The administrator of our server installed a CUDA Driver 3.0 on the root in /syssoft/cuda/bin/. I also find a directory of include, lib, and lib64 there.
nvcc: NVIDIA ® Cuda compiler driver
Copyright © 2005-2009 NVIDIA Corporation
Built on Fri_Feb_19_19:12:59_PST_2010
Cuda compilation tools, release 3.0, V0.2.1221
The problem is I installed SDK at my own home directory, which also has …/C/common/inc and …C/common/lib. Besides, there is another set of these lib and include directories in /usr/local/cuda
Unfortunately All these three sets are partly different, leading to my confusion about in commandline, which to -L and -I.
I encountered a problem, after successfully compile, when I run the program, it reports errors like
test.cu(620) : cudaSafeCall() Runtime API error : no CUDA-capable device is available.
I think this probably due to incompatibility of lib version or driver versions…I’m trying to using lib64 on ubuntu 10.04
Anyone has run into this sort of problem? Thanks