HPC in the cloud with StarCluster

Cluster in the Cloud


Cloud computing has become a viable option for highperformance computing. In this article, we discuss the use case for cloud-based HPC, introduce the StarCluster toolkit, and show how to build a custom machine image for compute nodes.

Virtualization has come a long way. So far, in fact, that it has become a viable option for high-performance computing (HPC) in the cloud.

StarCluster is a toolkit for launching, controlling, and orchestrating clusters of virtual servers within the Amazon Elastic Compute Cloud (EC2) service. The target audience for the StarCluster toolkit is scientists and researchers with a need for cluster computing power. That need may be for parallel computing, data processing tasks in batch jobs, running many iterations of a simulation model, or training and educational purposes.