SKiPPER: A Skeleton-Based Parallel Programming Environment for Real-Time Image Processing Applications
This paper presents SKiPPER, a programming environment dedicated to the fast prototyping of parallel vision algorithms on MIMD- DM platforms. SKiPPER is based upon the concept of algorithmic skele- tons, i.e. higher order program constructs encapsulating recurring forms of parallel computations and hiding their low-level implementation de- tails. Each skeleton is given an architecture-independent functional (but executable) specification and a portable implementation as a generic pro- cess template. The source program is a purely functional specification of the algorithm in which all parallelism is made explicit by means of com- posing instances of selected skeletons, each instance taking as parameters the application specific sequential functions written in C. SKiPPER compiles this specification down to a process graph in which nodes cor- respond to sequential functions and/or skeleton control processes and edges to communications. This graph is then mapped onto the target topology using a third-party CAD software (SynDEx). The result is a dead-lock free, optimized (but still portable) distributed executive, which SKiPPER finally turns into executable code for the target platform. The initial specification, written in ML language, can also be executed on any sequential platform to check the correctness of the parallel algorithm. The applicability of SKiPPER concepts and tools has been demonstrated by parallelising several realistic real-time vision applications both on a multi-DSP platform and a network of workstations. It is here illustrated with a real-time vehicle detection and tracking application.
KeywordsParallelism skeleton Caml image processing fast prototyping vehicle tracking
Unable to display preview. Download preview PDF.
- 1.M. Cole. Algorithmic skeletons: structured management of parallel computations. Pitman/MIT Press, 1989.Google Scholar
- 2.G. Cousineau and M. Mauny. The functional approach to programming. Cambridge University Press, 1998-see also: http://pauillac.inriafr/caml.
- 4.Marco Danelutto, Roberto DiCosmo, Xavier Leroy, and Susanna Pelagatti. Parallel functional programming with skeletons: the OCamlP3L experiment. In Proceedings ACM workshop on ML and its applications. Cornell University, 1998.Google Scholar
- 5.J. Darlington, Y. K Guo, H. W. To, and Y. Jing. Skeletons for structured parallel composition. In Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, 1995.Google Scholar
- 6.D. Ginhac. Prototypage rapide d’applications de vision artificielle par squelettes fonctionnels. PhD thesis, Univ. B. Pascal, 1999.Google Scholar
- 7.D. Ginhac, J. Sérot, and J. P. Dérutin. Fast prototyping of image processing applications using functional skeletons on a MIMD-DM architecture. In IAPR Workshop on Machine Vision and Applications, pages 468–471, Chiba, Japan, Nov 1998.Google Scholar
- 8.P. Legrand, R. Canals, and J. P. Dérutin. Edge and region segmentation processes on the parallel vision machine Transvision. In Computer Architecture for Machine Perception, pages 410–420, New-Orleans, USA, Dec 1993.Google Scholar
- 9.F. Marmoiton, F. Collange, P. Martinet, and J. P. Dérutin. A real time car tracker. In International Conference on Advances in Vehicle Control and Safety, Amiens, France, July 1998.Google Scholar
- 10.G. J. Michaelson and N. R. Scaife. Prototyping a parallel vision system in standard ML. Journal of Functional Programming, 1995.Google Scholar
- 11.D. B. Skillicorn. Architecture-independent parallel computation. IEEE Computer, 23(12):38–50, December 1990.Google Scholar
- 12.D. B. Skillicorn and D. Talia. Models and languages for parallel computation. Computing Surveys, June 1998.Google Scholar
- 13.Y. Sorel. Massively parallel systems with real time constraints. The “Algorithm Architecture Adequation” Methodology. In Proc. Massively Parallel Computing Systems, Ischia Italy, May 1994.Google Scholar