[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[HTCondor-users] Running MPI jobs in a Singularity container

Hi All,

I recognize this use-case is outside the norm for HTCondor but a new user let me pass along this question.

They are coming from a traditional HPC system and are wondering whether Parallel Universe supports running jobs in Singularity containers? Multi-node capability is of particular interest. If that is possible, are there any special configuration steps the sys-admin needs to take to make it work beyond that listed in the Docs?