Integration of high-performance computing into a VCL cloud

  • Authors:
  • Patrick Dreher;Mladen Vouk

  • Affiliations:
  • Massachusetts Institute of Technology, Boston, MA;North Carolina State University, Raleigh, NC

  • Venue:
  • VHPC '13 Proceedings of the 8th Workshop on Virtualization in High-Performance Cloud Computing
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

High-Performance Computing (HPC) services can range from those on peta-flop supercomputers down to smaller computational clusters used for HPC application development, pilot runs and staging. What they all have in common is that traditionally HPC facilities tend to be isolated from the more general scientific computing services. Advent of the cloud computing has started changing that. In this paper we discuss a very successful production-level architecture and policy framework for supporting HPC services within a more general cloud computing infrastructure called VCL. This integrated environment has been operating at NC State since fall 2004. It typically delivers over 14 million HPC CPU hours per year to NC State faculty and students. Our experience is that integration of HPC and non-HPC services in a cloud can substantially reduce the cost of both services.