3

So I am working on a project which is spitting me out that error, after some research showed that the problem lies with the cublas library.

So now I have the following "minimal" problem:

I opened the simpleCUBLAS example out of the NVIDIA CUDA SDK (4.2) to test if I can reproduce the problem .

the programm itself works but VS2010 gives me a similar output:

Eine Ausnahme (erste Chance) bei 0x75e3c41f in simpleCUBLAS.exe: Microsoft C++-Ausnahme: cudaError_enum an Speicherposition 0x003bf704..

7 times

so to my specs:

I use a GTX 460 for computing, compile with sm_20 use VS2010 on Windows 7 64-bit and nvcc --version gives me:

nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2011 NVIDIA Corporation Built on Fri_Jan_13_01:18:37_PST_2012 Cuda compilation tools, release 4.1, V0.2.1221

this is my first time posting here so I apologize for the horrible format it is posted

Marcus K.
  • 31
  • 2
  • According with your CUDA compiler version you have installed the CUDA toolkit 4.1 but you are working with a simpleCUBLAS example of the CUDA SDK 4.2. I'd look at that issue first. – pQB Jan 08 '13 at 18:22
  • that was weird cleaned up my path variables vcc is now release 4.2, V0.2.1221 but the problem remains – Marcus K. Jan 08 '13 at 19:25
  • @MarcusKarlbowski Could you please provide some more information, for example about the line where the exception (ausnahme) is thrown? Maybe, using the CUDA debugger would be helpful in doing that. – Vitality Jan 08 '13 at 21:54
  • Is this like German compiler ? give some English details ...... Eine Ausnahme (erste Chance) bei 0x75e3c41f in simpleCUBLAS.exe: Microsoft C++-Ausnahme: cudaError_enum an Speicherposition 0x003bf704.. – TripleS Jun 16 '13 at 07:55

1 Answers1

1

The observation you are making has to do with an exception that is caught and handled properly within the CUDA libraries. It is, in some cases, a normal part of CUDA GPU operation. As you have observed, your application returns no API errors and runs correctly. If you were not within the VS environment that can report this, you would not observe this at all.

This is considered normal behavior under CUDA. I believe there were some attempts to eliminate it in CUDA 5.5. You might wish to try that, although it's not considered an issue either way.

Robert Crovella
  • 143,785
  • 11
  • 213
  • 257