update a bunch of entries.

[oota-llvm.git] / lib / Target / X86 / X86ISelLowering.cpp

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index e4561aad41abeb3c8ecea57a5b4e2c34fc529df3..fca7b02c40abff9d0e0f6e7e2e2bae1644e7f99c 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -256,7 +256,7 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM)
     setOperationAction(ISD::SREM, VT, Expand);
     setOperationAction(ISD::UREM, VT, Expand);
     
-    // Add/Sub overflow ops with MVT::Flags are lowered to EFLAGS dependences.
+    // Add/Sub overflow ops with MVT::Glues are lowered to EFLAGS dependences.
     setOperationAction(ISD::ADDC, VT, Custom);
     setOperationAction(ISD::ADDE, VT, Custom);
     setOperationAction(ISD::SUBC, VT, Custom);
@@ -969,6 +969,8 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM)
   setTargetDAGCombine(ISD::SRL);
   setTargetDAGCombine(ISD::OR);
   setTargetDAGCombine(ISD::AND);
+  setTargetDAGCombine(ISD::ADD);
+  setTargetDAGCombine(ISD::SUB);
   setTargetDAGCombine(ISD::STORE);
   setTargetDAGCombine(ISD::ZERO_EXTEND);
   if (Subtarget->is64Bit())
@@ -1400,7 +1402,7 @@ X86TargetLowering::LowerCallResult(SDValue Chain, SDValue InFlag,
       if (CopyVT == MVT::f64) Opc = isST0 ? X86::FpGET_ST0_64:X86::FpGET_ST1_64;
       if (CopyVT == MVT::f80) Opc = isST0 ? X86::FpGET_ST0_80:X86::FpGET_ST1_80;
       SDValue Ops[] = { Chain, InFlag };
-      Chain = SDValue(DAG.getMachineNode(Opc, dl, CopyVT, MVT::Other, MVT::Flag,
+      Chain = SDValue(DAG.getMachineNode(Opc, dl, CopyVT, MVT::Other, MVT::Glue,
                                          Ops, 2), 1);
       Val = Chain.getValue(0);
 
@@ -2177,7 +2179,7 @@ X86TargetLowering::LowerCall(SDValue Chain, SDValue Callee,
   }
 
   // Returns a chain & a flag for retval copy to use.
-  SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Flag);
+  SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Glue);
   SmallVector<SDValue, 8> Ops;
 
   if (!IsSibcall && isTailCall) {
@@ -6034,7 +6036,7 @@ GetTLSADDR(SelectionDAG &DAG, SDValue Chain, GlobalAddressSDNode *GA,
            SDValue *InFlag, const EVT PtrVT, unsigned ReturnReg,
            unsigned char OperandFlags) {
   MachineFrameInfo *MFI = DAG.getMachineFunction().getFrameInfo();
-  SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Flag);
+  SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Glue);
   DebugLoc dl = GA->getDebugLoc();
   SDValue TGA = DAG.getTargetGlobalAddress(GA->getGlobal(), dl,
                                            GA->getValueType(0),
@@ -6183,7 +6185,7 @@ X86TargetLowering::LowerGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const {
     // Lowering the machine isd will make sure everything is in the right
     // location.
     SDValue Chain = DAG.getEntryNode();
-    SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Flag);
+    SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Glue);
     SDValue Args[] = { Chain, Offset };
     Chain = DAG.getNode(X86ISD::TLSCALL, DL, NodeTys, Args, 2);
 
@@ -6290,7 +6292,7 @@ SDValue X86TargetLowering::BuildFILD(SDValue Op, EVT SrcVT, SDValue Chain,
   SDVTList Tys;
   bool useSSE = isScalarFPTypeInSSEReg(Op.getValueType());
   if (useSSE)
-    Tys = DAG.getVTList(MVT::f64, MVT::Other, MVT::Flag);
+    Tys = DAG.getVTList(MVT::f64, MVT::Other, MVT::Glue);
   else
     Tys = DAG.getVTList(Op.getValueType(), MVT::Other);
 
@@ -7311,9 +7313,26 @@ SDValue X86TargetLowering::LowerSELECT(SDValue Op, SelectionDAG &DAG) const {
     Cond = EmitTest(Cond, X86::COND_NE, DAG);
   }
 
