[llvm][nvptx] add atomicity to counter in ISelLowering

[tpopp]

Summary

Previously uniqueCallSite could have race conditions between different
threads. Now it is accessed with an atomic RMW and will be unique
between different threads.

[tpopp]

Match LLVM naming convention.

[tpopp]

Another naming convention correction.

[bkramer]

llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp

68

Unnecessary, globals are always initialized to 0.

1246

Just pass unsigned by value

llvm/lib/Target/NVPTX/NVPTXISelLowering.h

SDValue LowerFormalArguments(SDValue Chain, CallingConv::ID CallConv,
                                const SDLoc &dl, SelectionDAG &DAG,
                                SmallVectorImpl<SDValue> &InVals) const override;
 
   SDValue LowerCall(CallLoweringInfo &CLI,
                     SmallVectorImpl<SDValue> &InVals) const override;
 
   std::string getPrototype(const DataLayout &DL, Type *, const ArgListTy &,
                            const SmallVectorImpl<ISD::OutputArg> &,
-                           MaybeAlign retAlignment, const CallBase &CB) const;
+                           MaybeAlign retAlignment, const CallBase &CB,
+                           unsigned UniqueCallSite) const;
 
   SDValue LowerReturn(SDValue Chain, CallingConv::ID CallConv, bool isVarArg,
                       const SmallVectorImpl<ISD::OutputArg> &Outs,
                       const SmallVectorImpl<SDValue> &OutVals, const SDLoc &dl,
                       SelectionDAG &DAG) const override;
 
   void LowerAsmOperandForConstraint(SDValue Op, std::string &Constraint,
                                     std::vector<SDValue> &Ops,

llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp

 #include <string>
 #include <utility>
 #include <vector>
 
 #define DEBUG_TYPE "nvptx-lower"
 
 using namespace llvm;
 
-static unsigned int uniqueCallSite = 0;
+static std::atomic<unsigned> GlobalUniqueCallSite;
 
 static cl::opt<bool> sched4reg(
     "nvptx-sched4reg",
     cl::desc("NVPTX Specific: schedule for register pressue"), cl::init(false));
 
 static cl::opt<unsigned>
 FMAContractLevelOpt("nvptx-fma-level", cl::ZeroOrMore, cl::Hidden,
                     cl::desc("NVPTX Specific: FMA contraction (0: don't do it"
NVPTXTargetLowering::LowerGlobalAddress(SDValue Op, SelectionDAG &DAG) const {
   auto PtrVT = getPointerTy(DAG.getDataLayout(), GAN->getAddressSpace());
   Op = DAG.getTargetGlobalAddress(GAN->getGlobal(), dl, PtrVT);
   return DAG.getNode(NVPTXISD::Wrapper, dl, PtrVT, Op);
 }
 
 std::string NVPTXTargetLowering::getPrototype(
     const DataLayout &DL, Type *retTy, const ArgListTy &Args,
     const SmallVectorImpl<ISD::OutputArg> &Outs, MaybeAlign retAlignment,
-    const CallBase &CB) const {
+    const CallBase &CB, unsigned UniqueCallSite) const {
   auto PtrVT = getPointerTy(DL);
 
   bool isABI = (STI.getSmVersion() >= 20);
   assert(isABI && "Non-ABI compilation is not supported");
   if (!isABI)
     return "";
 
   std::stringstream O;
-  O << "prototype_" << uniqueCallSite << " : .callprototype ";
+  O << "prototype_" << UniqueCallSite << " : .callprototype ";
 
   if (retTy->getTypeID() == Type::VoidTyID) {
     O << "()";
   } else {
     O << "(";
     if (retTy->isFloatingPointTy() || (retTy->isIntegerTy() && !retTy->isIntegerTy(128))) {
       unsigned size = 0;
       if (auto *ITy = dyn_cast<IntegerType>(retTy)) {
SDValue NVPTXTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
   const CallBase *CB = CLI.CB;
   const DataLayout &DL = DAG.getDataLayout();
 
   bool isABI = (STI.getSmVersion() >= 20);
   assert(isABI && "Non-ABI compilation is not supported");
   if (!isABI)
     return Chain;
 
