Ron12
May 1, 2012, 8:56am
1
Hi,
I am trying to execute MPI and CUDA code on a cluster. The code works fine on single machine but when I try to execute it on cluster I get error:
error while loading shared libraries: libcudart.so.4: cannot open shared object file: No such file or directory
I checked my PATH and LD_PATH and it looks ok. I have a .bashrc file which contains following entries -
export PATH=$PATH:/usr/local/lib/:/usr/local/lib/openmpi:/usr/local/cuda/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib:/usr/local/lib/openmpi/:/usr/local/cuda/lib/:
All the machines haves same installation of CUDA and OpenMPI.
Can anyone help me with this. This problem is really annoying.
Thanks.
Hi,
Not sure if it’s a typo, but there is a with space in your LD_LIBRARY_PATH definition… Better checking.
Ron12
May 1, 2012, 9:48am
3
There is no space. its just a type :)
Ron12
May 1, 2012, 10:04am
4
I have solved the issue.
Now I use mpirun -x LD_LIBRARY_PATH… to execute the job and everything works like a charm :)
I tried running my MPI + CUDA code by using -x LD_LIBRARY_PATH, but it’s still giving me error while loading shared libraries: libcudart.so.3: cannot open shared object file: No such file or directory .
I ran via terminal: mpirun -machinefile machines -x /usr/local/cuda/lib64 -np 6 ./mpicuda
I have no idea what is wrong with it.
Thanks in advance.
I tried running my MPI + CUDA code by using -x LD_LIBRARY_PATH, but it’s still giving me error while loading shared libraries: libcudart.so.3: cannot open shared object file: No such file or directory .
I ran via terminal: mpirun -machinefile machines -x /usr/local/cuda/lib64 -np 6 ./mpicuda
I have no idea what is wrong with it.
Thanks in advance.
My bad, right now it is working fine. mpirun -machinefile machines -x LD_LIBRARY_PATH -np 6 ./mpicuda
Hi c0mrade,
I am facing the same issue
error while loading shared libraries: libcudart.so.6.0: cannot open shared object file: No such file or directory
Requesting your assistance for resolution.
If you could post a step by step instruction that would be really helpful
You need to set your LD_LIBRARY_PATH environment variable correctly.
How to do this is covered in the linux getting started guide:
[url]CUDA Toolkit Documentation
The above document refers to CUDA 6.5, but the changes for CUDA 6.0 are similar. You can locate a similar document for cuda 6.0 in the doc directory of your cuda install.