Nov 15, 2005

Linux Networx Unveils the LS Series of Linux Supersystems

Linux Networx, The Linux Supercomputing Company, has launched the LS Series, a family of Linux Supersystems that blend the price and performance of Linux clusters with the power of legacy supercomputing, in a high-value supercomputing system. The LS Series makes Linux supercomputing available to a broader range of users because of its combination of optimized performance and reduced total cost of ownership. LS Series Supersystems are delivered ready for performance on power-up, eliminating the cost and complexity associated with first-generation supercomputing clusters.

"Every day a more diverse set of supercomputing users are turning to Linux. We designed the LS Series in response to their unique needs," said Robert (Bo) H. Ewald, CEO of Salt Lake-based Linux Networx. "The LS-1 family delivers affordable, manageable systems to users who want to focus on research or design instead of managing cluster infrastructure. The LS/X powers legacy supercomputing applications at a fraction of the cost of proprietary legacy supercomputers -- bringing the value of Linux to the high-end supercomputing market."

The LS Series includes two families, designed to meet the specific needs of midrange or legacy supercomputing application users. The LS-1 is a family of Linux Supersystems that blends application-optimized performance with systems value for third-party and custom applications. The LS/X is an extreme performance Linux Supercomputer that delivers legacy supercomputing performance, solving the most intense computational problems.

LS-1 Supersystems are specifically designed to make supercomputing more affordable and manageable for midrange users. LS-1 Supersystems are delivered as application-optimized systems, and arrive ready for performance at power-up. Users immediately focus on solving computational science and engineering challenges, leveraging a highly optimized system. No special facilities or cluster expertise required. Proven best-of-breed software and hardware configurations eliminate operational complexity and simplify upgrades -- dramatically reducing Total Cost of Ownership. LS-1 Supersystems are ideally suited for third-party applications such as computational fluid dynamics, crash analysis, structural engineering, flow simulation and interactive 3-D visualization.

Thanks to a modular subsystem approach, LS-1 Supersystems are also easily optimized for custom application codes. A range of pre-tested subsystem modules are available -- including varieties of compute, interconnect, visualization, data storage and application acceleration. LS-1 Supersystems are available for early access customers today, with general availability in Q1 2006.

The LS/X is an extreme performance Linux supercomputer -- blending the performance and scale of legacy supercomputing with the price and performance advantage of Linux clusters -- making it the ideal choice for applications that demand ultimate levels of sustained application performance. The LS/X eliminates the performance bottlenecks experienced by first-generation clusters. Ultimate performance technologies for compute, direct-attached memory and interconnect are integrated within the LS/X's scalable, tightly coupled architecture.

Thanks to a resilient and fully fault-tolerant system design, including redundant power, cooling and network architectures, applications run to completion without disruption. The LS/X's integrated switch infrastructure reduces cabling by more than 60 percent -- increasing reliability while simplifying serviceability and improving airflow. LS/X Supercomputers are available for Early Access customers in December 2005.