Diseño y Construcción

Construcción de un procesador paralelo con memoria común: SB-PRAM.

Publicaciones:

A. Formella (invited), Th. Grün and Ch. Kessler. The SB-PRAM: Concept, Design and Construction. In Proceedings of 3rd International Working Conference on Massively Parallel Programming Models (MPPM-97). pp. 163-172, IEEE Computer Society Press, Los Alamos, 1998.

A. Formella, Th. Grün, J. Keller, W.J. Paul (invited), Th. Rauber and G. Rünger. Scientific Applications on the SB-PRAM. In Proceedings of the International Conference on Multi-Scale Phenomena and Their Simulation. World Scientific, Singapore, ISBN 981-02-3090-7, pp. 272-281, June 1997.

P. Bach, M. Braun, A. Formella, J. Friedrich, Th. Grün, and C. Lichtenau. Building the 4 Processor SB-PRAM Prototype. In Proceedings of the 30th Hawaii International Conference on System Science (HICSS-30). vol. 5, pp. 14-23, IEEE Computer Society Press, Los Alamos, January 1997.

A. Formella, J. Keller and Th. Walle. HPP: A High Performance PRAM. In Proceedings of Euro-Par '96. Springer LNCS, no. 1124, pp. 425-434, August 1996.

P. Bach, M. Braun, A. Formella, J. Friedrich, Th. Grün, H. Leister, C. Lichtenau and Th. Walle. Building the 4 Processor SB-PRAM Prototype. Technical Report No. 05/1996, Sonderforschungsbereich 124, Universität des Saarlandes, July 1996.

A. Formella, J. Keller and Th. Walle. HPP: A High Performance PRAM. Technical Report No. 02/1996, Sonderforschungsbereich 124, Universität des Saarlandes, February 1996.

Construcción de un procesador vectorial para aplicaciones numéricas.

Publicación: A. Formella, A. Obé, W.J. Paul, Th. Rauber and D. Schmidt. The SPARK 2.0 System - A Special Purpose Vector Processor with a VectorPascal Compiler. In Proceedings of the Hawaii 25th International Symposium on System Science HICSS-25, vol. 1, pp. 547-558, IEEE Computer Society Press, Los Alamos, 1991.

Análisis del Rendimiento

Un trazado de rayos como prueba difícil para ordenadores paralelos.

Publicación: A. Formella. Ray Tracing Complex Scenes: Sequential or in Parallel? Proceedings of 7th IASTED/ISMM International Conference on Parallel and Distributed Computing and Systems, pp. 89-92, Georgetown, October 1995.

Análisis comparativo del rendimiento de arquitecturas de ordenadores basadas en los paradigmas del procesamiento vectorial, del procesamiento paralelo o del procesamiento según el flujo de datos.

Publicaciones:

A. Formella, S.M. Müller, W.J. Paul and A. Bingert. Isolating the Reasons for the Performance of Parallel Machines on Numerical Programs I. In Christoph W. Kessler, editor, Automatic Parallelization - New Approaches to Code Generation, Data Distribution, and Performance Prediction Vieweg Advanced Studies in Computer Science, pp. 45-77. Viewieg, Wiesbaden, Germany, 1993.

A. Formella, S.M. Müller, W.J. Paul (invited) and A. Bingert. Isolating the Reasons for the Performance of Parallel Machines on Numerical Programs II. In A.J.G. Hey and J. Ferrante, editors, Portability and Performance for Parallel Processors pp. 223-269. John Wiley and Sons, 1993.

A. Formella, W. Massonne and W.J. Paul (invited). Cost Effectiveness of Data Flow Machines and Vector Processors. In Proceedings of the 1st Heinz Nixdorf Symposium: Parallel Architectures and their Efficient Use Paderborn, pp. 45-68, Springer LNCS 678, November 1992.