The msu ERC UltraScope system consists of a distributed computing system, custom PCI cards, and GPS receivers. The UltraScope system allows precision timestamping of events in a distributed application on a system whe...
详细信息
ISBN:
(纸本)0780366611
The msu ERC UltraScope system consists of a distributed computing system, custom PCI cards, and GPS receivers. The UltraScope system allows precision timestamping of events in a distributed application on a system where the CPU and PCI clocks are synchronous. This paper investigates methods by which the UltraScope system can be expanded to asynchronous systems. The count offset and clock properties for an asynchronous system are computed. The spectrum of these characteristics are analyzed to try to improve the accuracy of the UltraScope system on this class of computing systems.
This study is concerned with improving the robustness of preconditioning methods for the Euler equations, particularly when computing flows involving a stagnation region. Specifically, a technique first proposed by Da...
详细信息
This paper describes the human immune system and its functionalities from a computational viewpoint. The objective of this paper is to provide the biological basis for an artificial immune system. This paper will also...
详细信息
This study attempts a systematic discussion of local preconditioning methods for the two-dimensional Euler equations, including an assessment of some of the large body of work already completed in this area. The metho...
详细信息
A procedure is presented for efficient generation of high-quality unstructured grids suitable for CFD simulation of high Reynolds number viscous flow fields. Layers of anisotropic elements are generated by advancing a...
详细信息
Object-order rendering techniques present an attractive approach to run-time visualization of structured grid data, particularly when combined with a parallel rendering paradigm such as image composition. The ability ...
详细信息
ISBN:
(纸本)1581132379
Object-order rendering techniques present an attractive approach to run-time visualization of structured grid data, particularly when combined with a parallel rendering paradigm such as image composition. The ability of this combination to exploit hardware exceeds that of parallel image order methods. However, certain configurations of grid boundaries prevent composition from being performed correctly. In particular, when the boundary between two partitions contains concave sections, the partitions may no longer be depth sorted correctly, a requirement for some visualization techniques such as direct volume rendering. This occurs because the concave boundary prevents even the simple ordering of two adjacent partitions. If the data may be repartitioned such that it can be depth sorted correctly, then an image composition approach is a viable option. To facilitate such an operation, we present an algorithm to analyze the geometric structure of a grid boundary and extract knowledge about how the boundary impacts depth sorting and therefore image composition. We then show through examples how this knowledge may be applied to create a set of partitions that may be properly depth sorted.
MPI has emerged as a popular way to write architecture-independent parallel programs. By modifying an MPI library and associated MPI run-time environment, transparent extraction of timestamped information is possible....
详细信息
Embedded high perfonnance computing is being called upon to provide critical computing resources with increasing frequency. The ability to tolerate faults during operation, both maintaining operational capability and ...
详细信息
General-purpose programmers have come to expect a high degree of portability among widely varying architectures. Advances in run-time systems for parallel programs have been proposed in order to harness available reso...
详细信息
ISBN:
(纸本)9780818685798
General-purpose programmers have come to expect a high degree of portability among widely varying architectures. Advances in run-time systems for parallel programs have been proposed in order to harness available resources as efficiently as possible. Simultaneously, advances in algorithmic methods of dynamically balancing computational load have been proposed in order to respond to variations in actual performance and therefore in run-time. The primary mechanism for harnessing idle resources effectively, task migration, can be used alongside the primary mechanism for dynamic load balancing, data redistribution. Besides the fact that the two methods can be used simultaneously to spur further increases in performance, the run-time information-gathering infrastructure necessary to detect and use idle resources can also benefit dynamically load-balanced applications. This paper describes an architecture for and preliminary implementation of a system that combines data-parallel load balancing with task-parallel load balancing. Performance test results are included as well.
暂无评论