Luc Renambot

The distributed ASCI Supercomputer project

The Distributed ASCI Supercomputer (DAS) is a homogeneous wide-area distributed system consisting of four cluster computers at different locations. DAS has been used for research on communication software, parallel languages and programming systems, schedulers, parallel applications, and distributed applications. The paper gives a preview of the most interesting research results obtained so far in the DAS project.

High-performance dynamic graphics streaming for scalable adaptive graphics environment

The scalable adaptive graphics environment (SAGE) is specialized middleware for enabling data, high-definition video and extremely high-resolution graphics to be streamed in real-time from remotely distributed rendering and storage clusters to scalable display walls over ultra high-speed networks. In this paper, we present the SAGE architecture, focusing on its dynamic graphics streaming capability. In the SAGE framework, multiple visualization applications can be streamed to large tiled displays and viewed at the same time. The application windows can be moved, resized and overlapped like any standard desktop window manager. Every window movement or resize operation requires dynamic and non-trivial reconfiguration of the involved graphics streams. This approach has been successfully shown to scale to support streaming on the LambdaVision 100 megapixel display wall. SAGE is now being extended to support distance collaboration with multiple endpoints by streaming visualization to all the participants

CAVE2: a hybrid reality environment for immersive simulation and information analysis

Hybrid Reality Environments represent a new kind of visualization spaces that blur the line between virtual environments and high resolution tiled display walls. This paper outlines the design and implementation of the CAVE2TM Hybrid Reality Environment. CAVE2 is the world’s first near-seamless flat-panel-based, surround-screen immersive system. Unique to CAVE2 is that it will enable users to simultaneously view both 2D and 3D information, providing more flexibility for mixed media applications. CAVE2 is a cylindrical system of 24 feet in diameter and 8 feet tall, and consists of 72 near-seamless, off-axisoptimized passive stereo LCD panels, creating an approximately 320 degree panoramic environment for displaying information at 37 Megapixels (in stereoscopic 3D) or 74 Megapixels in 2D and at a horizontal visual acuity of 20/20. Custom LCD panels with shifted polarizers were built so the images in the top and bottom rows of LCDs are optimized for vertical off-center viewing- allowing viewers to come closer to the displays while minimizing ghosting. CAVE2 is designed to support multiple operating modes. In the Fully Immersive mode, the entire room can be dedicated to one virtual simulation. In 2D model, the room can operate like a traditional tiled display wall enabling users to work with large numbers of documents at the same time. In the Hybrid mode, a mixture of both 2D and 3D applications can be simultaneously supported. The ability to treat immersive work spaces in this Hybrid way has never been achieved before, and leverages the special abilities of CAVE2 to enable researchers to seamlessly interact with large collections of 2D and 3D data. To realize this hybrid ability, we merged the Scalable Adaptive Graphics Environment (SAGE) - a system for supporting 2D tiled displays, with Omegalib - a virtual reality middleware supporting OpenGL, OpenSceneGraph and Vtk applications.

The future of the CAVE

The CAVE, a walk-in virtual reality environment typically consisting of 4–6 3 m-by-3 m sides of a room made of rear-projected screens, was first conceived and built in 1991. In the nearly two decades since its conception, the supporting technology has improved so that current CAVEs are much brighter, at much higher resolution, and have dramatically improved graphics performance. However, rear-projection-based CAVEs typically must be housed in a 10 m-by-10 m-by-10 m room (allowing space behind the screen walls for the projectors), which limits their deployment to large spaces. The CAVE of the future will be made of tessellated panel displays, eliminating the projection distance, but the implementation of such displays is challenging. Early multi-tile, panel-based, virtual-reality displays have been designed, prototyped, and built for the King Abdullah University of Science and Technology (KAUST) in Saudi Arabia by researchers at the University of California, San Diego, and the University of Illinois at Chicago. New means of image generation and control are considered key contributions to the future viability of the CAVE as a virtual-reality device.

