Parallel Component Performance Benchmarks is a computer program developed to aid the evaluation of the Common Component Architecture (CCA) — a software architecture, based on a component model, that was conceived to foster high-performance computing, including parallel computing. More specifically, this program compares the performances (principally by measuring computing times) of componentized versus conventional versions of the Parallel Pyramid 2D Adaptive Mesh Refinement library — a software library that is used to generate computational meshes for solving physical problems and that is typical of software libraries in use at NASA's Jet Propulsion Laboratory.
This program was written by Daniel Katz, Edwin Tisdale, and Charles Norton of Caltech for NASA's Jet Propulsion Laboratory. For further information, access the Technical Suppor Package (TSP) free on-line at www.techbriefs.com/tsp under he Software category.
This software is available for commercial licensing. Please contact Don Hart of the California Institute of Technology at (818) 393-3425. Refer to NPO-30693.
This Brief includes a Technical Support Package (TSP).
Evaluating Performance of Components
(reference NPO30693) is currently available for download from the TSP library.
Don't have an account?
Overview
The document is a Technical Support Package from NASA's Jet Propulsion Laboratory (JPL) focused on evaluating the performance of components within the framework of the Common Component Architecture (CCA). It is identified by the reference number NPO-30693 and is part of NASA Tech Briefs aimed at disseminating aerospace-related developments with broader technological, scientific, or commercial applications.
The primary objective of the software discussed in the document is to assess the usability and performance implications of using componentized software libraries compared to conventional approaches. Specifically, it evaluates the Parallel Pyramid 2D Adaptive Mesh Refinement (AMR) library, which is a critical tool in computational applications, particularly in the context of NASA's work.
Key features of the software include its design, where both the software library and the main program are structured as components. This allows them to be loaded into memory and interconnected by a framework program, enhancing modularity and flexibility. The software serves as an experimental prototype to measure the performance penalties associated with adopting a component-based architecture, which is increasingly relevant for applications at JPL and potentially other NASA divisions.
The document outlines the challenges the software aims to address, particularly the learning curve for non-computer scientists, such as application or domain scientists, who may need to write components. To facilitate this, the software includes a simple "Hello world!" tutorial example, which serves as an introductory exercise for users unfamiliar with component programming.
Additionally, the software records the time taken to develop a componentized version of an existing application, allowing for a direct comparison of performance between the traditional and componentized methods. This evaluation is crucial for understanding how componentization can impact application performance and development time.
The Technical Support Package also provides contact information for further assistance and resources available through NASA's Scientific and Technical Information (STI) Program Office, emphasizing NASA's commitment to sharing knowledge and fostering innovation in aerospace technology.
In summary, this document serves as a comprehensive guide to a software tool designed to evaluate the CCA's effectiveness, highlighting its potential benefits and challenges in the context of NASA's computational applications.
