Modeling and Optimization of Parallel and Distributed Embedded Systems

Chapter 7High-Performance Energy-Efficient Multicore-Based Parallel Embedded Computing^*

Embedded system design is traditionally power-centric, but there has been a recent shift toward high-performance embedded computing (HPEC) due to the proliferation of compute-intensive embedded applications. For example, the signal processing for a 3G mobile handset requires 35–40 giga operations per second (GOPS) for a 14.4 Mbps channel and 210–290 GOPS for a 100 Mbps orthogonal frequency-division multiplexing (OFDM) channel. Considering the limited energy of a mobile handset battery, these performance levels must be met with a power dissipation budget of approximately 1 W, which translates to a performance efficiency of 25 mW/GOPS or 25 pJ/operation for the 3G receiver and 3–5 pJ/operation for the OFDM receiver [5, 6]. These demanding and competing power–performance requirements make modern embedded system design challenging.

The high-performance energy-efficient embedded computing (HPEEC) domain addresses the unique design challenges of high-performance and low-power/energy embedded computing. The HPEEC domain can be termed as high-performance green computing; however, green may refer to a bigger notion of environmental impact. These design challenges are competing because high performance typically requires maximum processor speeds with enormous energy consumption, whereas low power typically requires nominal or low processor speeds that offer modest performance. HPEEC requires thorough ...