ClearSpeed Demonstrates Fastest Chip on AMD- and Intel-Based Workstations at ISC; Demonstration Advances AMD and Intel Chips into Highest Levels of HPC Performance, without Heat or Energy Penalty

HEIDELBERG, Germany—(BUSINESS WIRE)—June 21, 2005— ClearSpeed Technology (LSE: CSD), a developer of high-performance, low-power, programmable microprocessor solutions, today announced the first public demonstration of the CSX600, the highest performance 64-bit floating point processor, at the International Supercomputer Conference (ISC) in Heidelberg. The CSX600 is designed as a co-processor and delivers a sustained performance of up to 25 Gigaflops (GFLOPS) at less than 10 watts.

The ClearSpeed demonstration systems include an IBM (NYSE:IBM) IntelliStation with AMD (NYSE:AMD) dual-Opteron processors and a second box with dual-Xeon Intel (Nasdaq:INTC) processors. One system is running two dual co-processor CSX600 boards, and the second system includes one CSX600 board. At 100 GFLOPS (sustained with two boards) and 50 GFLOPS (sustained with one board), these systems are believed to demonstrate the highest ratio of performance per watt ever achieved in workstations.

"Clusters based on AMD and Intel processors today dominate the HPC category because of their outstanding combination of performance and low cost," said Tom Beese, ClearSpeed CEO. "ClearSpeed extends this model by enabling further substantial increases in performance without significant cost or energy increases."

The demonstrations show the acceleration of BLAS, FFTs, GROMACS, Mathematica and MATLAB, which are all standard applications that apply to a wide range of industries including the sciences, finance, aerospace, automotive, and oil and gas. The CSX600 prototype demonstration is available for public review in the ClearSpeed booth, C01.

"This is a significant achievement by ClearSpeed," said Dave Turek, vice president of Deep Computing, IBM. "We are very pleased that the company has chosen to demonstrate the potential of the CSX600 on our IntelliStation at Heidelberg."

As the first commercial ClearSpeed product, the CSX600 will offer 64-bit, IEEE 754 double-precision floating point reaching 25 GFLOPS sustained performance (DGEMM), while the dual-chip CSX600 board will offer 50 GFLOPS sustained. These boards are in a standard PCI-X form factor and can be slotted in to new and existing workstations, servers and clusters.

ClearSpeed is working with the HPC community and software vendors to port and accelerate computationally-intensive applications and proprietary codes through software tools and standard libraries.

"Intel's leading processor-based HPC platforms are the most widely deployed across high performance computing," said Ben Bennett, manager of Intel's World Wide HPC Program Office. "We see ClearSpeed's CSX600 as a complementary architecture enhancing solutions for industries such as engineering design, bio-sciences and research."

Given its compatibility with PCI-X, ClearSpeed boards can be quickly installed in existing workstations and servers to provide significant increases in performance. Such system upgrades, while offering up to a 10x increase in performance, can be achieved without additional power or cooling due to the efficiency of ClearSpeed's architecture.

"ClearSpeed brings an exciting technology to our new and existing customers and makes a very interesting proposition for extending the life of existing HPC Clusters," said Terry Fisher, business development manager of Compusys, which today announced a partnership with ClearSpeed. "The potential is that this technology will change the way we think about HPC forever."

Product availability and support

Details on product availability of the ClearSpeed CSX600 and support will be released in 2005. Currently standard libraries, tools and other resources are available to independent software vendors. Software development kits and sample silicon will be available to OEMs in Q3 of 2005.

About ClearSpeed

Established in 1997, ClearSpeed Technology is a semiconductor company focused on delivering high performance co-processors to be used alongside general purpose processors in the world's most compute-intensive applications. ClearSpeed's advanced multi-threaded array processing technology provides the ability to significantly accelerate data-intensive applications at extremely low power. Products include chips, boards, software tools, applications and support. ClearSpeed has offices in San Jose, Calif. and Bristol, UK and has over 40 patents granted and pending. For more information on ClearSpeed, visit

Owen Media for ClearSpeed
Paul Owen, 206-322-1167

Email Contact


Review Article Be the first to review this article
CST Webinar Series


Featured Video
Manager, Field Applications Engineering for Real Intent at Sunnyvale, CA
Upcoming Events
SEMICON Europe at Grenoble France - Oct 25 - 27, 2016
ARM TechCon 2016 at Santa Clara Convention Center Santa Clara CA - Oct 25 - 27, 2016
Call For Proposals Now Open! at Santa Clara Convention Center, Santa Clara, CA California CA - Oct 25 - 27, 2016
DeviceWerx - 2016 at Green Valley Ranch Casino & Resort Las Vegas NV - Nov 3 - 4, 2016
S2C: FPGA Base prototyping- Download white paper

Internet Business Systems © 2016 Internet Business Systems, Inc.
595 Millich Dr., Suite 216, Campbell, CA 95008
+1 (408)-337-6870 — Contact Us, or visit our other sites:
AECCafe - Architectural Design and Engineering TechJobsCafe - Technical Jobs and Resumes GISCafe - Geographical Information Services  MCADCafe - Mechanical Design and Engineering ShareCG - Share Computer Graphic (CG) Animation, 3D Art and 3D Models
  Privacy Policy