EVALUATING COMPUTATIONAL COSTS WHILE HANDLING DATA AND CONTROL PARALLELISM
Abstract
The aim of this work is to introduce a computational costs system associated to a semantic framework for orthogonal data and control parallelism handling. In such a framework a parallel application is described by a semantic expression involving in an orthogonal manner both data access and control parallelism abstractions. The evaluation of such an expression is driven by a set of rewriting rules each of which is combined with a computational cost. We present how to proceed in the evaluation of the final cost of the application as well as how such information together with the semantic framework capabilities can be exploited to increase the overall performance.
References
-
Murray Cole , Algorithmic Skeletons: structured management of parallel computation ( Monograms. Pitman/MIT Press , Cambridge, MA , 1989 ) . Google Scholar -
S. Bromling , Pattern-based parallel programming , 2002 International Conference on Parallel Programming (ICPP-02) ( 2002 ) . Google Scholar Manuel Díaz ,LNCS (2001) p. 16. Google Scholar- Journal of Parallel and Distributed Computing 45(2), 148 (1997), DOI: 10.1006/jpdc.1997.1367. Crossref, ISI, Google Scholar
H. Kuchen , A skeleton library, Proc. of Euro-Par 20022400 (2002) pp. 620–628. Google Scholar- Parallel Processing Letters 12(2), 141 (2002), DOI: 10.1142/S0129626402000896. Link, Google Scholar
-
L. Rauchwerger , F. Arzu and K. Ouchi , Standard templates adaptive parallel library (STAPL) , 4th International Workshop on Languages, Compilers, and Run-Time Systems for Scalable Computers ,LNCS ( 1998 ) . Google Scholar S. Campa and M. Danelutto , A framework for orthogonal data and control parallelism exploitation, Proceedings of ICCSA 20043046,LNCS (Springer Verlag, 2004) pp. 1295–1300. Google Scholar-
Sonia Campa , A formal framework for orthogonal data and control parallelism handling , Int. Conf. on Computational Science (ICCS 2005) ,LNCS , eds.V. Sunderman ( Springer ) . Google Scholar - In Parallel Algorithms and Applications 16(3), 87 (2001). Google Scholar
S. Gilmore , Evaluating the performance of skeletonbased high level parallel programs, Proceedings of the Intl. Conference on Computational Science (ICCS 2004)3038,LNCS (Springer Verlag, 2004) pp. 289–296. Google ScholarM. Aldinucci and M. Danelutto , Rewriting skeleton programs: How to evaluate the data-parallel stream-parallel tradeoff, In Proc. of the 1st Intl. Workshop on Constructive Methods for Parallel Programming,MIP (1998) pp. 44–58. Google Scholar


