I tried running the gpu compiled code and am getting the following error:
“./kspaceFirstOrder3D-CUDA: error while loading shared libraries: libmvec.so.1: cannot open shared object file: No such file or directory”
I can't find this library, and my google searches are coming up empty. Does anyone have an idea where I might find it?
I am also not sure I am doing this properly.
Here is how I log into a node with a gpu:
[njm7@login02 ~]$ srun -n 1 --pty -t 1:00:00 -p gpu --gres=gpu:1 bash
srun: job 11701595 queued and waiting for resources
srun: job 11701595 has been allocated resources
[njm7@compute-g-16-175 ~]$ module load gcc/6.2.0
[njm7@compute-g-16-175 ~]$ module load cuda/9.0
[njm7@compute-g-16-175 ~]$ module load matlab/2017a
[njm7@compute-g-16-175 ~]$ LD_PRELOAD='/n/app/gcc/6.2.0/lib64/libstdc++.so.6.0.22' matlab -nodesktop
Here is what I get when I try to run the simulation using the compiled gpu binary:
Running k-Wave simulation...
start time: 05-Apr-2018 10:59:25
reference sound speed: 3274.9813m/s
dt: 7.6889ns, t_end: 119.708us, time steps: 15570
input grid size: 44 by 44 by 492 grid points (14.5055 by 14.5055 by 162.1978mm)
maximum supported frequency: 2.275MHz
expanding computational grid...
computational grid size: 64 by 64 by 512 grid points
precomputation completed in 1.14s
saving input files to disk...
completed in 2.1249s
system('export LD_LIBRARY_PATH=; cd /home/njm7/MFILES/k-Wave/binaries/; ./kspaceFirstOrder3D-CUDA -i /home/njm7/DATA/TMPat1Element0054a_105925.mat_input.h5 -o /home/njm7/DATA/TMPat1Element0054a_105925.mat_output.h5 --p_raw -s 14542' ,'-echo');
./kspaceFirstOrder3D-CUDA: error while loading shared libraries: libmvec.so.1: cannot open shared object file: No such file or directory
Is this the right way to do this?