Using a CSP Based Programming Model for Reconfigurable Processor Arrays

Zain-ul-Abdin,; Svensson, Bengt

doi:10.1109/reconfig.2008.41

Cited by 8 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case, we have extended the frontend for supporting occam-pi and developed a new backend, targeting XPP, thus generating native code in the proprietary language NML. The Ambric backend targeting Ambric array of processors was developed in an earlier work [9].…”

Section: A Compiler For Xppmentioning

confidence: 99%

“…We will also be focusing on expressing the reconfigurability of the underlying hardware in a programming model by relying on the concepts of mobility introduced in the pi-calculus. Previously we have reported the use of occam-pi for programming the Ambric array of processors [9]; in this paper the target architecture for our proof of concept implementations is the eXtreme Processing Platform (XPP) [10]. We present the results of streaming FIR and DCT algorithm implementations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Occam-pi as a High-Level Language for Coarse-Grained Reconfigurable Architectures

Zain-ul-Abdin

Svensson

2011

2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and PHD Forum

Self Cite

View full text Add to dashboard Cite

Abstract-Recently we proposed occam-pi as a high-level language for programming coarse grained reconfigurable architectures. The constructs of occam-pi combine ideas from CSP and pi-calculus to facilitate expressing parallelism, communication, and reconfigurability. The feasability of this approach was illustrated by developing a compiler framework to compile occam-pi implementations to the Ambric architecture.In this paper, we demonstrate the applicability of occam-pi for programing an array of functional units, eXtreme Processing Platform (XPP). This is made possible by extending the compiler framework to target the XPP architecture, including automatic floating to fixed-point conversion. Different implementations of a FIR filter and a DCT algorithm were developed and evaluated on the basis of performance and resource consumption. The reported results reveal that the approach of using occam-pi to program the category of coarse grained reconfigurable architectures appears to be promising. The resulting implementations are generally much superior to those programmed in C and comparable to those hand-coded in the low-level native language NML.

show abstract

Section: A Compiler For Xppmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Occam-pi as a High-Level Language for Coarse-Grained Reconfigurable Architectures

Zain-ul-Abdin

Svensson

2011

2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and PHD Forum

Self Cite

View full text Add to dashboard Cite

show abstract

“…As a proof of concept we performed an experiment by using occam-pi [6] for programming the Ambric array of processors after implementing a compiler [7]. Occam-pi is an extension of classical occam that includes the mobility features of the pi-calculus.…”

Section: Programming Reconfigurable Processor Arrays In Occam-pimentioning

confidence: 99%

“…This work is part of our ongoing research whose initial studies are presented here. An application study is performed in which the results of three different implementations of the 1D-DCT algorithm are compared on the basis of performance versus resource requirements [7]. The comparison reveals that the most parallelized version, which uses 34 processors, produces 27 times higher throughput when compared with the serialized implementation.…”

Section: Programming Reconfigurable Processor Arrays In Occam-pimentioning

confidence: 99%

High-level programming of coarse-grained reconfigurable architectures

Ul-Abdin

2009

2009 International Conference on Field Programmable Logic and Applications

View full text Add to dashboard Cite

We propose that, in order to meet high computational demands, the application development has to be based on suitable models of computations that will lead to scalable and reusable implementations. The models should enhance the understanding of the application and at the same time enable the developer to organize the computations so that they can be efficiently mapped to the target reconfigurable architecture. The goal of the thesis is to propose methods to program future coarse-grained reconfigurable architecttures in a productive manner in such a way as to achieve energy efficient mapping with improved performance.

©2009 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Embedded Parallel Computin

show abstract

“…In earlier work, we have demonstrated the feasability of using the occam-pi language to program an emerging massively parallel reconfigurable architecture by implementing a 1D-DCT algorithm [5] [6]. In this paper we demonstrate the applicability of the approach by programming computeintensive parts of Synthetic Aperture Radar (SAR) systems.…”

Section: Introductionmentioning

confidence: 99%

Programming Real-Time Autofocus on a Massively Parallel Reconfigurable Architecture Using Occam-pi

Zain-ul-Abdin

Åhlander²,

Svensson

2011

2011 IEEE 19th Annual International Symposium on Field-Programmable Custom Computing Machines

Self Cite

View full text Add to dashboard Cite

Abstract-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 wellstudied 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. I. INTRODUCTION AND MOTIVATIONEmbedded signal processing systems are facing the challenges of increased computational demands. Massively parallel reconfigurable architectures, which can be configured to form application-specific hardware, offer high degree of parallelism to meet the application requirements. However, the applicability of reconfigurable processor arrays in embedded and high performance computing is constrained by the need for mastering low-level structural description languages and the lack of support in these languages for expressing dynamic reconfiguration. Clearly, all these challenges need to be taken care of by using an appropriate programming model.We proposed to use a concurrent programming model that allows the programmer to express computations in a productive manner by matching it to the target hardware using highlevel constructs, and the language is further supported by a compiler for providing portability across different hardware resources. Occam [2] is a programming language based on the Communicating Sequential Processes (CSP) [1] concurrent model of computation and was developed by Inmos for their microprocessor chip Transputer. However, CSP can only express a static model of the application, where processes synchronize through communication over fixed channels. In contrast, the pi-calculus [3] allows modeling of dynamic construc-

show abstract

Using a CSP Based Programming Model for Reconfigurable Processor Arrays

Abstract: Abstract

Cited by 8 publications

References 10 publications

Occam-pi as a High-Level Language for Coarse-Grained Reconfigurable Architectures

Occam-pi as a High-Level Language for Coarse-Grained Reconfigurable Architectures

High-level programming of coarse-grained reconfigurable architectures

Programming Real-Time Autofocus on a Massively Parallel Reconfigurable Architecture Using Occam-pi

Contact Info

Product

Resources

About