The high performance Fortran handbook
The high performance Fortran handbook
PVM: Parallel virtual machine: a users' guide and tutorial for networked parallel computing
PVM: Parallel virtual machine: a users' guide and tutorial for networked parallel computing
Global arrays: a nonuniform memory access programming model for high-performance computers
The Journal of Supercomputing
The visualization toolkit (2nd ed.): an object-oriented approach to 3D graphics
The visualization toolkit (2nd ed.): an object-oriented approach to 3D graphics
MPI: The Complete Reference
Frame-based components for generalized particle methods
HPDC '97 Proceedings of the 6th IEEE International Symposium on High Performance Distributed Computing
Jabiru: Harnessing Java 3D Behaviors for Device and Display Portability
IEEE Computer Graphics and Applications
A Component Architecture for High-Performance Scientific Computing
International Journal of High Performance Computing Applications
International Journal of High Performance Computing Applications
Level-oriented universal visual representation environment
Annales UMCS, Informatica
| Hi-index | 0.00 |
This paper will discuss the development of two viewer interfaces for the CUMULVS system, one for virtual reality (VR) visualization via ImmersaDeskTM/CAVETM systems, and one for 3D data visualization using the commercial component-based AVS/Express visualization environment. The CUMULVS (Collaborative, User Migration, User Library fee Visualization and Steering) system, developed at Oak Ridge National Laboratory, is an essential platform for interacting with high-performance scientific simulation programs on-the-fly. It provides runtime visualization of data while they are being computed, as well as coordinated computational steering, application-directed checkpointing and fault recovery mechanisms, and rudimentary model coupling functions. CUMULVS consists of a set of cooperative libraries that enable the dynamic attachment of front-end "viewer" programs to running applications, for interactive visualization of extracted data snapshots using a variety of visualization tools. A development strategy will be presented for integrating CUMULVS with the given visualization libraries and environments, including discussion of the various data transformations and the visualization pipeline necessary for converting raw CUMULVS data into fully rendered graphical entities. In addition to the immersive VR CUMULVS viewer, an overview of the object-based AVS/Express CUMULVS viewer design will be presented, including discussion of the various components, modules, macros and user interfaces. A comparison will be made of the two viewer design approaches.