DEFENSE

Seismic Algorithm Benchmarks and ROI Analysis Prove Value of the Software, Hardware and Interconnect Technology Delivered in Celoxica FPGA Co-Processing Solutions: At the AMD Torrenza Initiative seminar this week, Celoxica presented results of an oil-exploration algorithm customer benchmark, achieving 28x performance improvement on a forward wave migration algorithm. In addition, Celoxica presented a financial analysis that showed a consistent 10x return on capital invested on FPGA-enabled servers, and a 50% increase in return on investment by adding one FPGA acceleration card to each server. Celoxica’s accelerated computing solution consists of an FPGA acceleration board, algorithm acceleration libraries, and a communication interconnect kernel based on the high bandwidth, low latency HyperTransport technology standard. Celoxica enables FPGA co-processing with their proven programming compiler which allows applications to be accelerated by software developers using a familiar “C” language design flow. Celoxica delivers an integrated accelerated computing solution, including programming support to enable customers to use a software flow to accelerate their applications. Typical benchmark results for FPGA co-processing have shown from a 12x to 50x performance improvement, depending on the amount of parallelism available in the customer algorithm. To augment these results, Celoxica has developed a calculator that figures accelerated computing return on investment based on hardware purchase and support costs, power savings, reduced cooling costs, reduced space requirements, and improved revenue opportunity from increased computing performance. Customers typically realize 50% higher returns by adding FPGA co-processors to their standard server configurations. "Celoxica has delivered proven performance and power advantages of accelerated computing for customers in industries such as oil exploration, financial analysis and life sciences," said Jeff Jussel vice president of marketing and strategic partnerships for Celoxica. "As we add another data point to our list of successes, we are now able to quantify the financial advantages of our FPGA co-processing solution." "HyperTransport technology and AMD64 technology with Direct Connect Architecture can provide a tightly coupled co-processor expansion capability that enables the benchmark results and significant customer returns seen by FPGA-based acceleration," said Mike Goddard, senior director, Advanced Technology Planning and Performance Labs, AMD. "Celoxica’s integrated acceleration hardware and easy-to-use software programming interface continue to produce successful examples of the value of AMD’s Torrenza initiative." The Celoxica accelerated computing solutions include the RCHTX acceleration card, and the DK5 software to FPGA compiler. Already being used by computing server customers, these products combine to simplify FPGA co-processing and give software programmers the ability to accelerate their applications and achieve excellent return on investment.