Seg Faults in OCL SDK examples when run in cuda-gdb

Hello,

I get SegFaults when running most of the OCL Nvidia SDK examples on cuda-gdb. I have:

cudatoolkit_3.2.16_linux_64_ubuntu10.04

SDK Version: gpucomputingsdk_3.2.16_linux

Driver: 260.19.36 on a GTX580

Executing e.g. oclVectorAdd works fine from console.

But in cuda-gdb I get:

NVIDIA (R) CUDA Debugger

3.2 release

Portions Copyright (C) 2008-2010 NVIDIA Corporation

GNU gdb 6.6

Copyright (C) 2006 Free Software Foundation, Inc.

GDB is free software, covered by the GNU General Public License, and you are

welcome to change it and/or distribute copies of it under certain conditions.

Type "show copying" to see the conditions.

There is absolutely no warranty for GDB.  Type "show warranty" for details.

This GDB was configured as "x86_64-unknown-linux-gnu"...

(no debugging symbols found)

Using host libthread_db library "/lib/libthread_db.so.1".

(cuda-gdb) r

Starting program: /home/scratch/rdiehl/NVIDIA_GPU_Computing_SDK/OpenCL/bin/linux/release/oclVectorAdd

(no debugging symbols found)

(no debugging symbols found)

(no debugging symbols found)

(no debugging symbols found)

(no debugging symbols found)

(no debugging symbols found)

(no debugging symbols found)

(no debugging symbols found)

[Thread debugging using libthread_db enabled]

[New process 14355]

(no debugging symbols found)

/home/scratch/rdiehl/NVIDIA_GPU_Computing_SDK/OpenCL/bin/linux/release/oclVectorAdd Starting...

# of float elements per Array   = 11444777

Global Work Size                = 11444992

Local Work Size                 = 256

# of Work Groups                = 44707

Allocate and Init Host Mem...

[New Thread 139986343360288 (LWP 14355)]

(no debugging symbols found)

(no debugging symbols found)

clGetPlatformID...

clGetDeviceIDs...

[New Thread 139986114221824 (LWP 14359)]

[New Thread 139986105829120 (LWP 14360)]

clCreateContext...

clCreateCommandQueue...

clCreateBuffer...

oclLoadProgSource (VectorAdd.cl)...

clCreateProgramWithSource...

(no debugging symbols found)

clBuildProgram...

clCreateKernel (VectorAdd)...

clSetKernelArg 0 - 3...

clEnqueueWriteBuffer (SrcA and SrcB)...

clEnqueueNDRangeKernel (VectorAdd)...

Program received signal SIGSEGV, Segmentation fault.

[Switching to Thread 139986105829120 (LWP 14360)]

0x00007f510f89fa93 in ?? () from /usr/lib/libcuda.so

So, what’s the matter?

Greets