Index: include/llvm/CodeGen/SelectionDAG.h
===================================================================
--- include/llvm/CodeGen/SelectionDAG.h
+++ include/llvm/CodeGen/SelectionDAG.h
@@ -1456,6 +1456,11 @@
            isConstantFPBuildVectorOrConstantFP(N);
   }
 
+  /// KeepNodeAlive - Depends on \p ShouldKeep parameter starts or ends
+  /// considering node \p N as alive (i.e. being referenced) even if the node
+  /// is actually dead.
+  void KeepNodeAlive(SDNode *N, bool ShouldKeep);
+
 private:
   void InsertNode(SDNode *N);
   bool RemoveNodeFromCSEMaps(SDNode *N);
@@ -1496,6 +1501,7 @@
 
   std::map<std::pair<std::string, unsigned char>,SDNode*> TargetExternalSymbols;
   DenseMap<MCSymbol *, SDNode *> MCSymbols;
+  SmallDenseMap<SDNode *, std::unique_ptr<HandleSDNode>, 16> PreservedNodes;
 };
 
 template <> struct GraphTraits<SelectionDAG*> : public GraphTraits<SDNode*> {
Index: lib/CodeGen/SelectionDAG/SelectionDAG.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -661,6 +661,9 @@
   // If we have operands, deallocate them.
   removeOperands(N);
 
+  // No need to keep it alive anymore.
+  PreservedNodes.erase(N);
+
   NodeAllocator.Deallocate(AllNodes.remove(N));
 
   // Set the opcode to DELETED_NODE to help catch bugs when node
@@ -966,6 +969,7 @@
   ExternalSymbols.clear();
   TargetExternalSymbols.clear();
   MCSymbols.clear();
+  PreservedNodes.clear();
   std::fill(CondCodeNodes.begin(), CondCodeNodes.end(),
             static_cast<CondCodeSDNode*>(nullptr));
   std::fill(ValueTypeNodes.begin(), ValueTypeNodes.end(),
@@ -7940,6 +7944,19 @@
   return nullptr;
 }
 
+/// KeepNodeAlive - Depends on \p ShouldKeep parameter starts or ends
+/// considering node \p N as alive (i.e. being referenced) even if the node
+/// is actually dead.
+void SelectionDAG::KeepNodeAlive(SDNode *N, bool ShouldKeep) {
+  if (ShouldKeep && PreservedNodes.count(N) == 0) {
+    auto user = std::unique_ptr<HandleSDNode>(new HandleSDNode(SDValue(N, 0)));
+    PreservedNodes.insert(std::make_pair(N, std::move(user)));
+  }
+
+  if (!ShouldKeep)
+    PreservedNodes.erase(N);
+}
+
 #ifndef NDEBUG
 static void checkForCyclesHelper(const SDNode *N,
                                  SmallPtrSetImpl<const SDNode*> &Visited,
Index: lib/Target/NVPTX/NVPTXISelLowering.h
===================================================================
--- lib/Target/NVPTX/NVPTXISelLowering.h
+++ lib/Target/NVPTX/NVPTXISelLowering.h
@@ -565,6 +565,7 @@
   SDValue LowerShiftLeftParts(SDValue Op, SelectionDAG &DAG) const;
 
   SDValue LowerSelect(SDValue Op, SelectionDAG &DAG) const;
+  SDValue LowerLibcallFnNameSymbol(SDValue Op, SelectionDAG &DAG) const;
 
   void ReplaceNodeResults(SDNode *N, SmallVectorImpl<SDValue> &Results,
                           SelectionDAG &DAG) const override;
Index: lib/Target/NVPTX/NVPTXISelLowering.cpp
===================================================================
--- lib/Target/NVPTX/NVPTXISelLowering.cpp
+++ lib/Target/NVPTX/NVPTXISelLowering.cpp
@@ -1305,10 +1305,16 @@
     if (!Outs[OIdx].Flags.isByVal()) {
       if (Ty->isAggregateType() || Ty->isVectorTy()) {
         unsigned align = 0;
-        const CallInst *CallI = cast<CallInst>(CS->getInstruction());
-        // +1 because index 0 is reserved for return type alignment
-        if (!getAlign(*CallI, i + 1, align))
-          align = DL.getABITypeAlignment(Ty);
+        // Call site is empty for libcall.
+        if (CS) {
+          const CallInst *CallI = cast<CallInst>(CS->getInstruction());
+          // +1 because index 0 is reserved for return type alignment
+          if (!getAlign(*CallI, i + 1, align))
+            align = DL.getABITypeAlignment(Ty);
+        }
+        else {
+           align = DL.getABITypeAlignment(Ty);
+        }
         unsigned sz = DL.getTypeAllocSize(Ty);
         O << ".param .align " << align << " .b8 ";
         O << "_";
@@ -1622,6 +1628,9 @@
   GlobalAddressSDNode *Func = dyn_cast<GlobalAddressSDNode>(Callee.getNode());
   unsigned retAlignment = 0;
 
+  // Libcalls doesn't have call site and but they still are NOT indirect calls.  
+  bool isIndirectCall = !Func && CS;
+
   // Handle Result
   if (Ins.size() > 0) {
     SmallVector<EVT, 16> resvtparts;
@@ -1660,7 +1669,12 @@
     }
   }
 
