Why cudaStreamCreate gets segmentation fault

Hi all!
There are four Tesla C2075 on my server, so I just tested the simpleMultiGPU in the SDK. Unexpectedly I got a segmentation fault. With cuda-gdb I found this fault occured when cudaStreamCreate is called the second time. Here is the deviceQuery output:
deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 4.2, CUDA Runtime Version = 4.2, NumDevs = 4, Device = Tesla C2075, Device = Tesla C2075
The dirver version is ok, so why the second cudaStreamCreate doesn't work. can anybody help me?

Some code maybe?