ANDES: a Tool for Evaluating Parallel Systems
Resumo
This paper presents the ANDESenvironment, a tool for supporting the performance evaluation of parallel systems. ANDES is structured as a modular tool. The parallel program, the parallel computer and the strategies used for implementing the software on the hardware are described separately. The interaction among modules occur when using ANDES. This environment is employed during the early phases of the software or hardware design. The evaluation technique currently adopted is based on the execution of synthetic workloads. However, ANDES can be used with other techniques that are compatible with the information described inside each module. A first prototype of the tool is running on a Transputer network. A more recent version runs on a computer network supporting PVM (Parallel Virtual Machine). ANDES was used to compare different mapping algorithms.
Referências
Mark Debbage, Mark B. Hill, and Denis A. Nicole. The Virtual Channel Router. Transputer Communications, 1(1):318, August 1993.
Raj Jain. The art of computer systems performance analysis: techniques for experimental design, measurement, simulation, and modeling. Wiley Professional Computing. John Wiley and Sons, New York, 1991.
Brian W. Kernighan and Dennis M. Ritchie. The C programming language. Prentice-Hall Software Series. Prentice-Hall, Englewood Cliffs, second edition, 1988.
Ted G. Lewis and Hesham El-Rewini. Introduction to Parallel Computing. Prentice-Hall International, Englewood Cliffs, 1992.
Denis A. Nicole. ESPRIT project 1085: reconfigurable Transputer processor architecture. In C. R. Jesshope and K. D. Reinartz, editors, CONPAR88, pages 81-89, Cambridge, 1989. British Computer Society, Cambridge University Press.
Michael G. Norman and Peter Thanisch. Models of machines and computation for mapping in multicomputers. ACM Computing Surveys, 25(3):263-302, September 1993.
D. A. Poplawski. Synthetic models of distributed memory parallel programs. Technical Report ORNL/TM 11634, Oak Ridge National Laboratory Martin Marietta, ORNL Oak Ridge, Tennessee 37831 - USA, 1990.
V. S. Sunderam, G. A. Geist, J. Dongarra, and R. Manchek. The PVM concurrent computing system: evolution, experiences, and trends. Parallel Computing, 20(4):531-546, April 1994.
Tao Yang and Apostolos Gerasoulis. PYRROS: static scheduling and code generation for message passing multiprocessors. In Proceedings of the 6th ACM International Conference on Supercomputing, pages 428-437. ACM, July 1992.
