1 files changed, 61 insertions, 7 deletions

diff --git a/lib/Target/NVPTX/NVPTXISelLowering.cpp b/lib/Target/NVPTX/NVPTXISelLowering.cpp
index 6ea10ea..f1a99d7 100644
--- a/lib/Target/NVPTX/NVPTXISelLowering.cpp
+++ b/lib/Target/NVPTX/NVPTXISelLowering.cpp
@@ -174,10 +174,11 @@ NVPTXTargetLowering::NVPTXTargetLowering(NVPTXTargetMachine &TM)
   setTruncStoreAction(MVT::f64, MVT::f32, Expand);
 
   // PTX does not support load / store predicate registers
-  setOperationAction(ISD::LOAD, MVT::i1, Expand);
+  setOperationAction(ISD::LOAD, MVT::i1, Custom);
+  setOperationAction(ISD::STORE, MVT::i1, Custom);
+
   setLoadExtAction(ISD::SEXTLOAD, MVT::i1, Promote);
   setLoadExtAction(ISD::ZEXTLOAD, MVT::i1, Promote);
-  setOperationAction(ISD::STORE, MVT::i1, Expand);
   setTruncStoreAction(MVT::i64, MVT::i1, Expand);
   setTruncStoreAction(MVT::i32, MVT::i1, Expand);
   setTruncStoreAction(MVT::i16, MVT::i1, Expand);
@@ -402,7 +403,7 @@ std::string NVPTXTargetLowering::getPrototype(Type *retTy,
 
     if (isABI) {
       unsigned align = Outs[i].Flags.getByValAlign();
-      unsigned sz = getTargetData()->getTypeAllocSize(ETy);
+      unsigned sz = getDataLayout()->getTypeAllocSize(ETy);
       O << ".param .align " << align
           << " .b8 ";
       O << "_";
@@ -655,11 +656,11 @@ NVPTXTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
       else {
         if (Func) { // direct call
           if (!llvm::getAlign(*(CS->getCalledFunction()), 0, retAlignment))
-            retAlignment = getTargetData()->getABITypeAlignment(retTy);
+            retAlignment = getDataLayout()->getABITypeAlignment(retTy);
         } else { // indirect call
           const CallInst *CallI = dyn_cast<CallInst>(CS->getInstruction());
           if (!llvm::getAlign(*CallI, 0, retAlignment))
-            retAlignment = getTargetData()->getABITypeAlignment(retTy);
+            retAlignment = getDataLayout()->getABITypeAlignment(retTy);
         }
         SDVTList DeclareRetVTs = DAG.getVTList(MVT::Other, MVT::Glue);
         SDValue DeclareRetOps[] = { Chain, DAG.getConstant(retAlignment,
@@ -856,11 +857,64 @@ LowerOperation(SDValue Op, SelectionDAG &DAG) const {
   case ISD::EXTRACT_SUBVECTOR:
     return Op;
   case ISD::CONCAT_VECTORS: return LowerCONCAT_VECTORS(Op, DAG);
+  case ISD::STORE: return LowerSTORE(Op, DAG);
+  case ISD::LOAD: return LowerLOAD(Op, DAG);
   default:
     llvm_unreachable("Custom lowering not defined for operation");
   }
 }
 
+
+// v = ld i1* addr
+//   =>
+// v1 = ld i8* addr
+// v = trunc v1 to i1
+SDValue NVPTXTargetLowering::
+LowerLOAD(SDValue Op, SelectionDAG &DAG) const {
+  SDNode *Node = Op.getNode();
+  LoadSDNode *LD = cast<LoadSDNode>(Node);
+  DebugLoc dl = Node->getDebugLoc();
+  assert(LD->getExtensionType() == ISD::NON_EXTLOAD) ;
+  assert(Node->getValueType(0) == MVT::i1 &&
+         "Custom lowering for i1 load only");
+  SDValue newLD = DAG.getLoad(MVT::i8, dl, LD->getChain(), LD->getBasePtr(),
+                              LD->getPointerInfo(),
+                              LD->isVolatile(), LD->isNonTemporal(),
+                              LD->isInvariant(),
+                              LD->getAlignment());
+  SDValue result = DAG.getNode(ISD::TRUNCATE, dl, MVT::i1, newLD);
+  // The legalizer (the caller) is expecting two values from the legalized
+  // load, so we build a MergeValues node for it. See ExpandUnalignedLoad()
+  // in LegalizeDAG.cpp which also uses MergeValues.
+  SDValue Ops[] = {result, LD->getChain()};
+  return DAG.getMergeValues(Ops, 2, dl);
+}
+
+// st i1 v, addr
+//    =>
+// v1 = zxt v to i8
+// st i8, addr
+SDValue NVPTXTargetLowering::
+LowerSTORE(SDValue Op, SelectionDAG &DAG) const {
+  SDNode *Node = Op.getNode();
+  DebugLoc dl = Node->getDebugLoc();
+  StoreSDNode *ST = cast<StoreSDNode>(Node);
+  SDValue Tmp1 = ST->getChain();
+  SDValue Tmp2 = ST->getBasePtr();
+  SDValue Tmp3 = ST->getValue();
+  assert(Tmp3.getValueType() == MVT::i1 && "Custom lowering for i1 store only");
+  unsigned Alignment = ST->getAlignment();
+  bool isVolatile = ST->isVolatile();
+  bool isNonTemporal = ST->isNonTemporal();
+  Tmp3 = DAG.getNode(ISD::ZERO_EXTEND, dl,
+                     MVT::i8, Tmp3);
+  SDValue Result = DAG.getStore(Tmp1, dl, Tmp3, Tmp2,
+                                ST->getPointerInfo(), isVolatile,
+                                isNonTemporal, Alignment);
+  return Result;
+}
+
+
 SDValue
 NVPTXTargetLowering::getExtSymb(SelectionDAG &DAG, const char *inname, int idx,
                                 EVT v) const {
@@ -916,7 +970,7 @@ NVPTXTargetLowering::LowerFormalArguments(SDValue Chain,
                                           DebugLoc dl, SelectionDAG &DAG,
                                        SmallVectorImpl<SDValue> &InVals) const {
   MachineFunction &MF = DAG.getMachineFunction();
-  const TargetData *TD = getTargetData();
+  const DataLayout *TD = getDataLayout();
 
   const Function *F = MF.getFunction();
   const AttrListPtr &PAL = F->getAttributes();
@@ -965,7 +1019,7 @@ NVPTXTargetLowering::LowerFormalArguments(SDValue Chain,
     // to newly created nodes. The SDNOdes for params have to
     // appear in the same order as their order of appearance
     // in the original function. "idx+1" holds that order.
-    if (PAL.paramHasAttr(i+1, Attribute::ByVal) == false) {
+    if (PAL.getParamAttributes(i+1).hasAttribute(Attributes::ByVal) == false) {
       // A plain scalar.
       if (isABI || isKernel) {
         // If ABI, load from the param symbol