SpyderByte.com ;Technical Portals 
      
 News & Information Related to Linux High Performance Computing, Linux Clustering and Cloud Computing
Home About News Archives Contribute News, Articles, Press Releases Mobile Edition Contact Advertising/Sponsorship Search Privacy
HPC Vendors
Cluster Quoter (HPC Cluster RFQ)
Hardware Vendors
Software Vendors
HPC Consultants
Training Vendors
HPC Resources
Featured Articles
Cluster Builder
Beginners
Whitepapers
Documentation
Software
Lists/Newsgroups
Books
User Groups & Organizations
HP Server Diagrams
HPC News
Latest News
Newsletter
News Archives
Search Archives
HPC Links
ClusterMonkey.net
Scalability.org
HPCCommunity.org

Beowulf.org
HPC Tech Forum (was BW-BUG)
Gelato.org
The Aggregate
Top500.org
Cluster Computing Info Centre
Coyote Gultch
Dr. Robert Brown's Beowulf Page
FreshMeat.net: HPC Software
SuperComputingOnline
HPC User Forum
GridsWatch
HPC Newsletters
Stay current on Linux HPC news, events and information.
LinuxHPC.org Newsletter

Other Mailing Lists:
Linux High Availability
Beowulf Mailing List
Gelato.org (Linux Itanium)

LinuxHPC.org
Home
About
Contact
Mobile Edition
Sponsorship

Latest News

U. of Nottingham Deploys Level 5 Networks EtherFabric to Accelerate Biophysics Research
Posted by Kenneth Farmer, Wednesday September 28 2005 @ 08:28AM EDT

SUNNYVALE, Calif. -- Sept. 27, 2005 -- Triples the Speed of Applications in the Lab's High Performance Computing Center, Dramatically Improves Time-to-Market and Return-on-Investment

Level 5 Networks, a leading developer of high-speed server interconnect solutions, announced today that University of Nottingham School of Pharmacy has deployed Level 5 Networks' EtherFabric(TM) to eliminate the interconnect processing bottleneck in its high-performance computing (HPC) cluster used to conduct biophysics research. After simply replacing eight out of 16 existing Ethernet cards -- without any other hardware or software changes -- the researchers experienced a 300 percent increase in performance. Such performance enhancements significantly speed time to market in clinical trials, getting medicines out to the masses that need them sooner, and can also reduce a project's overhead and operational costs.

The research work conducted by the Laboratory of Biophysics and Surface Analysis (LBSA) at Nottingham University involves the "folding" nature of proteins and has the potential to lead to important discoveries in the areas of diabetes, Alzheimer's disease, and other ailments. The research is conducted on a 16-node satellite clone of a larger computing cluster comprising 512 Sun V20z nodes, each with two AMD Opteron 248 CPUs, running SUSE Professional Linux 9.0. The research cluster runs standard versions of molecular engineering and simulation applications including AMBER, CHARMM and Moil. Prior to deploying EtherFabric, all the nodes were connected using motherboard gigabit interconnects. As the number of parallel processes increased, however, CPU performance degraded, seriously slowing down research.

"We buy computers to do calculations, not to run networks, but with standard Ethernet, our CPUs simply choked on the high transaction rate and the massive amount of data our research involved," said Dr. Phil Williams, an Advanced Research Fellow in Theoretical Biophysics at the School of Pharmacy, University of Nottingham. "The beauty of EtherFabric is that we were able to install it by simply replacing a card and installing a driver. No new cables. No changes to applications. No problems. And after upgrading only eight of our 16 nodes with EtherFabric, we saw an immediate 300 percent increase in performance, leading to some stunning benefits."

The benefits include enabling the University to do three times the work using the same resources. And this time is precious. With typical pharmaceutical drugs, each day saved in development is worth over $1 million in costs. With three times the performance, the University's running costs for each job (electricity, air conditioning, and maintenance) have been reduced significantly, providing both financial and environmental benefits. In a shared computing environment using multiple-CPU nodes, where multiple researchers rely on the same resources, removing the system overhead for networking from the CPU reduces the impact of one job on another.

"Whether the goal is greater throughput for high-performance computing applications or increased speed for data center operations, IT managers need to hit their targets without the high cost and risk of ripping out their infrastructure, recompiling their applications or updating their operating system," said Dan Karr, President and CEO of Level 5 Networks. "EtherFabric is the only solution that is fully system compatible, which means that any networked computing environment can easily and cost-effectively achieve significant performance gains."

About LBSA

The Laboratory of Biophysics and Surface Analysis (LBSA) in the School of Pharmacy, University of Nottingham, investigates fundamental and applied biomolecular and material problems of relevance to pharmaceutical and healthcare research. This involves cutting-edge multidisciplinary science at the interface of biology, chemistry, pharmaceutics, materials science and physics. Project themes include molecular structure and interactions, biomaterials, nanoscale formulation studies, biomolecular and biopolymer patterning, and computational modeling. For more information, please visit http://www.nottingham.ac.uk/~pazxc/ .

About Level 5 Networks

Level 5 Networks helps Fortune 2000 companies maximize the return on their investment in data center hardware and software by enabling servers to respond more quickly to client requests and to get more processing done in less time. The company's EtherFabric is the only interconnect solution that provides high performance and complete compatibility with existing data center software and hardware infrastructure. Level 5 Networks' founding team members are world-class researchers in high-performance networking who built the world's fastest LAN in 2000. For more information, please visit http://www.level5networks.com .

< Streamline Computing recognized as one of the UK’s top 100 technology companies | High Performance Linux Clustering, Part 1: Clustering Fundamentals >

 

Affiliates

Cluster Monkey

HPC Community


Supercomputing 2010

- Supercomputing 2010 website...

- 2010 Beowulf Bash

- SC10 hits YouTube!

- Louisiana Governor Jindal Proclaims the week of November 14th "Supercomputing Week" in honor of SC10!








Appro: High Performance Computing Resources
IDC: Appro Xtreme-X Supercomputer Blade Solution
Analysis of the Xtreme-X architecture and management system while assessing challenges and opportunities in the technical computing market for blade servers.

Video - The Road to PetaFlop Computing
Explore the Scalable Unit concept where multiple clusters of various sizes can be rapidly built and deployed into production. This new architectural approach yields many subtle benefits to dramatically lower total cost of ownership.
White Paper - Optimized HPC Performance
Multi-core processors provide a unique set of challenges and opportunities for the HPC market. Discover MPI strategies for the Next-Generation Quad-Core Processors.

Appro and the Three National Laboratories
[Appro delivers a new breed of highly scalable, dynamic, reliable and effective Linux clusters to create the next generation of supercomputers for the National Laboratories.

AMD Opteron-based products | Intel Xeon-based products



Home About News Archives Contribute News, Articles, Press Releases Mobile Edition Contact Advertising/Sponsorship Search Privacy
     Copyright © 2001-2013 LinuxHPC.org
Linux is a trademark of Linus Torvalds
All other trademarks are those of their owners.
    
  SpyderByte.com ;Technical Portals