Computer H igh-speed, wide-area networks have made it both possible and desirable to interconnect geographically distributed applications that control distributed collections of scientific data, remote scientific instruments, and highperformance computer systems. Such an application might, for example, control a remote radio telescope, transmit raw data from the telescope site to a distributed data archive, and concurrently convolve the data to create images for real-time visualization. Developing just such a distributed application infrastructure is the goal of our partners in the National Computational Science Alliance, one of the NSF Partnerships for an Advanced Computational Infrastructure. Although interconnecting these applications enables geographically distributed science and engineering teams to collaborate in new ways, the resultant distributed computations pose significant performance analysis and optimization challenges. First, the execution environments of geographically distributed applications are far less deterministic than those of locally distributed, parallel applications. 1 Network bandwidths and latencies, computing resources, and available data repositories can vary from one execution to another, and even during a single execution. Consequently, identifying and correcting performance bottlenecks exposed during one execution may not benefit later executions. Second, distributed applications are highly complex. Application components execute atop disparate system software and hardware. Real-time instruments often impose scheduling and access constraints. Accessing data repositories sometimes necessitates data translation for correlation with experimental or computational data. Finally, enabling effective remote interaction and visualization necessitates quality-ofservice (QoS) guarantees. Incorporating QoS into these hardware and software systems further increases their complexity. Historically, performance analysis has focused on monolithic applications executing on large, standalone, parallel systems. In such a domain, measurement, postmortem analysis, and code optimization suffice to eliminate performance bottlenecks and optimize applications. Most existing performance analysis systems-for example, SvPablo, 2 Medea, 3 and Paragraph 4-use only postmortem analysis. To tune the emerging distributed applications, however, a new generation of online performance measurement and optimization tools must adapt application behavior dynamically as resource availability changes. In addition to providing real-time adaptive control, new performance tools must gather data from multiple sources and software levels (application, library, system, and network). Furthermore, these tools must enable geographically dispersed teams to collaborate in identifying and correcting performance problems. This capability requires support of distributed visualization and control, as well as support of both synchronous and asynchronous collaboration. The Virtue prototype exploits human sensory capabilities to help performa...

No abstract

We present a new external memory multiresolution surface representation for massive polygonal meshes. Previous methods for building such data structures have relied on resampled surface data or employed memory intensive construction algorithms that do not scale well. Our proposed representation combines efficient access to sampled surface data with access to the original surface. The construction algorithm for the surface representation exhibits memory requirements that are insensitive to the size of the input mesh, allowing it to process meshes containing hundreds of millions of polygons. The multiresolution nature of the surface representation has allowed us to develop efficient algorithms for view-dependent rendering, approximate collision detection, and adaptive simplification of massive meshes. The empirical performance of these algorithms demonstrates that the underlying data structure is a powerful and flexible tool for operating on massive geometric data.

An experimental telerobotics (TR) simulation is described suitable for studying human operator (H.0.) performance.Simple manipulator pick-and -place and tracking tasks allowed quantitative comparison of a number of calligraphic display viewing conditions. The Ames -Berkeley enhanced perspective display was utilized in conjunction with an experimental helmet mounted display system (HMD) that provided stereoscopic enhanced views. Two degree -of-freedom rotations of the head were measured with a Helmholtz coil instrument and these angles used to compute a directional conical window into a 3 -D simulation.The vector elements within the window were then transformed by projective geometry calculations to an intermediate stereoscopic display, received by two video cameras and imaged onto the HMD mini -display units (one -inch CRT video receivers) mounted on the helmet.An introduced communication delay was found to produce decrease in performance. in considerable part, this difficulty could be compensated for by preview control information. That neurological control of normal human movement contains a sampled data period of 0.2 seconds may relate to this robustness of H.O. control to delay.A number of control modes could be compared in this TR simulation, including displacement, rate an 3cceleratory control using position and force joysticks.A homeomorphic controller turned out to be no better than .joysticks; the adaptive properties of the H.O. can apparently permit quite good control over a variety of controller configurations and control modes. Training by optimal control example seemed helpful in preliminary experiments.

We studied the effects on oil sweep efficiency of the proportion, hierarchical organization, and connectivity of high-permeability open-framework conglomerate (OFC) cross-sets within the multi-scale stratal architecture found in fluvial deposits. Utilizing numerical simulations and the RVA/Paraview open-source visualization package, we analyzed oil production rate, water breakthrough time, and spatial and temporal distribution of residual oil saturation. The effective permeability of the reservoir exhibits large-scale anisotropy created by the organization of OFC cross-sets within unit bars, and the organization of unit bars within compound bars. As a result oil sweep efficiency critically depends on the direction of the pressure gradient. When pressure gradient is oriented normal to paleoflow direction, the total oil production and the water breakthrough time are larger, and remaining oil saturation is smaller. This result is found regardless of the proportion or connectivity of the OFC cross-sets, within the ranges examined. Contrary to expectations, the total amount of trapped oil due to the effect of capillary trapping does not depend on the pressure gradient within the examined range. Hence the pressure difference between production and injection wells does not affect sweep efficiency, although the spatial distribution of oil remaining in the reservoir depends on this value. Whether or not clusters of connected OFC span the domain does not affect sweep efficiency, only the absolute rate of oil production. The RVA/Paraview application allowed us to visualize and examine these non-intuitive results.Oil sweep efficiency is fundamentally controlled by the nature of immiscible displacement of a non-wetting liquid by a wetting liquid in porous media (Buckley and Leverett, 1942). This process includes the effects of capillary pressure and relative permeability on oil trapping and early water breakthrough (Kortekaas, 1985;Corbett et al.