[CUDA] Add --no-cuda-noopt-debug, which disables --cuda-noopt-debug.

include/clang/Driver/Options.td

def cuda_host_only : Flag<["--"], "cuda-host-only">,
   HelpText<"Compile CUDA code for device only">;
 def cuda_compile_host_device : Flag<["--"], "cuda-compile-host-device">,
   HelpText<"Compile CUDA code for both host and device (default).  Has no "
            "effect on non-CUDA compilations.">;
 def cuda_gpu_arch_EQ : Joined<["--"], "cuda-gpu-arch=">, Flags<[DriverOption]>,
   HelpText<"CUDA GPU architecture (e.g. sm_35).  May be specified more than once.">;
 def cuda_noopt_device_debug : Flag<["--"], "cuda-noopt-device-debug">,
   HelpText<"Enable device-side debug info generation. Disables ptxas optimizations.">;
+def no_cuda_noopt_device_debug : Flag<["--"], "no-cuda-noopt-device-debug">;
 def cuda_path_EQ : Joined<["--"], "cuda-path=">, Group<i_Group>,
   HelpText<"CUDA installation path">;
 def fcuda_flush_denormals_to_zero : Flag<["-"], "fcuda-flush-denormals-to-zero">,
   Flags<[CC1Option]>, HelpText<"Flush denormal floating point values to zero in CUDA device mode.">;
 def fno_cuda_flush_denormals_to_zero : Flag<["-"], "fno-cuda-flush-denormals-to-zero">;
 def dA : Flag<["-"], "dA">, Group<d_Group>;
 def dD : Flag<["-"], "dD">, Group<d_Group>, Flags<[CC1Option]>,
   HelpText<"Print macro definitions in -E mode in addition to normal output">;

lib/Driver/Tools.cpp

void NVPTX::Assembler::ConstructJob(Compilation &C, const JobAction &JA,
 
   std::vector<std::string> gpu_archs =
       Args.getAllArgValues(options::OPT_march_EQ);
   assert(gpu_archs.size() == 1 && "Exactly one GPU Arch required for ptxas.");
   const std::string& gpu_arch = gpu_archs[0];
 
   ArgStringList CmdArgs;
   CmdArgs.push_back(TC.getTriple().isArch64Bit() ? "-m64" : "-m32");
-  if (Args.getLastArg(options::OPT_cuda_noopt_device_debug)) {
+  if (Args.hasFlag(options::OPT_cuda_noopt_device_debug,
+                   options::OPT_no_cuda_noopt_device_debug, false)) {
     // ptxas does not accept -g option if optimization is enabled, so
     // we ignore the compiler's -O* options if we want debug info.
     CmdArgs.push_back("-g");
     CmdArgs.push_back("--dont-merge-basicblocks");
     CmdArgs.push_back("--return-at-end");
   } else if (Arg *A = Args.getLastArg(options::OPT_O_Group)) {
     // Map the -O we received to -O{0,1,2,3}.
     //

test/Driver/cuda-external-tools.cu

 // RUN: | FileCheck -check-prefix ARCH64 -check-prefix SM20 -check-prefix OPT3 %s
 // RUN: %clang -### -target x86_64-linux-gnu -Ofast -c %s 2>&1 \
 // RUN: | FileCheck -check-prefix ARCH64 -check-prefix SM20 -check-prefix OPT3 %s
 
 // With debugging enabled, ptxas should be run with with no ptxas optimizations.
 // RUN: %clang -### -target x86_64-linux-gnu --cuda-noopt-device-debug -O2 -c %s 2>&1 \
 // RUN: | FileCheck -check-prefix ARCH64 -check-prefix SM20 -check-prefix DBG %s
 
+// --no-cuda-noopt-device-debug overrides --cuda-noopt-device-debug.
+// RUN: %clang -### -target x86_64-linux-gnu --cuda-noopt-debug \
+// RUN:   --no-cuda-noopt-debug -O2 -c %s 2>&1 \
+// RUN: | FileCheck -check-prefix ARCH64 -check-prefix SM20 -check-prefix OPT2 %s
+
 // Regular compile without -O.  This should result in us passing -O0 to ptxas.
 // RUN: %clang -### -target x86_64-linux-gnu -c %s 2>&1 \
 // RUN: | FileCheck -check-prefix ARCH64 -check-prefix SM20 -check-prefix OPT0 %s
 
 // Regular compiles with -Os and -Oz.  For lack of a better option, we map
 // these to ptxas -O3.
 // RUN: %clang -### -target x86_64-linux-gnu -Os -c %s 2>&1 \
 // RUN: | FileCheck -check-prefix ARCH64 -check-prefix SM20 -check-prefix OPT2 %s