PSEE: A Tool for Parallel Systems Learning

Abstract

Programs for parallel computers of distributed memory are difficult to write, understand, evaluate and debug. The design and performance evaluation of algorithms is much more complex than the conventional sequential one. The technical know/how necessary for the implementation of parallel systems is already available, but a critical problem is in the handling of complexity. In parallel distributed memory systems the performance is highly influenced by factors as interconnection scheme, granularity, computing/communication ratio, algorithm topology, parallel languages, and operating system policies. Interaction between these factors is not easy to understand and often unpredictable. This paper presents the PSEE (Parallel System Evaluation Environment), an interactive graphical environment, which permits to study the behaviour of parallel distributed memory systems, as well as several enhancements to increase the goodness of this tool. PSEE is an easy-to-use environment that enables parallel distributed memory systems programmers take decisions about the behaviour program and parallel computer in terms such as scalability, tuning and performance of the underlying parallel machine.