JuxtaView - a tool for interactive visualization of large imagery on scalable tiled displays

JuxtaView is a cluster-based application for viewing ultra-high-resolution images on scalable tiled displays. We present in JuxtaView, a new parallel computing and distributed memory approach for out-of-core montage visualization, using LambdaRAM, a software-based network-level cache system. The ultimate goal of JuxtaView is to enable a user to interactively roam through potentially terabytes of distributed, spatially referenced image data such as those from electron microscopes, satellites and aerial photographs. In working towards this goal, we describe our first prototype implemented over a local area network, where the image is distributed using LambdaRAM, on the memory of all nodes of a PC cluster driving a tiled display wall. Aggressive prefetching schemes employed by LambdaRAM help to reduce latency involved in remote memory access. We compare LambdaRAM with a more traditional memory-mapped file approach for out-of-core visualization.

VIRPI: a high-level toolkit for interactive scientific visualization in virtual reality

Research areas that require interactive visualization of simulation data tend to dismiss virtual reality due to the lack of accessible tools for application specialists. This paper presents an integral toolkit for interactive visualization in virtual reality environments. The toolkit defines a framework to build applications that allow the user to interact with arbitrary simulation software and describe virtual measurement tools for the visualized data. The approach is illustrated with a case study in medical imaging.

TeraVision: a distributed, scalable, high resolution graphics streaming system

In electronically mediated distance collaborations involving scientific data, there is often the need to stream the graphical output of individual computers or entire visualization clusters to remote displays. This work presents TeraVision as a scalable platform-independent solution which is capable of transmitting multiple synchronized high-resolution video streams between single workstations and/or clusters without requiring any modifications to be made to the source or destination machines. Issues addressed include: how to synchronize individual video streams to form a single larger stream; how to scale and route streams generated by an array of M/spl times/N nodes to fit a X/spl times/Y display; and how TeraVision exploits a variety of transport protocols. Results from experiments conducted over gigabit local-area networks and wide-area networks (between Chicago and Amsterdam), are presented. Finally, we propose the scalable adaptive graphics environment (SAGE) - an architecture to support future collaborative visualization environments with potentially billions of pixels.

Visibility masks for solving complex radiosity computations on multiprocessors

This paper presents a strategy to handle very complex scenes for radiosity computation. Compared to other radiosity algorithms, our solution focuses on the ability to compute the radiosity in local environments instead of solving the problem for the whole environment. By splitting the problem into subproblems, using virtual interface and visibility masks, our technique is able to achieve better data locality than other standard solutions. We present an implementation of visibility masks on a distributed memory parallel computer (Intel Paragon XP/S).

Ultrascale Collaborative Visualization Using a Display-Rich Global Cyberinfrastructure

The scalable adaptive graphics environment (SAGE) is high-performance graphics middleware for ultrascale collaborative visualization using a display-rich global cyberinfrastructure. Dozens of sites worldwide use this cyberinfrastructure middleware, which connects high-performance-computing resources over high-speed networks to distributed ultraresolution displays.

Towards efficient parallel radiosity for DSM-based parallel computers using virtual interfaces

The paper presents the performance evaluation of a new technique for radiosity computation which aims at exploiting efficiently the different levels of a memory hierarchy of both sequential and parallel computers. Such ability is essential when dealing with complex environments having several millions of polygons. The principle of the technique is to split the initial environment into several sub-environments and compute the radiosity within each sub-environment. Exchange of energy between sub-environments is performed by means of virtual interfaces and visibility masks. The size of sub-environments can be adapted in order to fit into a cache or a local memory. The authors performed several experiments using an SGI Origin 2000 to show the effectiveness of the solution. It improves both the sequential and parallel execution of a progressive radiosity algorithm. The technique decreases the execution time on one processor of an SGI Origin 2000 by a factor of more than 5 and leads to a very good efficiency for complex environments (1 million of polygons) on a multiprocessor configuration.