In this video from SC15, Bill Mannel from HPE, Charlie Wuischpard from Intel, and Nick Nystrom from the Pittsburgh Supercomputing Center discuss their collaboration for High Performance Computing. Early next year, Hewlett Packard Enterprise will deploy the Bridges supercomputer based on Intel technology for breakthrough data centric computing at PSC.
“Welcome to Bridges, a new concept in HPC – a system designed to support familiar, convenient software and environments for both traditional and non-traditional HPC users. It is a richly connected set of interacting systems offering a flexible mix of gateways (web portals), Hadoop and Spark ecosystems, batch processing and interactivity.”
Bridges will include:
- Compute nodes with hardware-supported shared memory ranging from 128GB to 12TB per node to support genomics, machine learning, graph analytics and other fields where partitioning data is impractical
- GPU nodes to accelerate applications as diverse as machine learning, image processing and materials science
- Database nodes to drive gateways and workflows and to support fusion, analytics, integration and data management
- Webserver nodes to host gateways and provide access to community datasets
- Data transfer nodes with 10 GigE connections to enable data movement between Bridges and XSEDE, campuses, instruments and other advanced cyberinfrastructure