equivalent to 'cpusets' for gpu's

I work with clusters of computers and manage the nodes with torque and Moab . A user is able to submit a job to a node, and request the amount of resources they need. #The following submits the job foo.sh to 1 node, requesting 8 cores, and 1 gpu qsub foo.sh -l nodes=1:ppn=8:gpus=1 Because it is possible for a user to take more resources than requested, I've enabled the hwloc library (cpusets) to keep users in check. From what I have found, there is no possible way to prevent a user from taking more gpu's than they have requested. **Is there a 'cpuset' equivalent for gpu's?** ---------- *Resources* Moab Documentation Torque Documentation hwloc documentation