Red Hat Steps Up with HPC Software Solutions at SC18

Print Friendly, PDF & Email

In this video from SC18 in Dallas, Yan Fisher and Dan McGuan from Red Hat describe the company’s powerful software solutions for HPC and Ai workloads.

All supercomputers on the coveted Top500 list run on Linux, a scalable operating system that has matured over the years to run some of the most critical workloads and in many cases has displaced proprietary operating systems in the process. For the past two decades, Red Hat Enterprise Linux has served as the foundation for building software stacks for many supercomputers. We are looking to continue this trend with the next generation of systems that seek to break the exascale threshold.

At the conference, Red Hat shared insights on new supercomputers, including Summit and Sierra, nascent architectures, like Arm, and building more open computing environments that can further negate the need for proprietary and monolithic implementations. The updated Top500 list is an excellent example of how open technologies continue to proliferate in high performance computing and highlights how the ongoing software optimization work performed on these systems can benefit their performance.

Highlights included:

  • Proven HPC infrastructure. Red Hat Enterprise Linux provides the foundation for many HPC software stacks and is available across multiple hardware architectures. It is at the core of Red Hat OpenStack Platform and Red Hat OpenShift, both of which are part of many HPC environments. There is a lot more to building supercomputer’s software ecosystem than the operating system. Learn about Red Hat’s infrastructure portfolio for science and research.
  • Persistent scale-out storage. Just like the compute nodes have moved away from using proprietary designs, the storage infrastructure has gone through its own transition to a more scalable cost-efficient software-defined file, block and object storage that is independent of hardware. Red Hat delivers open source Ceph and Gluster technologies in their storage portfolio.
  • Emerging HPC technologies. Learn how Red Hat is enabling new hardware architectures, supporting various acceleration technologies and network interconnects, and helping to drive open innovation and standardization in high-performance computing via collaborative community efforts like the OpenHPC Project and industry collaboration that aim at exascale.
  • Performance-sensitive cloud solutions. HPC workloads no longer need to run on bare-metal hardware specifically tailored for this purpose. These workloads can often be deployed in the cloud using software containers that are easier to provision, access, orchestrate and scale as needed, using dedicated container platforms, such as Kubernetes-based Red Hat OpenShift.

Red Hat advocates for open source technology, but it is not just about the software — it is about the culture of systemic collaboration using open standards and continuous innovation. No one company can support that alone and that is why Red Hat relies on a wide landscape of partners to deliver tangible business benefits to our joint customers.

See our complete coverage of SC18

Sign up for our insideHPC Newsletter