+  // a <  b ? -1 :  0 -> RES = ~setcc_carry
+  // a <  b ?  0 : -1 -> RES = setcc_carry
+  // a >= b ? -1 :  0 -> RES = setcc_carry
+  // a >= b ?  0 : -1 -> RES = ~setcc_carry
+  if (Cond.getOpcode() == X86ISD::CMP) {
+    unsigned CondCode = cast<ConstantSDNode>(CC)->getZExtValue();
+
+    if ((CondCode == X86::COND_AE || CondCode == X86::COND_B) &&
+        (isAllOnes(Op1) || isAllOnes(Op2)) && (isZero(Op1) || isZero(Op2))) {
+      SDValue Res = DAG.getNode(X86ISD::SETCC_CARRY, DL, Op.getValueType(),
+                                DAG.getConstant(X86::COND_B, MVT::i8), Cond);
+      if (isAllOnes(Op1) != (CondCode == X86::COND_B))
+        return DAG.getNOT(DL, Res, Res.getValueType());
+      return Res;
+    }
+  }
+
   // X86ISD::CMOV means set the result (which is operand 1) to the RHS if
   // condition is true.
-  SDVTList VTs = DAG.getVTList(Op.getValueType(), MVT::Flag);
+  SDVTList VTs = DAG.getVTList(Op.getValueType(), MVT::Glue);
   SDValue Ops[] = { Op2, Op1, CC, Cond };
   return DAG.getNode(X86ISD::CMOV, DL, VTs, Ops, array_lengthof(Ops));
 }
@@ -7514,7 +7533,7 @@ X86TargetLowering::LowerDYNAMIC_STACKALLOC(SDValue Op,
   Chain = DAG.getCopyToReg(Chain, dl, X86::EAX, Size, Flag);
   Flag = Chain.getValue(1);
 
-  SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Flag);
+  SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Glue);
 
   Chain = DAG.getNode(X86ISD::WIN_ALLOCA, dl, NodeTys, Chain, Flag);
   Flag = Chain.getValue(1);
@@ -8569,7 +8588,7 @@ SDValue X86TargetLowering::LowerCMP_SWAP(SDValue Op, SelectionDAG &DAG) const {
                     Op.getOperand(3),
                     DAG.getTargetConstant(size, MVT::i8),
                     cpIn.getValue(1) };
-  SDVTList Tys = DAG.getVTList(MVT::Other, MVT::Flag);
+  SDVTList Tys = DAG.getVTList(MVT::Other, MVT::Glue);
   MachineMemOperand *MMO = cast<AtomicSDNode>(Op)->getMemOperand();
   SDValue Result = DAG.getMemIntrinsicNode(X86ISD::LCMPXCHG_DAG, DL, Tys,
                                            Ops, 5, T, MMO);
@@ -8581,7 +8600,7 @@ SDValue X86TargetLowering::LowerCMP_SWAP(SDValue Op, SelectionDAG &DAG) const {
 SDValue X86TargetLowering::LowerREADCYCLECOUNTER(SDValue Op,
                                                  SelectionDAG &DAG) const {
   assert(Subtarget->is64Bit() && "Result not type legalized?");
-  SDVTList Tys = DAG.getVTList(MVT::Other, MVT::Flag);
+  SDVTList Tys = DAG.getVTList(MVT::Other, MVT::Glue);
   SDValue TheChain = Op.getOperand(0);
   DebugLoc dl = Op.getDebugLoc();
   SDValue rd = DAG.getNode(X86ISD::RDTSC_DAG, dl, Tys, &TheChain, 1);
@@ -8775,7 +8794,7 @@ void X86TargetLowering::ReplaceNodeResults(SDNode *N,
     return;
   }
   case ISD::READCYCLECOUNTER: {
-    SDVTList Tys = DAG.getVTList(MVT::Other, MVT::Flag);
+    SDVTList Tys = DAG.getVTList(MVT::Other, MVT::Glue);
     SDValue TheChain = N->getOperand(0);
     SDValue rd = DAG.getNode(X86ISD::RDTSC_DAG, dl, Tys, &TheChain, 1);
     SDValue eax = DAG.getCopyFromReg(rd, dl, X86::EAX, MVT::i32,
@@ -8811,7 +8830,7 @@ void X86TargetLowering::ReplaceNodeResults(SDNode *N,
     SDValue Ops[] = { swapInH.getValue(0),
                       N->getOperand(1),
                       swapInH.getValue(1) };
-    SDVTList Tys = DAG.getVTList(MVT::Other, MVT::Flag);
+    SDVTList Tys = DAG.getVTList(MVT::Other, MVT::Glue);
     MachineMemOperand *MMO = cast<AtomicSDNode>(N)->getMemOperand();
     SDValue Result = DAG.getMemIntrinsicNode(X86ISD::LCMPXCHG8_DAG, dl, Tys,
                                              Ops, 3, T, MMO);
@@ -11513,6 +11532,44 @@ static SDValue PerformADCCombine(SDNode *N, SelectionDAG &DAG,
   return SDValue();
 }
 
