This paper describes a run-time system (DesCaRTeS) that has been used for developing applications that run on a network of embedded system controllers. DesCaRTeS is written in Dynamic C and provides Dynamic C programs...
详细信息
This paper describes a run-time system (DesCaRTeS) that has been used for developing applications that run on a network of embedded system controllers. DesCaRTeS is written in Dynamic C and provides Dynamic C programs with easy-to-use functionality to run on such networks, send and receive messages, perform remote procedure calls, and dynamically create processes. This paper reports on some of the applications for which DesCaRTeS has been used, the experience in developing them using DesCaRTeS, and the experience gained in developing DesCaRTeS. It also presents performance comparisons between these applications written using DesCaRTeS and equivalent applications written using native Dynamic C. (C) 2003 Elsevier Ltd. All rights reserved.
Recently we proposed occam-pi as a high-level language for programming massively parallel reconfigurable architectures. The design of occam-pi incorporates ideas from CSP and pi-calculus to facilitate expressing paral...
详细信息
ISBN:
(纸本)9780769543017
Recently we proposed occam-pi as a high-level language for programming massively parallel reconfigurable architectures. The design of occam-pi incorporates ideas from CSP and pi-calculus to facilitate expressing parallelism and reconfigurability. The feasability of this approach was illustrated by building three occam-pi implementations of DCT executing on an Ambric. However, because DCT is a simple and well-studied algorithm it remained uncertain whether occam-pi would also be effective for programming novel, more complex algorithms. In this paper, we demonstrate the applicability of occam-pi for expressing various degrees of parallelism by implementing a significantly large case-study of focus criterion calculation in an autofocus algorithm on the Ambric architecture. Autofocus is a key component of synthetic aperture radar systems. Two implementations of focus criterion calculation were developed and evaluated on the basis of performance. The comparison of the performance results with a single threaded software implementation of the same algorithm show that the throughput of the two implementations are 11x and 23x higher than the sequential implementation despite a much lower (9x) clock frequency. The two designs are, respectively, 29x and 40x more energy efficient.
暂无评论