +4,7 @@
 ;CHECK: ALU
 ;CHECK: ALU
 ;CHECK-NOT: ALU
+;CHECK: CF_END
 
 define void @main() #0 {
 main_body:
diff --git a/test/CodeGen/R600/disconnected-predset-break-bug.ll b/test/CodeGen/R600/disconnected-predset-break-bug.ll
index 09baee7..012c17b 100644
--- a/test/CodeGen/R600/disconnected-predset-break-bug.ll
+++ b/test/CodeGen/R600/disconnected-predset-break-bug.ll
@@ -6,7 +6,7 @@
 
 ; CHECK: @loop_ge
 ; CHECK: LOOP_START_DX10
-; CHECK: PRED_SET
+; CHECK: ALU_PUSH_BEFORE
 ; CHECK-NEXT: JUMP
 ; CHECK-NEXT: LOOP_BREAK
 define void @loop_ge(i32 addrspace(1)* nocapture %out, i32 %iterations) nounwind {
diff --git a/test/CodeGen/R600/predicates.ll b/test/CodeGen/R600/predicates.ll
index eb8b052..fb093ed 100644
--- a/test/CodeGen/R600/predicates.ll
+++ b/test/CodeGen/R600/predicates.ll
@@ -46,11 +46,11 @@
 
 ; CHECK: @nested_if
 ; CHECK: ALU_PUSH_BEFORE
-; CHECK: PRED_SET{{[EGN][ET]*}}_INT Exec
 ; CHECK: JUMP
+; CHECK: POP
+; CHECK: PRED_SET{{[EGN][ET]*}}_INT Exec
 ; CHECK: PRED_SET{{[EGN][ET]*}}_INT Pred,
 ; CHECK: LSHL T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, 1, 0(0.000000e+00) Pred_sel
-; CHECK: POP
 define void @nested_if(i32 addrspace(1)* %out, i32 %in) {
 entry:
   %0 = icmp sgt i32 %in, 0
@@ -73,12 +73,12 @@
 
 ; CHECK: @nested_if_else
 ; CHECK: ALU_PUSH_BEFORE
-; CHECK: PRED_SET{{[EGN][ET]*}}_INT Exec
 ; CHECK: JUMP
+; CHECK: POP
+; CHECK: PRED_SET{{[EGN][ET]*}}_INT Exec
 ; CHECK: PRED_SET{{[EGN][ET]*}}_INT Pred,
 ; CHECK: LSH{{[LR] T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, 1, 0(0.000000e+00) Pred_sel
 ; CHECK: LSH{{[LR] T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, 1, 0(0.000000e+00) Pred_sel
-; CHECK: POP
 define void @nested_if_else(i32 addrspace(1)* %out, i32 %in) {
 entry:
   %0 = icmp sgt i32 %in, 0