COM

[ComRegisterFunction()]
       public static void RegisterClass(string key)
       {
           StringBuilder sb = new StringBuilder(key);
           sb.Replace(@"HKEY_CLASSES_ROOT\", "");
           RegistryKey k = Registry.ClassesRoot.OpenSubKey(sb.ToString(), true);
           RegistryKey ctrl = k.CreateSubKey("Control");
           ctrl.Close();
           RegistryKey inprocServer32 = k.OpenSubKey("InprocServer32", true);
           inprocServer32.SetValue("CodeBase", Assembly.GetExecutingAssembly().CodeBase);
           inprocServer32.Close();
           k.Close();
           MessageBox.Show("Registered");
       }

       [ComUnregisterFunction()]
       public static void UnregisterClass(string key)
       {
           StringBuilder sb = new StringBuilder(key);
           sb.Replace(@"HKEY_CLASSES_ROOT\", "");
           RegistryKey k = Registry.ClassesRoot.OpenSubKey(sb.ToString(), true);
           k.DeleteSubKey("Control", false);
           k.OpenSubKey("InprocServer32", true);
           k.DeleteSubKey("CodeBase", false);
           k.Close();
           MessageBox.Show("UnRegistered");
       }

I am trying to run a Simple CUDA program which queries the numbers of GPUs in the nodes using Open MPI v1.6.1 (64 bit) in Windows 7 Professional 64 bit Machines. When I run the application in root node, the correct GPU count is getting. But when the same application is tried to run in different nodes remotely using Open MPI, the GPU count is getting as 0, ie, it is showing as No CUDA capable GPU is present in the node.

The root and the nodes having Compute Capability 2.1 capable GPUs. I have built the code with CUDA 4.2. When a normal MPI application is running, it is working correctly.

Is there any special settings required for running a CUDA application in Windows 7 using Open MPI v1.6.1?