SCIENCE

Bright Computing has announced that the company has entered into an OEM agreement with Cray. This agreement enables Cray to include Bright Cluster Manager as an integral feature of its high-performance external solutions for large HPC installations. Bright Cluster Manager provides a centralized monitoring and management solution for power management, image management, trouble-shooting, system provisioning, workload management and system health monitoring. Cray will leverage Bright Cluster Manager’s flexibilities to offer its customers a combination of these services and additional services, such as automated Lustre server failover.

This solution has already been deployed on large HPC installations, including the external services piece of the Cray XE6 supercomputer at the United States Department of Energy's National Energy Research Scientific Computing Center (NERSC). Cray plans to deploy Bright Cluster Manager on new Cray systems that will be equipped with large external services solutions, and will soon begin upgrading a number of existing large installations around the world.

“Bright Cluster Manager is a major differentiator and enabler for Cray’s external solutions,” said Chuck Morreale, vice president of Cray’s custom engineering group. “Bright provides easy-to-use, yet powerful provisioning, monitoring, and management capabilities for our external servers, and provides the flexibility to deploy additional automated management services to meet the specific needs of each customer. We are now able to log important data that was not previously captured – allowing performance analysts and remote support engineers to make more informed decisions.”

Data storage is an important external HPC solution for Cray and the company has developed systems that manage incredibly complex data-management tasks – addressing a key opportunity in HPC. According to IDC, the market for storage in HPC is growing faster than the demand for HPC servers, reaching $4.9 billion in 2014, or nearly 40% of the investment in HPC servers. The driver behind this growth is the data explosion in HPC, data intensive computing, and the proliferation of iterative methods and problems being studied at larger scales. (Source: IDC Predictions 2011: Worldwide High-Performance Computing webcast, 16 February 2011)

“Cray’s decision to choose Bright Cluster Manager for their external solutions is a strong endorsement of the versatility of and reliability of our cluster management capabilities,” said Dr. Matthijs van Leeuwen, Founder and CEO of Bright Computing. “This use of Bright in important HPC installations for storage servers, login servers, data movers, pre-and post-processing servers is validation of both Cray and Bright’s ability to meet the increasingly complex requirements of HPC users.”