Virtue: Performance visualization of parallel and distributed applications

High-speed, wide-area networks have made it both possible and desirable to interconnect geographically distributed lections of scientific data, remote scientific instruments, and high-performance computer systems. Historically, performance analysis has focused on monolithic applications e xecuting on large, stand-alone, parallel systems. In such a domain, measure ment, postmortem analysis, and code optimization suffice to eliminate perfo rmance bottlenecks and optimize applications. Distributed visualization, data mining, and analysis tools allow scientists to collaboratively analyze and understand complex phenomena. Likewise, rea l-time performance measurement and immersive performance display systems-th at is, systems providing large stereoscopic displays of complex data-enable collaborating groups to interact with executing software, tuning its behav ior to meet research and performance goals. To satisfy these demands, the authors designed Virtue, a prototype system t hat integrates collaborative, immersive performance visualization with real -time performance measurement and adaptive control of applications on compu tational grids. These tools enable physically distributed users to explore and steer the behavior of complex software in real time and to analyze and optimize distributed application dynamics.