Bell, Torvalds usher in next wave of supercomputing
Proponents say the 'Green Destiny' could be a model for future high-performance computing.
IDG News Service - Some of the IT world's top luminaries gathered at Los Alamos National Laboratory in Los Alamos, N.M., Friday to witness the unveiling of a compact supercomputer that proponents say could provide the model for high-performance computing systems in the years ahead.
Gordon Bell, one of the original brains behind the minicomputer, and Linus Torvalds, creator of the Linux operating system, joined a collection of scientists for the unveiling of the supercomputer, a Beowolf cluster called Green Destiny that was built from hundreds of so-called blade servers -- compact servers stripped down to their most basic components.
Using server blades, Los Alamos scientists were able to build a system that is much smaller, consumes less power and is more cost-effective than typical supercomputers, according to Wu-chun Feng, team leader of the Research And Development In Advanced Network Technology group at Los Alamos.
"[Current supercomputers] are not addressing some of the fundamental issues that will be key for this coming decade," Feng said. "Simply doing bigger, faster machines is not good enough anymore."
Unlike many supercomputers that use specialized components and can fill entire buildings, the Green Destiny fits 240 server blades from The Woodlands, Texas-based RLX Technologies Inc. into a server rack that would fit inside most closets. The blades use low-powered processors from Transmeta Corp. and a version of the Linux operating system.
The system consumes far less power than other supercomputers and should also require less maintenance, according to Feng. Using server blades meant trade-offs were made for overall CPU performance and internal bandwidth between components, but the research effort is still in its relatively early stages, he said.
A smaller version of Green Destiny, called MetaBlade, has been up and running for nine months without a failure, unlike other systems, which require "regular maintenance," Feng said.
The engineers who developed the systems said they preferred to use Crusoe processors from Santa Clara, Calif.-based Transmeta because they don't rely on boosting transistor count to achieve faster performance, which they said is the case with chips from rivals Advanced Micro Devices Inc. and Intel Corp.
"In contrast to the traditional transistor-laden and hence power-hungry CPUs from AMD and Intel, the Crusoe CPU is fundamentally software-based with a small hardware core," Feng wrote in a white paper about his project (download PDF).
"Because of the substantial difference in power dissipation, the Transmeta processor requires no active cooling, whereas a Pentium 4 [and most definitely an IA-64] processor can heat to the point of failure if it's not aggressively cooled," he wrote.
Intel and Sunnyvale, Calif.-based AMD were not immediately available to
- An Insightful Approach to Optimizing Mainframe MLC Spend This paper discusses how you can penetrate the complexity of IBM mainframe MLC products and the MLC price model to gain insight into...
- Meeting the Exploding Demand for New IT Services In this eBook, explore the top trends driving the New IT for IT Service Management, and how leading organizations are evolving to focus...
- Hybrid IT-A Low-Risk Path from On-Premise to ITaaS This white paper provides a strategy to move part or all of your ITSM suite to the cloud as a stepping stone to...
- Paving the Windows XP Migration Path to Success Support for Windows XP has ended, leaving organizations with three choices: Windows 8, Windows 7 or a combination. With the right planning and...
- Increase Your Data Center IQ Discover how to improve network efficiency, lower IT costs and more proactively manage your physical, virtual and cloud environments.
- Optimize Data Center Resources and Plan for the Future Eliminate over-provisioning and capacity shortfalls with pro-active capacity optimization. Join us in the evolution from capacity monitoring to capacity optimization in your data... All Hardware White Papers | Webcasts