PC Clusters for Virtual Reality

Raffin, Bruno; Soares, Luciano; Ni, Tao; Ball, Robert; Schmidt, Greg S.; Livingston, Mark; Staadt, Oliver; May, Richard

doi:10.1109/vr.2006.107

Cited by 27 publications

(17 citation statements)

References 38 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The system can take advantage of more current technologies, since the commodity industry regularly releases new and more powerful devices with decreasing costs. As compared with special purpose hardware, its compliance with standards favors software and hardware interoperability [12].…”

Section: Characteristicsmentioning

confidence: 99%

“…However, since each node renders an arbitrary fragment of the scene or model, the rendering results must be collected and composited at the display nodes before they can be displayed. The I/O overheads of this composition processing in the sort-last approach are limiting factors for dynamic visualization on the clusterbased LHRD [12], [73]. When it is used for tiled display setups, sort-last is typically used for static visualization of highly complex models on LHRD rather than for general dynamic visualizations [74].…”

Section: Immediate and Parallel Renderingmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Software Frameworks for Cluster-Based Large High-Resolution Displays

Chung

Andrews

North

2014

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Abstract-Large high-resolution displays (LHRD) enable visualization of extremely large-scale data sets with high resolution, large physical size, scalable rendering performance, advanced interaction methods, and collaboration. Despite the advantages, applications for LHRD can be developed only by a select group of researchers and programmers, since its software implementation requires design and development paradigms different from typical desktop environments. It is critical for developers to understand and take advantage of appropriate software tools and methods for developing their LHRD applications. In this paper, we present a survey of the state-of-the-art software frameworks and applications for cluster-based LHRD, highlighting a three-aspect taxonomy. This survey can aid LHRD application and framework developers in choosing more suitable development techniques and software environments for new LHRD applications, and guide LHRD researchers to open needs in LHRD software frameworks.

show abstract

Section: Characteristicsmentioning

confidence: 99%

Section: Immediate and Parallel Renderingmentioning

confidence: 99%

A Survey of Software Frameworks for Cluster-Based Large High-Resolution Displays

Chung

Andrews

North

2014

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…While the sort-last method enables to divide the terrain model more evenly, this method requires reading back the rendered image pixels in each of the nodes in order to compose them into the final terrain on the large display ( Fig. 6(right)) and it causes serious network overhead as the size of VTMS data increases [25]. Therefore, sort-last is more appropriate for static visualization in order to visualize an extremely large terrain data set [26].…”

Section: Developmental Choices and Implementationmentioning

confidence: 99%

Developing Large High-Resolution Display Visualizations of High-Fidelity Terrain Data

Chung¹,

North

Ferris

2013

Journal of Computing and Information Science in Engineering

View full text Add to dashboard Cite

The vehicle terrain measurement system (VTMS) allows highly detailed terrain modeling and vehicle simulations. Visualization of large-scale terrain datasets taken from VTMS provides better insights into the characteristics of the pavement or road surface. However, the resolution of these terrain datasets greatly exceeds the capability of traditional graphics displays and computer systems. Large high-resolution displays (LHRDs) enable visualization of large-scale VTMS datasets with high resolution, large physical size, scalable rendering performance, advanced interaction methods, and collaboration. This paper investigates beneficial factors, implementation issues, and case study applications of LHRDs for visualizing large, high-fidelity, terrain datasets from VTMS. Two prototype visualizations are designed and evaluated with automotive and pavement engineers to demonstrate effectiveness of LHRDs for multiscale tasks that involve understanding pavement surface details within the overall context of the terrain. IntroductionAdvances in modern 3D laser measurement systems, GPS, and various sensor technologies make it possible to obtain detailed high-fidelity terrain measurements. For example, the VTMS scans pavement and other road surfaces with millimeter precision over large areas and long driving distances [1]. These terrain measurements are of particular interest to automotive and pavement engineers who perform vehicle simulations and pavement evaluations. Such data enable detailed analysis and high-fidelity simulation of interactions between vehicle systems and terrain, to predict behaviors and validate vehicle designs. Multiscale terrain data that are both detailed and large in extent are very useful for monitoring pavement health and planning road repair [2,3].Simultaneously, advances in LHRD systems have made it possible to visualize large multiscale data [4] (for example, see Fig. 1). LHRD significantly increases visual scalability over standard small displays with its large field of view and high resolution [5], enabling visualizations to display a large amount of detailed data. Such displays have shown significant userperformance advantages in a variety of visual analytics and complex information work tasks that involve a large amount of data in other data domains [6][7][8].In this paper, we propose the coupling of high-fidelity terrain measurement systems with large high-resolution display systems to support detailed visual analysis of terrain by automotive and pavement engineers. The main purpose of this paper is to demonstrate and accommodate actual pavement analyses utilizing both VTMS and LHRD. Our basic hypothesis is that the combination of both systems will enable engineers to better understand, validate, and compare high-fidelity terrain datasets, in conjunction with vehicle simulations and pavement engineering, in a more interactive and collaborative manner.To that end, we design, develop, and evaluate two prototype visualizations of high-fidelity terrain data on an LHRD to support various pavemen...

show abstract

“…In master-slave mode, an instance of the application is executed on each node of the cluster, while in client-server mode a client node issues rendering tasks to the render servers via network. A good survey on distributed rendering software was given by Ni et al [36] and Raffin et al [39]. Some of the best known software packages include CAVELib [8], VRjuggler [5], Syzygy [44], AnyScreen [10], OpenSG [40], Chromium [17], NAVER [18], Jinx [47] , and CGLX [11].…”

Section: Related Workmentioning

confidence: 99%

Giga-Scale Multiresolution Volume Rendering on Distributed Display Clusters

Thelén

Meyer

Ebert

et al. 2011

Human Aspects of Visualization

View full text Add to dashboard Cite

Abstract.Visualizing the enormous level of detail comprised in many of today's data sets is a challenging task and demands special processing techniques as well as a presentation on appropriate display devices. Desktop computers and laptops are often not suited for this task because data sets are simply too large and the limited screen size of these devices prevents users from perceiving the entire data set and severely restricts collaboration. Large high-resolution displays that combine the images of multiple smaller devices to form one large display area have proven to be an adequate solution to the ever-growing quantity of available data. The displays offer enough screen real estate to visualize such data sets entirely and facilitate collaboration, since multiple users are able to perceive the information at the same time. For an interactive visualization, the CPUs on the cluster driving the GPUs can be used to split up the computation of a scene into different areas, where each area is computed by a different rendering node.In this paper we focus on volumetric data sets and introduce a dynamic subdivision scheme incorporating multi-resolution wavelet representation to visualize data sets with several gigabytes of voxel data interactively on distributed rendering clusters. The approach makes efficient use of the resources available on modern graphics cards which mainly limit the amount of data that can be visualized. The implementation was successfully tested on a tiled display comprised of 25 compute nodes driving 50 LCD panels.

show abstract

PC Clusters for Virtual Reality

Cited by 27 publications

References 38 publications

A Survey of Software Frameworks for Cluster-Based Large High-Resolution Displays

A Survey of Software Frameworks for Cluster-Based Large High-Resolution Displays

Developing Large High-Resolution Display Visualizations of High-Fidelity Terrain Data

Giga-Scale Multiresolution Volume Rendering on Distributed Display Clusters

Contact Info

Product

Resources

About