ARM has teamed with US-based embedded processor core developer Intrinsity to create high performance versions of the ARM Cortex-R4 processor.

Cycle-accurate RTL FastCores built with Intrinsity's proprietary Fast14 1-of-N Domino Logic (NDL) circuit technology are claimed to run twice as fast as ordinary synthesised static logic versions.

The first of these will be implementations of the Cortex-R4 processor operating at around twice the frequency achievable using standard synthesis techniques on the same silicon process.  The Cortex-R4X processor implementations are available for licensing from ARM immediately.

According to Graham Budd, executive v-p and general manager, processor division, ARM: "Through this relationship we can extend the performance range of the Cortex-R4 processor to meet the requirements of new market domains.”

Various configurations of the Cortex-R4 processor will be available as Cortex-R4X implementations, on a range of silicon processes.

The first implementation will operate at 600MHz under worst-case operating conditions on the TSMC 65LP process.  As a cycle-accurate implementation of the Cortex-R4 processor it executes all the same software binaries, and is fully supported by the RealView development suite.

Standard Cortex-R4 processor models can be used for cycle accurate modelling of the Cortex-R4X processor implementation with RealView SoC Designer, offering rapid prototyping and architectural exploration.

"By working closely with ARM on the development of the Cortex-R4X processor implementations, together we will be able to reach a much broader base of designers who are looking for ways to achieve higher performance without sacrificing power efficiency and bring new SoCs to market quickly,” said Bob Russo, CEO at Intrinsity.