Dynamically Reconfigurable Embedded Architecture-An Alternative To Application-Specific Digital Signal Processing Architectures

Abstract

Emerging trends in design of real-time digital signal processing systems indicate that in the future, a significant amount of performance improvement can be achieved using dynamically reconfigurable embedded architectures consisting of reconfigurable, general-purpose components. Although embedded real-time systems have long been prevailing in our society, no firm scientific base has been established yet to handle timing requirements in a systematic manner in real-time embedded computing. Because of this lack of the scientific base, many embedded systems have been designed in an ad hoc manner and most of them have been customized to specific applications, showing inflexibility for the other type of applications. This paper proposes a dynamically reconfigurable embedded architecture which bridges the gap between the embedded system and ASICs. This architecture combines a reconfigurable hardware processing unit with a software programmable processor. The main goal is to take advantage of the capabilities of both resources. While the processor takes care of all sequential computations the reconfigurable hardware takes specialized vector operations. With such integrated system architecture, specific properties of applications, such as parallelism, regularity of computation and data granularity can be exploited by creating custom operators, pipelines and interconnection pathways. To handle the conflicting requirements of being a flexible architecture and implement some application-specific algorithms, a dynamically reconfigurable embedded architecture is proposed. The proposed architecture consists of arithmetic operation-level configurable modules interconnected through multiple data buses that can be logically configured to form one or more pipelines before a specific application is initiated and remains unchanged till the completion of the application. This architecture is targeted at high throughput and real time signal processing applications. The idea of dynamic reconfiguration - changing a circuit while it is operating - is exploited. In particular, we illustrate how dynamic reconfiguration can achieve significant performance improvement.