Sign up for our newsletter and get the latest HPC news and analysis.
Send me information from insideHPC:


Univa partners with UberCloud

Today Univa announced a new global partnership and reseller agreement with UberCloud. Under terms of the agreement, UberCloud, a leading HPC cloud provider, will resell Univa Grid Engine™ and related Univa products to UberCloud’s growing community of HPC customers across a range of industries, including manufacturing, life sciences and oil and gas.

When organizations run HPC applications in the cloud, the meter starts running immediately,” says Gary Tyreman, CEO of Univa. “It’s not just infrastructure and software costs, but the larger issue of engineering productivity that’s at issue. By deploying packaged HPC applications in containers, and managing them with Univa Grid Engine, users become productive immediately. They can focus on their work rather than spending time troubleshooting complicated HPC software stacks.”

Univa and UberCloud have a long history of collaboration and have been pioneers in applying containers to HPC since the early days of Docker. Containers allow for packable, portable applications for on-premises, cloud and hybrid cloud deployments. UberCloud is the only commercial organization that has built a library of secure, registry-deployed HPC application containers that support key technologies, like Infiniband, MPI, GPUs and NFS essential for many enterprise HPC verticals.

In November of 2017, the two companies announced the integration of UberCloud parallel application containers with Univa Grid Engine, enabling enterprises to automatically dispatch and run MPI parallel jobs in containers, from a user-specified Docker image. Today’s announcement extends this partnership further.

Univa Grid Engine complements UberCloud’s containerized workload strategy. Support for Docker containers is woven tightly into the design of Univa Grid Engine. Key functionality includes container-aware job limit controls, accounting, array jobs, interactive jobs, parallel jobs and support for device mapping between containers and host operating systems, all key prerequisites for effectively managing containerized enterprise HPC applications.

Wolfgang Gentzsch from the UberCloud

It’s like we’ve come full circle with our Univa and UberCloud collaboration,” says Wolfgang Gentzsch, Co-founder, and President of UberCloud. “When I started GENIAS Software in 1990, we developed CODINE, one of the first commercial workload schedulers, under Fritz Ferstl’s technology leadership. When Sun Microsystems acquired our company in 2000, we renamed it Sun Grid Engine which eventually became Oracle Grid Engine until the intellectual property was acquired by Univa in 2013. And here we are, integrating our software container technology into Univa Grid Engine and proudly reselling the whole application self-service stack; simply amazing!”

UberCloud were co-winners with Stanford University in innovative work in life sciences on the living heart project leading to three prestigious awards during the annual SuperComputing 2017 in Denver, Colorado.

We’re delighted to announce this important relationship with UberCloud,” continues Gary Tyreman, CEO of Univa. “UberCloud is a clear leader in packaging applications for consumption by the enterprise, and the availability of Univa Grid Engine on UberCloud will be beneficial to a wide range of customers who increasingly see cloud migration as a key part of their strategy going forward.”

Univa continues to innovate and make it easier for enterprise customers of all kinds to deploy applications to public, private and hybrid clouds. On March 15, 2018, Univa announced the open source Project Tortuga to accelerate the migration to hybrid cloud. In addition, Univa also provides cloud and cloud-native HPC solutions with its Navops product family.

Sign up for our insideHPC Newsletter

Leave a Comment

*

Resource Links: