Evaluation of P/sup 3/T+: a performance estimator for distributed and parallel applications

Abstract

In this paper, we report on experiences with P 3 T +, a performance estimator for distributed and parallel programs which is used to examine at compile time the performance outcome of changes in code, problem and machine sizes, and target architectures. P 3 T + computes a variety of performance parameters including work distribution, number of transfers, amount of data transferred, transfer times, computation times, and number of cache misses. It is unique in that it models programs, code transformations, and parallel and distributed architectures and derives a performance prediction based on all three of these elements. P 3 T + is the successor tool of P 3 T which computed a similar set of performance parameters, however, for parallel programs only. P 3 T + has been re-designed and re-implemented from scratch and goes beyond P 3 T by extending the class of programs that can be handled and by employing several novel estimation methods (symbolic analysis, simulation, pre-measured kernel codes, etc.).The core part of this paper reports on the evaluation of P 3 T + to demonstrate both accuracy and usefulness of this tool for realistic kernel codes taken from real-world applications (pricing of financial derivatives and quantum mechanical calculations of solids).

POETRIES: Performance Oriented Environment for Transparent Resource-Management, Implementing End-User Parallel/Distributed Applications

“…In the set of studies related to performance monitoring, analysis and tuning we have found tools that make a trace-based analysis, such as Kappa-Pi [9] and EXPERT [10], along with other studies based on static prediction, such as P 3 T+ [11], which predicts performance mainly based on information gathered at compilation time.…”

Semi-Proving: An Integrated Method for Program Proving, Testing, and Debugging

“…This is because the output of a symbolic execution is more informative than that of executing a concrete input, as a symbolic input represents more than one element of the input domain. In recent years, symbolic execution techniques have been studied intensively not only in software engineering, but also in the areas of programming languages and high-performance compilers [9], [25], [26], [27], [29], [36]. Sophisticated techniques and automated tools for symbolic-analysis and pathconstraint simplifications have been developed to facilitate more effective parallelism and optimization of programs.…”