An Analysis of Conventional & Heterogenous Workloads on Production Supercomputing Resources

Cloud computing setups are a huge investment of resources and personnel to maintain. As
the workload on a system is a major contributing factor to both the performance of the
system and a representation of the needs of system users, a clear understanding of the
workload is critical to organizations that support supercomputing systems. In this paper,
we analyze traces from two production level supercomputers to infer the characteristics of
their workloads, and make observations as to the needs of supercomputer users based on
them. We particularly focus on the usage of graphical processing units by domain
scientists. Based on this analysis, we generate a synthetic workload that can be used for
testing future systems, and make observations as to e"cient resource provisioning.