+  unsigned UniqueCallSite = GlobalUniqueCallSite.fetch_add(1);
   SDValue tempChain = Chain;
-  Chain = DAG.getCALLSEQ_START(Chain, uniqueCallSite, 0, dl);
+  Chain = DAG.getCALLSEQ_START(Chain, UniqueCallSite, 0, dl);
   SDValue InFlag = Chain.getValue(1);
 
   unsigned paramCount = 0;
   // Args.size() and Outs.size() need not match.
   // Outs.size() will be larger
   //   * if there is an aggregate argument with multiple fields (each field
   //     showing up separately in Outs)
   //   * if there is a vector argument with more than typical vector-length
if (isIndirectCall) {
     // This is indirect function call case : PTX requires a prototype of the
     // form
     // proto_0 : .callprototype(.param .b32 _) _ (.param .b32 _);
     // to be emitted, and the label has to used as the last arg of call
     // instruction.
     // The prototype is embedded in a string and put as the operand for a
     // CallPrototype SDNode which will print out to the value of the string.
     SDVTList ProtoVTs = DAG.getVTList(MVT::Other, MVT::Glue);
-    std::string Proto = getPrototype(DL, RetTy, Args, Outs, retAlignment, *CB);
+    std::string Proto =
+        getPrototype(DL, RetTy, Args, Outs, retAlignment, *CB, UniqueCallSite);
     const char *ProtoStr =
       nvTM->getManagedStrPool()->getManagedString(Proto.c_str())->c_str();
     SDValue ProtoOps[] = {
       Chain, DAG.getTargetExternalSymbol(ProtoStr, MVT::i32), InFlag,
     };
     Chain = DAG.getNode(NVPTXISD::CallPrototype, dl, ProtoVTs, ProtoOps);
     InFlag = Chain.getValue(1);
   }
SDValue NVPTXTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
   SDValue CallArgEndOps[] = { Chain,
                               DAG.getConstant(isIndirectCall ? 0 : 1, dl, MVT::i32),
                               InFlag };
   Chain = DAG.getNode(NVPTXISD::CallArgEnd, dl, CallArgEndVTs, CallArgEndOps);
   InFlag = Chain.getValue(1);
 
   if (isIndirectCall) {
     SDVTList PrototypeVTs = DAG.getVTList(MVT::Other, MVT::Glue);
-    SDValue PrototypeOps[] = { Chain,
-                               DAG.getConstant(uniqueCallSite, dl, MVT::i32),
-                               InFlag };
+    SDValue PrototypeOps[] = {
+        Chain, DAG.getConstant(UniqueCallSite, dl, MVT::i32), InFlag};
     Chain = DAG.getNode(NVPTXISD::Prototype, dl, PrototypeVTs, PrototypeOps);
     InFlag = Chain.getValue(1);
   }
 
   SmallVector<SDValue, 16> ProxyRegOps;
   SmallVector<Optional<MVT>, 16> ProxyRegTruncates;
 
   // Generate loads from param memory/moves from registers for result
for (unsigned i = 0, e = VTs.size(); i != e; ++i) {
 
         // Cleanup
         VecIdx = -1;
         LoadVTs.clear();
       }
     }
   }
 
-  Chain = DAG.getCALLSEQ_END(Chain,
-                             DAG.getIntPtrConstant(uniqueCallSite, dl, true),
-                             DAG.getIntPtrConstant(uniqueCallSite + 1, dl,
-                                                   true),
-                             InFlag, dl);
+  Chain = DAG.getCALLSEQ_END(
+      Chain, DAG.getIntPtrConstant(UniqueCallSite, dl, true),
+      DAG.getIntPtrConstant(UniqueCallSite + 1, dl, true), InFlag, dl);
   InFlag = Chain.getValue(1);
-  uniqueCallSite++;
 
   // Append ProxyReg instructions to the chain to make sure that `callseq_end`
   // will not get lost. Otherwise, during libcalls expansion, the nodes can become
   // dangling.
   for (unsigned i = 0; i < ProxyRegOps.size(); ++i) {
     SDValue Ret = DAG.getNode(
       NVPTXISD::ProxyReg, dl,
       DAG.getVTList(ProxyRegOps[i].getSimpleValueType(), MVT::Other, MVT::Glue),