+// fold (add Y, (sete  X, 0)) -> adc  0, Y
+//      (add Y, (setne X, 0)) -> sbb -1, Y
+//      (sub (sete  X, 0), Y) -> sbb  0, Y
+//      (sub (setne X, 0), Y) -> adc -1, Y
+static SDValue OptimizeConditonalInDecrement(SDNode *N, SelectionDAG &DAG) {
+  DebugLoc DL = N->getDebugLoc();
+  
+  // Look through ZExts.
+  SDValue Ext = N->getOperand(N->getOpcode() == ISD::SUB ? 1 : 0);
+  if (Ext.getOpcode() != ISD::ZERO_EXTEND || !Ext.hasOneUse())
+    return SDValue();
+
+  SDValue SetCC = Ext.getOperand(0);
+  if (SetCC.getOpcode() != X86ISD::SETCC || !SetCC.hasOneUse())
+    return SDValue();
+
+  X86::CondCode CC = (X86::CondCode)SetCC.getConstantOperandVal(0);
+  if (CC != X86::COND_E && CC != X86::COND_NE)
+    return SDValue();
+
+  SDValue Cmp = SetCC.getOperand(1);
+  if (Cmp.getOpcode() != X86ISD::CMP || !Cmp.hasOneUse() ||
+      !X86::isZeroNode(Cmp.getOperand(1)))
+    return SDValue();
+
+  SDValue CmpOp0 = Cmp.getOperand(0);
+  SDValue NewCmp = DAG.getNode(X86ISD::CMP, DL, MVT::i32, CmpOp0,
+                               DAG.getConstant(1, CmpOp0.getValueType()));
+
+  SDValue OtherVal = N->getOperand(N->getOpcode() == ISD::SUB ? 0 : 1);
+  if (CC == X86::COND_NE)
+    return DAG.getNode(N->getOpcode() == ISD::SUB ? X86ISD::ADC : X86ISD::SBB,
+                       DL, OtherVal.getValueType(), OtherVal,
+                       DAG.getConstant(-1ULL, OtherVal.getValueType()), NewCmp);
+  return DAG.getNode(N->getOpcode() == ISD::SUB ? X86ISD::SBB : X86ISD::ADC,
+                     DL, OtherVal.getValueType(), OtherVal,
+                     DAG.getConstant(0, OtherVal.getValueType()), NewCmp);
+}
 
 SDValue X86TargetLowering::PerformDAGCombine(SDNode *N,
                                              DAGCombinerInfo &DCI) const {
@@ -11523,6 +11580,8 @@ SDValue X86TargetLowering::PerformDAGCombine(SDNode *N,
     return PerformEXTRACT_VECTOR_ELTCombine(N, DAG, *this);
   case ISD::SELECT:         return PerformSELECTCombine(N, DAG, Subtarget);
   case X86ISD::CMOV:        return PerformCMOVCombine(N, DAG, DCI);
+  case ISD::ADD:
+  case ISD::SUB:            return OptimizeConditonalInDecrement(N, DAG);
   case X86ISD::ADC:         return PerformADCCombine(N, DAG, DCI);
   case ISD::MUL:            return PerformMulCombine(N, DAG, DCI);
   case ISD::SHL: