An Evaluation of High-Performance Embedded Processing on MPPAs

Abstract

Embedded signal processing is facing the challenges of increased performance as well as to achieve energy efficiency. Massively parallel processor arrays (MPPAs) consisting of hundreds of processing cores offer the possibility of meeting the growing performance demand in an energy efficient way by exploiting parallelism instead of scaling the clock frequency of a single processor. In this paper we evaluate two selected commercial architectures belonging to the category of MPPA. The adopted approach for the evaluation is to implement a real, industrial application in the form of compute-intensive parts of Synthetic Aperture Radar (SAR) systems.