Index: llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXTargetStreamer.h
===================================================================
--- llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXTargetStreamer.h
+++ llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXTargetStreamer.h
@@ -24,6 +24,9 @@
   NVPTXTargetStreamer(MCStreamer &S);
   ~NVPTXTargetStreamer() override;
 
+  /// Outputs the list of the DWARF '.file' directives to the streamer.
+  void outputDwarfFileDirectives();
+
   /// Record DWARF file directives for later output.
   /// According to PTX ISA, CUDA Toolkit documentation, 11.5.3. Debugging
   /// Directives: .file
Index: llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXTargetStreamer.cpp
===================================================================
--- llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXTargetStreamer.cpp
+++ llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXTargetStreamer.cpp
@@ -25,6 +25,12 @@
 
 NVPTXTargetStreamer::~NVPTXTargetStreamer() = default;
 
+void NVPTXTargetStreamer::outputDwarfFileDirectives() {
+  for (const std::string &S : DwarfFiles)
+    getStreamer().EmitRawText(S.data());
+  DwarfFiles.clear();
+}
+
 void NVPTXTargetStreamer::emitDwarfFileDirective(StringRef Directive) {
   DwarfFiles.emplace_back(Directive);
 }
@@ -82,9 +88,7 @@
     OS << "//\t}\n";
   if (isDwarfSection(FI, Section)) {
     // Emit DWARF .file directives in the outermost scope.
-    for (const std::string &S : DwarfFiles)
-      getStreamer().EmitRawText(S.data());
-    DwarfFiles.clear();
+    outputDwarfFileDirectives();
     OS << "//\t.section";
     Section->PrintSwitchToSection(*getStreamer().getContext().getAsmInfo(),
                                   FI->getTargetTriple(), OS, SubSection);
Index: llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
===================================================================
--- llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
+++ llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
@@ -16,6 +16,7 @@
 #include "InstPrinter/NVPTXInstPrinter.h"
 #include "MCTargetDesc/NVPTXBaseInfo.h"
 #include "MCTargetDesc/NVPTXMCAsmInfo.h"
+#include "MCTargetDesc/NVPTXTargetStreamer.h"
 #include "NVPTX.h"
 #include "NVPTXMCExpr.h"
 #include "NVPTXMachineFunctionInfo.h"
@@ -938,6 +939,10 @@
   if (HasDebugInfo)
     OutStreamer->EmitRawText("//\t}");
 
+  // Output last DWARF .file directives, if any.
+  static_cast<NVPTXTargetStreamer *>(OutStreamer->getTargetStreamer())
+      ->outputDwarfFileDirectives();
+
   return ret;
 
   //bool Result = AsmPrinter::doFinalization(M);
Index: llvm/trunk/test/DebugInfo/NVPTX/debug-file-loc-only.ll
===================================================================
--- llvm/trunk/test/DebugInfo/NVPTX/debug-file-loc-only.ll
+++ llvm/trunk/test/DebugInfo/NVPTX/debug-file-loc-only.ll
@@ -0,0 +1,48 @@
+; RUN: llc < %s -mtriple=nvptx64-nvidia-cuda | FileCheck %s
+
+; // Bitcode in this test case is reduced version of compiled code below:
+;extern "C" {
+;#line 1 "/source/dir/foo.h"
+;__device__ void foo() {}
+;#line 2 "/source/dir/bar.cu"
+;__device__ void bar() {}
+;}
+
+; CHECK: .target sm_{{[0-9]+}}//, debug
+
+; CHECK: .visible .func foo()
+; CHECK: .loc [[FOO:[0-9]+]] 1 31
+; CHECK:  ret;
+; CHECK: .visible .func bar()
+; CHECK: .loc [[BAR:[0-9]+]] 2 31
+; CHECK:  ret;
+
+define void @foo() !dbg !4 {
+bb:
+  ret void, !dbg !10
+}
+
+define void @bar() !dbg !7 {
+bb:
+  ret void, !dbg !11
+}
+
+; CHECK-DAG: .file [[FOO]] "{{.*}}foo.h"
+; CHECK-DAG: .file [[BAR]] "{{.*}}bar.cu"
+
+; CHECK-NOT: .section .debug{{.*}}
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!8, !9}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, producer: "", isOptimized: false, runtimeVersion: 0, emissionKind: DebugDirectivesOnly, enums: !2)
+!1 = !DIFile(filename: "bar.cu", directory: "/source/dir")
+!2 = !{}
+!4 = distinct !DISubprogram(name: "foo", scope: !5, file: !5, line: 1, type: !6, isLocal: false, isDefinition: true, scopeLine: 1, flags: DIFlagPrototyped, isOptimized: false, unit: !0, retainedNodes: !2)
+!5 = !DIFile(filename: "foo.h", directory: "/source/dir")
+!6 = !DISubroutineType(types: !2)
+!7 = distinct !DISubprogram(name: "bar", scope: !1, file: !1, line: 2, type: !6, isLocal: false, isDefinition: true, scopeLine: 2, flags: DIFlagPrototyped, isOptimized: false, unit: !0, retainedNodes: !2)
+!8 = !{i32 2, !"Dwarf Version", i32 2}
+!9 = !{i32 2, !"Debug Info Version", i32 3}
+!10 = !DILocation(line: 1, column: 31, scope: !4)
+!11 = !DILocation(line: 2, column: 31, scope: !7)