Index: cfe/trunk/include/clang/Driver/Options.td
===================================================================
--- cfe/trunk/include/clang/Driver/Options.td
+++ cfe/trunk/include/clang/Driver/Options.td
@@ -378,6 +378,8 @@
   Flags<[DriverOption, HelpHidden]>, HelpText<"CUDA GPU architecture">;
 def cuda_host_only : Flag<["--"], "cuda-host-only">,
   HelpText<"Do host-side CUDA compilation only">;
+def cuda_noopt_device_debug : Flag<["--"], "cuda-noopt-device-debug">,
+  HelpText<"Enable device-side debug info generation. Disables ptxas optimizations.">;
 def cuda_path_EQ : Joined<["--"], "cuda-path=">, Group<i_Group>,
   HelpText<"CUDA installation path">;
 def dA : Flag<["-"], "dA">, Group<d_Group>;
Index: cfe/trunk/lib/Driver/Tools.cpp
===================================================================
--- cfe/trunk/lib/Driver/Tools.cpp
+++ cfe/trunk/lib/Driver/Tools.cpp
@@ -10691,15 +10691,20 @@
   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)) {
+    // 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}.
+    //
+    // TODO: Perhaps we should map host -O2 to ptxas -O3. -O3 is ptxas's
+    // default, so it may correspond more closely to the spirit of clang -O2.
 
-  // Map the -O we received to -O{0,1,2,3}.
-  //
-  // TODO: Perhaps we should map host -O2 to ptxas -O3. -O3 is ptxas's default,
-  // so it may correspond more closely to the spirit of clang -O2.
-  if (Arg *A = Args.getLastArg(options::OPT_O_Group)) {
     // -O3 seems like the least-bad option when -Osomething is specified to
     // clang but it isn't handled below.
     StringRef OOpt = "3";
@@ -10725,9 +10730,6 @@
     CmdArgs.push_back("-O0");
   }
 
-  // Don't bother passing -g to ptxas: It's enabled by default at -O0, and
-  // not supported at other optimization levels.
-
   CmdArgs.push_back("--gpu-name");
   CmdArgs.push_back(Args.MakeArgString(gpu_arch));
   CmdArgs.push_back("--output-file");
Index: cfe/trunk/test/Driver/cuda-external-tools.cu
===================================================================
--- cfe/trunk/test/Driver/cuda-external-tools.cu
+++ cfe/trunk/test/Driver/cuda-external-tools.cu
@@ -18,6 +18,10 @@
 // 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
+
 // 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
@@ -59,9 +63,14 @@
 // ARCH64: "-m64"
 // ARCH32: "-m32"
 // OPT0: "-O0"
+// OPT0-NOT: "-g"
 // OPT1: "-O1"
+// OPT1-NOT: "-g"
 // OPT2: "-O2"
+// OPT2-NOT: "-g"
 // OPT3: "-O3"
+// OPT3-NOT: "-g"
+// DBG: "-g" "--dont-merge-basicblocks" "--return-at-end"
 // SM20: "--gpu-name" "sm_20"
 // SM35: "--gpu-name" "sm_35"
 // SM20: "--output-file" "[[CUBINFILE:[^"]*]]"