-  if (!Func) {
+  if (isa<ExternalSymbolSDNode>(Callee)) {
+    // Try to find the callee in the current module.
+    Callee = LowerLibcallFnNameSymbol(Callee, DAG);
+  }
+
+  if (isIndirectCall) {
     // This is indirect function call case : PTX requires a prototype of the
     // form
     // proto_0 : .callprototype(.param .b32 _) _ (.param .b32 _);
@@ -1684,7 +1698,7 @@
     Chain, DAG.getConstant((Ins.size() == 0) ? 0 : 1, dl, MVT::i32), InFlag
   };
   // We model convergent calls as separate opcodes.
-  unsigned Opcode = Func ? NVPTXISD::PrintCallUni : NVPTXISD::PrintCall;
+  unsigned Opcode = !isIndirectCall ? NVPTXISD::PrintCallUni : NVPTXISD::PrintCall;
   if (CLI.IsConvergent)
     Opcode = Opcode == NVPTXISD::PrintCallUni ? NVPTXISD::PrintConvergentCallUni
                                               : NVPTXISD::PrintConvergentCall;
@@ -1718,12 +1732,12 @@
   }
   SDVTList CallArgEndVTs = DAG.getVTList(MVT::Other, MVT::Glue);
   SDValue CallArgEndOps[] = { Chain,
-                              DAG.getConstant(Func ? 1 : 0, dl, MVT::i32),
+                              DAG.getConstant(!isIndirectCall, dl, MVT::i32),
                               InFlag };
   Chain = DAG.getNode(NVPTXISD::CallArgEnd, dl, CallArgEndVTs, CallArgEndOps);
   InFlag = Chain.getValue(1);
 
-  if (!Func) {
+  if (isIndirectCall) {
     SDVTList PrototypeVTs = DAG.getVTList(MVT::Other, MVT::Glue);
     SDValue PrototypeOps[] = { Chain,
                                DAG.getConstant(uniqueCallSite, dl, MVT::i32),
@@ -1824,6 +1838,15 @@
                              InFlag, dl);
   uniqueCallSite++;
 
+  if (!CS) {
+    // Unfortunately, libcall expansion does not respect `Chain`...
+    // Our `CALLSEQ_END` becomes dead node (i.e. nobody references it) because
+    // only retval `LoadParam`s will be used after expansion. That means the
+    // node will be deleted at the next iteration of legalization and we have
+    // to make effors to keep it alive.
+    DAG.KeepNodeAlive(Chain.getNode(), true);
+  }
+
   // set isTailCall to false for now, until we figure out how to express
   // tail call optimization in PTX
   isTailCall = false;
@@ -2287,6 +2310,27 @@
   return DAG.getTargetExternalSymbol(SavedStr->c_str(), v);
 }
 
+SDValue
+NVPTXTargetLowering::LowerLibcallFnNameSymbol(SDValue Op,
+                                              SelectionDAG &DAG) const {
+  auto *Symbol = cast<ExternalSymbolSDNode>(Op)->getSymbol();
+  auto *Module = DAG.getMachineFunction().getFunction()->getParent();
+  auto PtrVT = getPointerTy(DAG.getDataLayout());
+
+  if (Module->getFunction(Symbol) != nullptr) {
+    return DAG.getTargetExternalSymbol(Symbol, PtrVT);
+  }
+
+  std::string ErrorStr;
+  raw_string_ostream ErrorFormatter(ErrorStr);
+
+  ErrorFormatter << "Undefined external symbol ";
+  ErrorFormatter << '"' << Symbol << '"';
+  ErrorFormatter.flush();
+
+  report_fatal_error(ErrorStr);
+}
+
 // Check to see if the kernel argument is image*_t or sampler_t
 
 static bool isImageOrSamplerVal(const Value *arg, const Module *context) {
Index: test/CodeGen/NVPTX/libcall.ll
===================================================================
--- /dev/null
+++ test/CodeGen/NVPTX/libcall.ll
@@ -0,0 +1,24 @@
+; RUN: llc < %s -march=nvptx | FileCheck %s
+; Allow to make libcalls that are defined in current module
+
+; An intrinsic
+declare double @llvm.powi.f64(double, i32) nounwind readnone
+
+; Underlying libcall
+define double @__powidf2(double, i32) {
+  ret double 0.0
+}
+
+define double @powi() {
+  ; CHECK:      { // callseq 0, 0
+  ; CHECK:      call.uni (retval0),
+  ; CHECK-NEXT: __powidf2,
+  ; CHECK-NEXT: (
+  ; CHECK-NEXT: param0,
+  ; CHECK-NEXT: param1
+  ; CHECK-NEXT: );
+  ; CHECK-NEXT: ld.param.f64 %fd{{[0-9]+}}, [retval0+0];
+  ; CHECK-NEXT: } // callseq 0
+  %1 = call double @llvm.powi.f64(double 1.0, i32 undef)
+  ret double %1
+}
Index: test/CodeGen/NVPTX/zero-cs.ll
===================================================================
--- test/CodeGen/NVPTX/zero-cs.ll
+++ test/CodeGen/NVPTX/zero-cs.ll
@@ -1,7 +1,7 @@
 ; RUN: not llc < %s -march=nvptx 2>&1 | FileCheck %s
-; used to seqfault and now fails with a "Cannot select"
+; used to seqfault and now fails with a "Undefined external symbol"
 
-; CHECK: LLVM ERROR: Cannot select: {{t7|0x[0-9a-f]+}}: i32 = ExternalSymbol'__powidf2'
+; CHECK: Undefined external symbol "__powidf2"
 define double @powi() {
   %1 = call double @llvm.powi.f64(double 1.000000e+00, i32 undef)
   ret double %1