Red Hat, provider of open-source solutions, today announced that it will be entering into a partnership with several U.S. Department of Energy (DOE) laboratories in order to improve cloud-native standards and practices in high-performance computing (HPC).
Among these labs are Lawrence Berkeley National Laboratory, Lawrence Livermore National Laboratory, and Sandia National Laboratories.
By combining Red Hat’s cloud-native expertise and the laboratories understanding of the unique needs of large-scale HPC deployments, these collaborations are intended to use standardized container platforms to link HPC and cloud applications while creating common usage patterns for industry, enterprise, and HPC deployments.
This partnership will work to address current gaps as well as help to lay groundwork for exascale computing, such as standardization, scale, cloud-native application development, and container storage.
“The HPC community has served as the proving ground for compute-intensive applications, embracing containers early on to help deal with a new set of scientific challenges and problems,” said Chris Wright, senior vice president and chief technology officer at Red Hat. “That led to the lack of standardization across various HPC sites creating barriers to building and deploying containerized applications that can effectively span large-scale HPC, commercial and cloud environments, while also taking advantage of emerging hardware accelerators. Through our collaboration with leading laboratories, we are working to remove these barriers, opening the door to liberating next-generation HPC workloads.”
A few examples of projects between Red Hat and DOE labs include:
- Red Hat and the National Energy Research Scientific Computing Center (NERSC) are collaborating on enhancements to Podman, a daemonless container engine for developing, managing, and running container images on Linux systems, to set it up to replace NERSC’s development runtime, Shifter.
- Red Hat and Sandia National Labs are exploring the deployment scenarios of Kubernetes-based infrastructure at extreme scale in order to bring simpler, well-defined mechanisms for delivering containerized workloads to users.
- Lastly, Lawrence Livermore National Laboratories and Red Hat are working together to try and bring HPC job schedulers to Kubernetes through a standardized interface to help IT teams better manage parallel workflows alongside containerized jobs.