Projections : A Preliminary Performance Tool for Charm

The advent and acceptance of massively parallel machines has made it increasingly important to have tools to analyze the performance of programs running on these machines. Current day performance tools suuer from two drawbacks: they are not scalable and they lose speciic information about the user program in their attempt for generality. In this paper, we present Projections, a scalable performance tool, for Charm that can provide program-speciic information to help the users better understand the behavior of their programs.

[1]  E. Reingold,et al.  Combinatorial Algorithms: Theory and Practice , 1977 .

[2]  Allen D. Malony,et al.  An integrated performance data collection, analysis, and visualization system , 1989 .

[3]  Daniel A. Reed,et al.  Scalable Performance Environments for Parallel Systems , 1991, The Sixth Distributed Memory Computing Conference, 1991. Proceedings.

[4]  Michael T. Heath,et al.  Visualizing the performance of parallel programs , 1991, IEEE Software.

[5]  Laxmikant V. Kalé,et al.  A load balancing strategy for prioritized execution of tasks , 1993, [1993] Proceedings Seventh International Parallel Processing Symposium.

[6]  Peter Hinz,et al.  Visualizing the performance of parallel programs , 1996 .