Portable Submission Interface for Jobs
A Python abstraction layer over cluster schedulers
Write Scheduler Agnostic HPC Applications
Use a unified API to run your HPC application virtually
anywhere. Tested on a wide variety of clusters,
translates abstract job specifications into concrete
scripts and commands to send to the scheduler.
PSI/J runs entirely in user space
There is no need to wait for infrequent deployment cycles.
The HPC world can be rather dynamic and the ability to
quickly react to experimental changes in cluster
environments is essential.
Use built-in or community contributed plugins
It is virtually impossible for a single entity to provide
stable and tested adapters to all clusters and schedulers.
That is why PSI/J enables
and encourages community contributions to scheduler
adapters, testbeds, and specific cluster knowledge.
PSI/J has a rich HPC legacy
PSI/J was built by a team with decades of experience building workflow systems for large scale computing.