High Performance Computing systems offer excellent metrics for speed and efficiency when using bare metal hardware, a high speed interconnect, and parallel applications. This however does not represent a significant portion of scientific computational tasks. In contrast cloud computing has provided management and implementation flexibility at a cost of performance. We therefore suggest two approaches to make HPC resources available in a dynamically reconfigurable hybrid HPC/Cloud architecture. Both can can be achieved with few modifications to existing HPC/Cloud environments. The first approach, from the University of Melbourne, generates a consistent compute node operating system image with variation in the virtual hardware specification. The second approach, from the University of Freiburg, deploys a cloud-client on the HPC compute nodes, so the HPC hardware can run Cloud-Workloads for backfilling free compute slots.

Lev Lafayette (University of Melbourne) and Bernd Wiebelt (Freiburg University), poster and presentation to IEEE eScience, Auckland, October 25, 2017,