Stony Brook, NY, June 17, 2013

Computer Science Associate Professor Radu Sion and collaborators from North Carolina State University (NCSU) were awarded $460k by the National Science Foundation to research enabling cost-effective cloud HPC.

The project examines novel services built on top of public cloud infrastructure to enable cost-effective HPC. The Principal Investigators (PIs), Stony Brook Associate Professor Radu Sion and NCSU Associate Professor Xiaosong Ma, will explore on-demand, elastic, and configurable features of cloud computing to complement traditional supercomputer/cluster platforms. Specifically, this research aims to assess the efficacy of building dynamic cloud-based clusters leveraging the configurability and tiered pricing model of cloud instances. The scientific value of this research lies in the unique use of untapped features of cloud computing for HPC and the strategic adoption of small, cloud-based clusters for the purpose of developing/tuning applications for large supercomputers.

Through this research, the PIs will answer key research questions regarding; (1) automatic workload-specific cloud cluster configuration, (2) cost-aware and contention-aware data and task co-scheduling, and (3) adaptive, integrated cloud instance provisioning and job scheduling, plus workload aggregation for cloud instance rental cost reduction. This research will result in tools that adaptively aggregate, configure, and reconfigure cloud resources for different HPC needs, with the purpose of offering low-cost R&D environments for scalable parallel applications.