Breakthrough IP from Arithmatica Boosts Silicon Performance, Reduces Chip Area without Changing Design Process
CellMath Technology Incorporated in NVIDIA, Xilinx and Layer N Flagship Products
REDWOOD CITY, Calif. - Apr. 26, 2004 - Arithmatica, Inc., the first company focused solely on using advances in silicon math algorithms to increase speed and/or lower costs for math-intensive ICs, today announced its CellMath™ product line for standard cell and custom IC design flows. This breakthrough silicon intellectual property (IP) helps companies significantly improve silicon efficiency far beyond what can be done with traditional EDA tools, without changing current design practices. Applying it to math-critical blocks in graphics chips can reduce overall chip area by up to 10 percent, saving millions of dollars in manufacturing costs for each design. It also improves performance in processor designs in varying degrees, depending on the application.
CellMath is ideal for math-intensive 3D graphics acceleration and high-performance processors in high-growth application segments that depend on generation-to-generation improvements in performance, power and area to win or maintain competitive advantage. Companies including NVIDIA Corporation, Xilinx, Inc., and Layer N Networks, Inc. successfully have incorporated CellMath technology in their flagship products, achieving impressive performance and cost goals.
Gopal Solanki, Vice President Platform Products at NVIDIA stated, "The PC graphics community demands a constant pace of improved quality of experience at very competitive price points. Using Arithmatica's CellMath Graphics Library, we were able to achieve a new threshold of performance in our next-generation of graphics processors while reducing the chip area dedicated to calculations in many of our major blocks by typically 20-30 percent. As an early customer, we worked closely with Arithmatica's engineering team and we were able to embed their silicon IP in a variety of designs without any schedule impact within our projects. The result is that our new product line has the highest performance GPU in the market today and we are positioned to be very aggressive in terms of expanding our market leadership. It is refreshing to work with a young company that delivers on its commitments and we look forward to a long working relationship with Arithmatica."
The Xilinx® custom design group develops high-performance, highly parallel digital signal processing (DSP) elements. "Arithmatica helped Xilinx achieve a very aggressive performance goal by increasing the speed of next-generation DSP operations by more than 50 percent - setting a new industry benchmark," said Jennifer Wong, director of IC Design at Xilinx, the global leader in programmable logic solutions headquartered in San Jose, Calif. "Arithmatica's IP in conjunction with the new DSP architecture achieved a remarkable 8x improvement in silicon efficiency, measured in MHz/Watt, over the previous generation. The Arithmatica silicon math team worked closely with the Xilinx custom design group to meet the world-class performance goals within the allotted schedule."
"We have been working with Arithmatica since the early phases of our product development," said Ed Reynolds, Vice President, Marketing at Layer N Networks, Inc. "We believe Arithmatica's technology has helped us achieve significant innovation that will benefit our customers. Our first product - UltraLock, the industry's only plug-and-play SSL offload solution - demonstrates this, and we have a strong roadmap that will keep us in a leadership position."
Higher Performance, Less Risk
The CellMath product line comprises a graphics library, processor library and configurable instances backed by a pipeline of 15 patent applications. These provide a rich set of application-level functions - literally billions of permutations, of floating-point dot product and multiply-accumulate configurations, for example - that are delivered with gate-level netlists and bit-accurate simulation models. Each function can be tailored for bit widths, speed and area goals, pipelining, and internal precision, among other configuration options.
Compared to traditional methods, CellMath functions are based on faster carry-propagate logic that is central to efficient addition, faster parallel counters, core to multiplication, and optimizations in floating-point and single-instruction multiple data (SIMD) computational operations. CellMath also improves productivity and lowers risk by providing simulation models that are formally verified against the gate-level netlist. Companies can take advantage of CellMath without changing their design flow, standard cell libraries or process technology.
Dave Burow, CEO of Arithmatica, said, "The explosive growth in consumer electronic products that require 3D graphics, high-quality audio and video, and high-bandwidth data transmission is driving the demand for powerful, easily implemented, cost-effective silicon math. We are pleased that technology leaders like NVIDIA, Xilinx, Layer N and others have successfully deployed our technology to improve the speed, area and power consumption of their math-intensive chips for their next-generation products."
Pricing and Availability
The CellMath graphics library, processor library and configurable instances are available now for licensing, priced from U.S. $175,000; Arithmatica's licensing model includes a project-based, non-royalty fee pricing structure, eliminating periodic time-consuming accounting and payment procedures.
About Arithmatica
Arithmatica is the first company focused solely on using advances in silicon math to increase speed and/or lower costs for math-intensive ICs, such as 3D graphics accelerators and high-performance processors. Its unique IP provides significant, permanent improvement to licensees' arithmetic IC circuits. Founded in 1998, Arithmatica is headquartered in Redwood City, Calif., with a research and development center near Oxford, UK. For further information, please visit: www.arithmatica.com.
# # # #
Note to Editors: Arithmatica, the Arithmatica logo and CellMath are trademarks of Arithmatica, Inc. All other trademarks and registered trademarks belong to their respective companies.
|
Related News
- Dolphin Integration breakthrough innovation for TSMC 180 nm BCD Gen 2 process: Up to 30% savings in silicon area with the new SpRAM RHEA
- Synopsys and Samsung Foundry Boost Power, Performance and Area for Modern SoCs on Samsung's SF2 Process
- Synopsys DesignWare PVT Subsystem Drives Performance, Power and Silicon Lifecycle Management on TSMC's N3 Process Technology
- CEA-Leti & Dolphin Design Report FD-SOI Breakthrough that Boosts Operating Frequency by 450% and Reduces Power Consumption by 30%
- Synopsys Fusion Technology Enables Lower Power, Smaller Area, and Higher Performance on Samsung Foundry 7LPP Process with EUV
Breaking News
- Launching MosChip DigitalSky™ for Building Connected Intelligent Enterprises
- Crypto Quantique collaborates with ADLINK to simplify and enhance device security in industrial PCs
- Xiphera Partners with IPro for the Israeli Chip Design Market
- Siemens collaborates with GlobalFoundries to certify Analog FastSPICE for the foundry's high-performance processes
- EXTOLL collaborates with Frontgrade Technologies for High-Speed SerDes IP
Most Popular
- BrainChip Introduces Lowest-Power AI Acceleration Co-Processor
- Launching MosChip DigitalSky™ for Building Connected Intelligent Enterprises
- Siemens collaborates with GlobalFoundries to certify Analog FastSPICE for the foundry's high-performance processes
- RaiderChip brings Meta Llama 3.2 LLM HW acceleration to low cost FPGAs
- Crypto Quantique collaborates with ADLINK to simplify and enhance device security in industrial PCs
E-mail This Article | Printer-Friendly Page |