A whole segment of the power industry is dedicated to supplying the fluctuating needs of microprocessors and ASICs at the point of load. Yet to date, there has been no consistent way of defining how those loads vary under real-life conditions. Datasheet "typical" energy consumption specifications are difficult to compare across vendors. It's even harder to compare processor cores for system-on-a-chip implementations.
That may be changing. The Embedded Microprocessor Benchmark Consortium (EEMBC) plans to add an energy-consumption metric to the performance scores it provides for embedded processors tested against its application-focused benchmarks. The metric will be an optional component of the performance benchmark scores published for each processor. The scores will take into account the energy consumed by the benchmarked devices while running each of the consortium's application-focused benchmark suites. Once the standardized methods are finalized, the details of how EEMBC measures energy consumption will be available for download from www.eembc.org.
The metric will provide comparable information about energy consumption. It also will illustrate the "cost" of a device's performance in terms of the power budget, as designers can derive a performance/energy number using the consolidated performance score in each benchmark suite. Separate EEMBC working groups are addressing energy measurements for hardware platforms/devices and IP processor cores.