At last year’s International supercomputing conference (ISC) we noted the trend of Linux underpinning the vast majority of supercomputers that are being built using sophisticated acceleration and interconnect technologies, effectively redefining the term “commodity“ in high performance computing (HPC).
Fast forward to ISC18 and Linux is the defacto standard operating system for all top supercomputers with Red Hat Enterprise Linux powering some of the largest and most intelligent supercomputers on the planet - Summit and Sierra. Red Hat is looking forward to seeing how these two newest US-based supercomputers have scored on the latest iteration of the Top500 list.
In the past, HPC workloads have had to run on custom-built software stacks and overly-specialized hardware. As HPC customers move toward cloud deployments, Red Hat is bringing open technologies to the supercomputing arena, from the world’s leading enterprise Linux platform tailored for HPC workloads to massively scalable, fully open cloud infrastructure, along with the management and automation technologies needed to keep these deployments running smoothly.
Red Hat technologies are at the heart of this transformation and we will be showcasing our latest solutions for HPC at ISC18. Stop by our booth (H-700) to learn about:
- 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 Virtualization and Red Hat OpenStack Platform, both of which are part of many HPC environments.
- Persistent scale-out storage
With the modernization of HPC applications based on containers and the adoption of hybrid cloud infrastructure, many enterprises, and government agencies with HPC workloads are increasingly frustrated with existing storage technologies. Software-defined solutions, like Red Hat Gluster Storage and Red Hat Ceph Storage, provide cost-effective alternatives for scale-out network-attached storage (NAS), containerized applications, and hybrid cloud environments.
- Emerging technologies for highly scalable environments
Large supercomputing sites find Red Hat OpenShift Container Platform and Red Hat Ansible Automation compelling for their science work as they can provide better application portability and system provisioning and automation. Modern applications are more and more frequently involving machine learning, artificial intelligence, and other data science workloads which can make use of hardware such as GPUs. NVIDIA and Red Hat are working hard to enable these workloads and to make them usable with Linux containers for deployment simplification, build automation, and scale.
Also in the booth, you will have an opportunity to experience the power and flexibility of the Red Hat portfolio by way of a virtual reality experience. In this interactive encounter, you will create your own compute cluster using multiple hardware architectures, including Arm, x86_64 and IBM POWER, deploy multiple Red Hat products to solve advanced computational problems and visualize the results.
Red Hat’s chief ARM architect, Jon Masters, will be presenting on the effects of the Spectre and Meltdown vulnerabilities on large size clusters during the show. Be sure to catch his presentation at booth N-210 in the exhibit hall on Wednesday, June 27 from 3:30-4:00 pm.
See demos in our booth, discuss trends, challenges, and opportunities you’re facing with our global team, claim your red fedora and just in time for the FIFA World Cup enter to win soccer-themed barbeque grill that we’re raffling off at the end of each conference day.
For last minute announcements, demo updates and additional information please visit www.red.ht/ISC18. We look forward to seeing you in Frankfurt!
About the author
Yan Fisher is a Global evangelist at Red Hat where he extends his expertise in enterprise computing to emerging areas that Red Hat is exploring.