Although the absolute attainable performance of the clockless core lags behind that of a synthesible ARM968E-S, at equivalent performance the ARM996HS consumed a factor of 2.8 less power than the ARM968E-S, or 36 percent, according to simulation benchmark data from Handshake Solutions, the Philips Electronics subsidiary working with ARM (Cambridge, England) on the asynchronous processor project. The ARM996HS current peaks are reduced by a factor 2.5 to 40 percent of the ARM968E-S, the data showed. The ARM996HS has a gate count of 89,000 compared with the 88,000 of the ARM968E-S. Both are based on the ARM9 processor and the ARMv5Te instruction set.

The ARM996HS performance varies between about 50 percent of a 100-MHz clocked ARM968E-S at 1.0 volts and a temperature of 125 degrees centigrade and about 75 percent of the performance at nominal voltage of 1.2 volts and 25 degrees centigrade.

Because clockless processors consume zero dynamic power when there is no activity, they can significantly extend battery life compared with clocked equivalents, although this is software and application dependent.

ARM’s clocked processor cores are already well known for power efficient operation. Taking the power consumption lower and the efficiency higher in clockless versions could have broad consequences across the industry although, for now, the ARM996HS is being promoted for its low electromagnetic footprint, another benefit of clockless performance which would make the processor core suitable for automotive and mixed-signal applications.

Richard York, ARM’s ARM996HS product manager, said ARM would not rush to introduce clockless versions of other cores. “It [asynchronous logic] will take some time to become widely accepted because it is very different,” he told EE Times.

In addition, designing the core, although now complete, has not been straightforward.