Cisco Integrates Ethernet and InfiniBand Management to Support High Performance Data Center Applications and Strengthen InfiniBand as a Data Center Technology
New unified compute fabric framework simplifies management, configuration, and troubleshooting for compute intensive applications
SAN JOSE, Calif., June 27, 2006 - Cisco Systems, Inc. ® announced that it is expanding its portfolio of solutions that support compute-intensive applications by delivering a common framework integrating Ethernet and Infiniband, integrated end-to-end management software, and a new InfiniBand switching platform and operating system software. Together, they provide a single, unified high performance compute fabric, which is protocol-agnostic, while improving management, reliability, and security.
The solution portfolio includes:
* End-to-end management integration: CiscoWorks LMS, Resource Manager Essentials, and Dynamic Fault Manager now provide support for Cisco SFS-7000 Series InfiniBand switches
* Support for open standards such as Open Fabrics and Open MPI,
* New Cisco SFS 7000D Series InfiniBand DDR switches
* New operating system version 2.7 for integrated manageability and security capabilities. OS 2.7 has the same command language interface, command syntax, and many of the same management and security features as Cisco IOS.
By expanding Cisco management and diagnostic tools to include support for InfiniBand switches, Ethernet and Infiniband technologies are integrated under a common framework for network management, application protocols, and application programming interfaces (APIs). This common framework simplifies configuration, management, and troubleshooting for enterprises deploying compute clusters.
“Because Cisco offers an integrated, compute cluster framework, we can take advantage of unified management and intelligence between our Infiniband compute network and Ethernet management network,” said Professor Jerry M. Harris, director of the Center for Computational Earth and Environmental Science, School of Earth Sciences at Stanford. “With these capabilities we can build a reliable, high performance, low latency fabric which will scale to thousands of nodes and can deliver tangible benefits that directly influence our productivity.”
“By supporting open standards for InfiniBand and developing more standardized, comprehensive management tools, Cisco is providing a strong impetus to drive this technology and support its entry into mainstream enterprise data centers,” said Bailey, technical director, at OCF plc. “Now customers with high performance clustered applications can take advantage of integrated management software and view their network infrastructure in a unified way that simplifies configuration and management.”
The new Cisco SFS 7000D Series InfiniBand DDR switches scale from 24 ports to 288 ports and add Double Data Rate (DDR) capabilities that double the bandwidth from 10-Gbps to 20-Gbps and decrease latency to support the most demanding applications. The Cisco High Performance Subnet Manager includes performance and statistics tools capable of reporting on tens of thousands of network ports in under a minute.
Cluster computing and high performance computing are rapidly being adopted by enterprise companies, research institutes, and universities as an alternative to supercomputers to handle projects requiring millions of simultaneously running calculations. Examples of high performance compute-intensive enterprise applications include: financial data analysis, data mining, market data analysis, computational chemistry, database tiers, and computational fluid dynamics. Cisco InfiniBand Server Fabric Switches support some of the world’s largest InfiniBand server clusters, and have been deployed in hundreds of server clusters, including both research and commercial environments in the US, Europe and Asia-Pacific.
“It is compelling to see Cisco combining Ethernet and InfiniBand into a complete solution, with unified management and protocols that work across both fabrics,” said Bernard Stemmelin, network group manager at CEA. “We anticipate that unified fabric management will improve our efficiency in operating a large computer center by reducing complexity in both deployment and management.”
“The needs of the application should drive the choice of technology,” said Krish Ramakrishnan, vice president and general manager, Server Networking and Virtualization Business Unit at Cisco. “Our goal is to provide a protocol agnostic infrastructure for compute and network intensive applications, easily and transparently managed, whether the customer is using Ethernet or InfiniBand or a combination of both. With new open standards for InfiniBand, it is emerging as a mature enterprise-class technology.”
About Cisco Systems
# # #
Cisco, Cisco Systems, and the Cisco Systems logo are registered trademarks or trademarks of Cisco Systems, Inc. and/or its affiliates in the United States and certain other countries. All other trademarks mentioned in this document or Website are the property of their respective owners. The use of the word partner does not imply a partnership relationship between Cisco and any other company. This document is Cisco Public Information.
- Contact Information
- Lee Davis
- Press Contact
- Cisco Systems, Inc.
- Contact via E-mail
This news content was configured by WebWire editorial staff. Linking is permitted.
News Release Distribution and Press Release Distribution Services Provided by WebWire.