Index: lib/Driver/Tools.cpp
===================================================================
--- lib/Driver/Tools.cpp
+++ lib/Driver/Tools.cpp
@@ -12235,6 +12235,96 @@
   assert(TC.getTriple().isNVPTX() && "Wrong platform");
 
   ArgStringList CmdArgs;
+
+  // OpenMP uses nvlink to link cubin files. The result will be embedded in the
+  // host binary by the host linker.
+  assert(!JA.isHostOffloading(Action::OFK_OpenMP) &&
+         "CUDA toolchain not expected for an OpenMP host device.");
+  if (JA.isDeviceOffloading(Action::OFK_OpenMP)) {
+    if (Output.isFilename()) {
+      CmdArgs.push_back("-o");
+      CmdArgs.push_back(Output.getFilename());
+    } else
+      assert(Output.isNothing() && "Invalid output.");
+
+    if (Args.hasArg(options::OPT_g_Flag))
+      CmdArgs.push_back("-g");
+
+    if (Args.hasArg(options::OPT_v))
+      CmdArgs.push_back("-v");
+
+    std::vector<std::string> GPUArchs =
+        Args.getAllArgValues(options::OPT_march_EQ);
+    assert(GPUArchs.size() == 1 && "Exactly one GPU Arch required for ptxas.");
+    const std::string &GPUArch = GPUArchs[0];
+
+    CmdArgs.push_back("-arch");
+    CmdArgs.push_back(Args.MakeArgString(GPUArch));
+
+    // add paths specified in LIBRARY_PATH environment variable as -L options.
+    addDirectoryList(Args, CmdArgs, "-L", "LIBRARY_PATH");
+
+    // add paths for the default clang library path.
+    SmallString<256> DefaultLibPath =
+        llvm::sys::path::parent_path(TC.getDriver().Dir);
+    llvm::sys::path::append(DefaultLibPath, "lib" CLANG_LIBDIR_SUFFIX);
+    CmdArgs.push_back(Args.MakeArgString(Twine("-L") + DefaultLibPath));
+
+    // add linking against library implementing OpenMP calls on NVPTX target
+    CmdArgs.push_back("-lomptarget-nvptx");
+
+    // nvlink relies on the extension used by the input files
+    // to decide what to do. Given that ptxas produces cubin files
+    // we need to copy the input files to a new file with the right
+    // extension.
+    // FIXME: this can be efficiently done by specifying a new
+    // output type for the assembly action, however this would expose
+    // the target details to the driver and maybe we do not want to do
+    // that
+    for (const auto &II : Inputs) {
+
+      if (II.getType() == types::TY_LLVM_IR ||
+          II.getType() == types::TY_LTO_IR ||
+          II.getType() == types::TY_LTO_BC ||
+          II.getType() == types::TY_LLVM_BC) {
+        C.getDriver().Diag(diag::err_drv_no_linker_llvm_support)
+            << getToolChain().getTripleString();
+        continue;
+      }
+
+      // Currently, we only pass the input files to the linker, we do not pass
+      // any libraries that may be valid only for the host.
+      if (!II.isFilename())
+        continue;
+
+      StringRef Name = llvm::sys::path::filename(II.getFilename());
+      std::pair<StringRef, StringRef> Split = Name.rsplit('.');
+      std::string TmpName =
+          C.getDriver().GetTemporaryPath(Split.first, "cubin");
+
+      const char *CubinF =
+          C.addTempFile(C.getArgs().MakeArgString(TmpName.c_str()));
+
+      const char *CopyExec = Args.MakeArgString(getToolChain().GetProgramPath(
+          C.getDriver().IsCLMode() ? "copy" : "cp"));
+
+      ArgStringList CopyCmdArgs;
+      CopyCmdArgs.push_back(II.getFilename());
+      CopyCmdArgs.push_back(CubinF);
+      C.addCommand(
+          llvm::make_unique<Command>(JA, *this, CopyExec, CopyCmdArgs, Inputs));
+
+      CmdArgs.push_back(CubinF);
+    }
+
+    AddOpenMPLinkerScript(getToolChain(), C, Output, Inputs, Args, CmdArgs, JA);
+
+    const char *Exec =
+        Args.MakeArgString(getToolChain().GetProgramPath("nvlink"));
+    C.addCommand(llvm::make_unique<Command>(JA, *this, Exec, CmdArgs, Inputs));
+    return;
+  }
+
   CmdArgs.push_back("--cuda");
   CmdArgs.push_back(TC.getTriple().isArch64Bit() ? "-64" : "-32");
   CmdArgs.push_back(Args.MakeArgString("--create"));
Index: test/Driver/openmp-offload.c
===================================================================
--- test/Driver/openmp-offload.c
+++ test/Driver/openmp-offload.c
@@ -590,6 +590,17 @@
 
 /// ###########################################################################
 
+/// Check cubin file generation and usage by nvlink
+// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps -no-canonical-prefixes %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-CUBIN %s
+
+// CHK-CUBIN: clang{{.*}}" "-o" "{{.*}}-openmp-nvptx64-nvidia-cuda.s"
+// CHK-CUBIN-NEXT: ptxas{{.*}}" "--output-file" "{{.*}}-openmp-nvptx64-nvidia-cuda.o" "{{.*}}-openmp-nvptx64-nvidia-cuda.s"
+// CHK-CUBIN-NEXT: cp{{.*}}-openmp-nvptx64-nvidia-cuda.o" "{{.*}}-openmp-nvptx64-nvidia-cuda-{{.*}}.cubin"
+// CHK-CUBIN-NEXT: nvlink" "-o" "{{.*}}-openmp-nvptx64-nvidia-cuda" "{{.*}}" "{{.*}}-openmp-nvptx64-nvidia-cuda-{{.*}}.cubin"
+
+/// ###########################################################################
+
 /// Check PTXAS is passed -c flag when offloading to an NVIDIA device using OpenMP.
 // RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps -no-canonical-prefixes %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-PTXAS %s