lssndrbarbieri@gmail.com Alessandro Barbieri ECP-VeloC/VELOC VeloC is a multi-level checkpoint/restart runtime that delivers high performance and scalability for complex heterogeneous storage hierarchies without sacrificing ease of use and flexibility. It is primarily used as a fault-tolerance tool for tightly coupled HPC applications running on supercomputing infrastructure but is essential in many other use cases: suspend-resume, migration, debugging. VeloC is a collaboration between Argonne National Laboratory and Lawrence Livermore National Laboratory as part of the Exascale Computing Project. Use sys-cluster/slurm as resource manager Use ipc as the communication protocol between client library and active backend Use socket as the communication protocol between client library and active backend