High Performance Computing Virtualization Drives Coventry U Engineering Program

UK-based Coventry University has implemented a virtualized environment in its automotive engineering program that has reduced management of its high-performance computing infrastructure.

The university implemented vSMP Foundation from ScaleMP. The institution reported that the new platform allows the Automotive Engineering Applied Research Group to run different types of applications in its virtualized environments, including OpenMP, MPI, and legacy code, while gaining better performance over the traditional high performance computing (HPC) system Coventry previously had in place.

To keep up with the increased demand from faculty and students, Coventry's computation center began looking to upgrade its high-performance computing infrastructure. As part of this initiative, the computation center decided to add additional symmetric multiprocessing (SMP) capability for running simulations requiring large amounts of memory in addition to running distributed (MPI-parallel) applications. Although the university wanted to move to an x86 architecture-based infrastructure to lower hardware costs, it expected to invest in both a cluster infrastructure as well as an SMP system to address its computing requirements.

Jim Tabor, head of the university's high performance computing center, evaluated vSMP Foundation specifically for its ability to address both needs: It could aggregate multiple server nodes into a single virtual system and it could support large shared memory applications and parallel applications on the same underlying IT infrastructure.

"We are scientists, not IT experts," said Carol Roberts, research fellow in the research group. "We need a system that works well with our software and frees up time to allow us to focus on what we consider to be the most demanding theoretical and modeling problems. We want the system to work flawlessly at a high level of performance so that we are unaware of it."

She said that ScaleMP's aggregation platform performs well with a wide range of applications. "By providing a single virtual system, vSMP Foundation technology significantly reduces the IT complexity and enables access to large shared memory for our most demanding larger simulations when needed."

vSMP Foundation supports aggregation of up to 16 servers into a single virtual SMP system with up to 4 TB of shared memory and up to 128 cores.

About the Author

Dian Schaffhauser is a former senior contributing editor for 1105 Media's education publications THE Journal, Campus Technology and Spaces4Learning.

Featured

  • CIS Sandbox Tutor Eli Blouin at Bentley University imagines a future technology learning partner that supports curiosity, critical thinking, feedback, and personalized learning.

    Student Voices: Technology as a Future Learning Partner

    A data analytics and marketing major at Bentley University and a distinguished lecturer at the university explore the future of "technology learning partners" — technologies that participate in the learning process by asking questions and giving feedback, not just information search results.

  • Abstract energetic glowing lines with particles

    Meta Steps Up Enterprise AI Ambitions with Muse Spark Launch

    Meta has announced the launch of Muse Spark 1.1, a multimodal reasoning model designed for agentic AI, alongside a new Meta Model API that gives developers access to the model for the first time.

  • Businessman using laptop analyzing data and growth graph chart

    AI Budgets in Education Show No Sign of Decline

    The vast majority of education organizations (98%) expect their AI infrastructure budgets to either increase or hold steady over the next year, according to a recent report from cloud storage provider Wasabi.

  • Dana Brunson facilitates a roundtable discussion with research and higher education IT leaders

    Internet2: Closing the Access Gap for Research Cyberinfrastructure

    Internet2's Research Engagement Team brings CIOs and other campus technology leadership together with research computing and data facilitators, forming a community that enables research cyberinfrastructure at institutions of all types and sizes.