A scalable embedded system for massive medical signal processing

Embedded Systems based on FPGA have been adopted as a solution to energy hungry data centers that have to meet real time requirement of massive data processing applications. Classic memory centric design approach was usually favored since most of designers were trained to rely on memory for calculation. However, scalability issue arose from this approach given massive signals from a large number of channels of remote clients. To solve the scalability issue, an embedded system design containing a streaming microarchitecture, embedded scheduler, and communication middleware for massive biomedical signal processing is proposed with a scalable case study of processing massive biomedical signals from multiple channels in this paper. Evaluation results show that our streaming system design has good performance in terms of scalability and latency.