New Floating Point Extensions for ARC Cores Enable Full Performance Math Functionality Without a Coprocessor; ARC FPX Extensions Set New Standard for Die Size Efficiency and Low Power.

SAN JOSE, Calif. -- ARC International (LSE:ARK) today announced new Floating Point Extensions (FPX) for the ARC(TM) 600 and ARC 700 processor core families. By implementing IEEE-754-compliant floating point functionality using the extendibility feature of ARC's patented configurability, ARC can achieve up to 90 percent reduction in gate count compared to competitors' floating point coprocessors with comparable performance. E[acute accent]ARC FPX extensions provide direct execution in hardware of the most frequently used floating point functions, which greatly accelerates computations requiring high math precision. Applications that are using floating point processing include graphics, image processing, printers, GPS, automotive controls and instrumentation. ARC FPX has already has been licensed by an ARC customer for use in a data input device. E[acute accent]Traditional approaches to hardware floating point processing require a coprocessor to execute instructions in accordance with the IEEE-754 standard. The resulting designs are complex and consume additional silicon area -- in some cases even more than the host CPU. ARC's FPX solution uses hardware extensions to accelerate the proven IEEE-754-compliant ARC MetaWare(R) math library. E[acute accent]ARC FPX extensions achieve near coprocessor performance with much smaller die area and power consumption. The most frequently used floating point instructions, including addition, subtraction and multiplication, are implemented in hardware; the other elements of the IEEE specification are implemented in software. E[acute accent]ARC FPX also provides configuration flexibility that is not available with coprocessors. Using the patented ARChitect(TM) configurator tool, SoC designers can easily select which extensions to include in their chip design: single precision only, double precision only, or both. In addition, users who wish to further accelerate their code can use ARC's extendible architecture and EIA tool to implement more math instructions specifically for their application. E[acute accent]Summary specifications and features comparison with traditional floating point coprocessors:

ARC(TM) FPX              Floating Point
                                                    Coprocessor
                                                   (ARM VF9-S(1))
---------------- --------------------------- -------------------------
Size in gates     Single Precision:  12-14K         100K - 130K
                  Double Precision:  24-30K
---------------- --------------------------- -------------------------
Performance            1.0 Mflops/MHz             1.3 Mflops/MHz
---------------- --------------------------- -------------------------
Additional Power    None (confirmed with        0.4 mW/MHz typical
                     customer benchmarks)       (0.13um, G process)
---------------- --------------------------- -------------------------
Configurability       Flexible - SP, DP       None, monolithic design
options                    or both
---------------- --------------------------- -------------------------
Additional math      Can be implemented         Fixed design, not
instructions             by the user                 extendible
---------------- --------------------------- -------------------------
           (1) ARM VFP9-S data from ARM Website

E[acute accent]"ARC's new floating point extensions are an excellent example of the benefits of configurability," said Derek Meyer, vice president of marketing for ARC International. "Adding a large coprocessor can be cost-prohibitive in many cost-sensitive designs. By offering floating point functionality as extensions to ARC's cores, we are able to provide customers with a cost-effective way to design computationally intensive applications."

E[acute accent]Availability

E[acute accent]ARC's Single Precision Floating Point Extensions are available now. Double Precision Extensions will be available in the early summer of 2005. For more information, contact ARC directly at [e-mail]. Additional technical information on ARC FPX extensions is located at www.ARC.com/FPX.

E[acute accent]About ARC International plc

E[acute accent]ARC International is the world leader in low-power, high-performance 32-bit configurable CPU/DSP processor cores, subsystems, real-time operating systems and development tools for embedded system design. ARC's patented configurable and extendible cores assist customers in the development of next generation digital media, consumer and communications devices, resulting in lower cost, higher performance SoC products. E[acute accent]ARC International maintains a worldwide presence with corporate offices in San Jose, California, USA and Elstree, UK. The company has research and development offices located in England and the United States. For more information please visit the ARC website at www.ARC.com. ARC International is listed on the London Stock Exchange as ARC International plc (LSE:ARK).

E[acute accent]ARC, the ARC logo, MetaWare and ARC-Based are trademarks or registered trademarks of ARC International. intent is a registered trademark of Tao Group Ltd. All other brands or product names contained herein are the property of their respective owners. This press release may contain certain "forward-looking statements" that involve risks and uncertainties. For factors that could cause actual results to differ, visit the company's website as well as the listing particulars filed with the United Kingdom Listing Authority and the Registrar of Companies in England and Wales.