Research and science disciplines are some of the earliest and most prevalent use cases for OpenStack clouds. High-performance computing (HPC) and high-throughput computing (HTC) workloads require massive scaling and cluster networking, access to large volumes of data, and workload and infrastructure manageability. OpenStack software supports these needs today and the development community is rapidly expanding services to fill gaps and scale for exponential future demands.
By managing resources as an OpenStack private cloud, researchers are able to work in environments tailored to their requirements. The dynamic, automated nature of software-defined infrastructure cuts away time wasted on the distractions of setup, and enables researchers to maximize the time they spend on research itself. Explore how to bring the benefits of cloud to HPC workloads in a book, “OpenStack for Scientific Research”, commissioned by the University of Cambridge and supported by the OpenStack Foundation.
The meaning of openness for OpenStack is prescribed by the Four Opens: open source, open design, open development, and open community. Community development and collaboration is a defining OpenStack value for global science organizations. Scientists, faculty, HPC engineers, operators and developers from academia and leading-edge businesses are fully engaged in the vibrant Scientific OpenStack community.
HPC engineers enjoy contributing to OpenStack’s ever-evolving code base to meet stringent workload requirements for all science workloads.
Members of scientific organizations collaborate in various ways:
The Working Group represents and advances the use cases and needs of research and high-performance computing atop OpenStack. Hundreds of members enjoy this great forum for cross-institutional collaboration, at online and in-person events.
Nine research organizations share how they use OpenStack for HPC-specific scenarios in the book, The Crossroads of Cloud and HPC: OpenStack for Scientific Research. These topics are covered in-depth, with case studies: