Spotlight (July 2007)
Issue: Volume: 30 Issue: 7 (July 2007)

Spotlight (July 2007)

A new chip that provides unrivaled rendering performance is being launched by ARTVPS, developers of the only processor said to accelerate raytracing. The new AR500 processor has been re-engineered to run at almost twice the speed of its predecessor, correctly modeling every detail of surface shading or shadow and refracted or reflected rays of light to produce truly photorealistic, final images.

AR500 provides the power to RayBox—the new successor to ART­VPS’s RenderDrive network renderer and Pure PCi-X card. A desk-side system with 14 AR500 dual-core processors, RayBox takes advantage of leading-edge, high-performance PCI Express technology using a high-speed serial link to connect to any PC or Mac.

Industry expert Jon Peddie comments: “ARTVPS is a pioneer of dedicated raytracing hardware technology, and its next-generation processor, the AR500, has taken rendering to the next level. Offloading rendering to a dedicated processor rather than a graphics card means you can render more data faster and with great results.”

RayBox is compatible with ART­VPS’s RenderPipe software renderer and integrates seamlessly with Autodesk’s 3ds Max and Maya. The product is priced at $8300.



Jon Peddie Research (JPR) released its “2007 Digital Content Creation Report,” which this year focuses on 3D modeling and animation, 2D animation, digital video, graphics and imaging, and audio. According to the research, the total DCC market grew 16 percent from $2.6 billion to reach more than $3 billion in 2006. The fastest growing segments in the future will be interactive development and video, as the Web offers new distribution networks and new programming approaches, such as AJAX , to enable small, compelling applications to be developed that extend the power of individual Web sites.

JPR predicts the market will reach $4.9 billion by 2012, reflecting a compound annual growth rate of 10 percent. “We are seeing big shifts in the digital content creation market. For example, there have been game-changing moves by Adobe with the acquisition of Macromedia and Serious Magic, Autodesk’s acquisition of Alias and Colorfront, and Google’s acquisition of Sketchup and YouTube. “The changes are good, but companies will have to be nimble to adapt,” says Kathleen Maher, senior analyst at Jon Peddie Research and author of the report.

For the short term, the outlook appears good for all DCC segments. There are exciting prospects for consumer products and for a growing mainstream of professional products. There are some challenges ahead, as well, most notably for the graphics and imaging market.

Video is a more complicated process and, thus, is not easily boiled down to a few processes. In addition, new avenues of distribution, such as media players, YouTube, MySpace, and so forth are helping spur interest in consumer video editing.

The resport also finds that the professional market overall is moving away from proprietary systems and toward mainstream, desktop-based systems. Most companies selling professional DCC tools are trying to adjust to this trend because there is an obvious positive side: As tools become more accessible in price and ease of use, there are more people who can take advantage of them.

The 2007 version of the DCC report is available now for $5000 for single electronic copies from JPR.

High-performance computing in fields such as geosciences, molecular biology, and medical diagnostics enable discoveries that transform billions of lives every day. Universities, research institutions, and companies in these and other related fields face a daunting challenge: As their simulation models become exponentially complex, so does their need for vast computational resources.

Nvidia took a giant step in meeting this challenge with the recent announcement of a new class of processors based on a new graphics processing unit (GPU). Under the Tesla brand, Nvidia will offer a family of GPU computing products that will place the power previously available only from supercomputers in the hands of scientists and engineers, thereby transforming today’s workstations into “personal supercomputers.”

“Today’s science is no longer confined to the laboratory; scientists employ computer simulations before a single physical experiment is performed. This fundamental transition to computational methods is forging a new path for discoveries in science and engineering,” says Jen-Hsun Huang, president and CEO of Nvidia. “Tesla dramatically reduces computation times, in some cases from weeks to hours.”

The Tesla family of GPU computing solutions spans from PCs to large-scale server clusters and includes three new products. Tesla GPU Computing Processor is a dedicated computing board that scales to multiple Tesla GPUs inside a single PC or workstation. The Tesla GPU features 128 parallel processors and delivers up to 518 gigaflops of parallel computation. The GPU computing processor can be used in existing systems, partnered with high-performance CPUs.

The Tesla Deskside Supercomputer is a scalable computing system that includes two Nvidia Tesla GPUs and attaches to a PC or workstation through an industry-standard PCI Express connection. With multiple deskside systems, a standard PC or workstation is transformed into a personal supercomputer, delivering up to 8 teraflops of compute power to the desktop.

The Tesla GPU Computing Server, a 1U server housing up to eight Tesla GPUs, contains more than 1000 parallel processors that add teraflops of parallel processing to clusters. The Tesla GPU Server is the first server system of its kind to bring GPU computing to the data center.

Computing on Tesla is through the only C-language development environment for the GPU. Nvidia’s CUDA is a complete software development solution that includes a C-compiler for the GPU, debugger/profiler, dedicated driver, and standard libraries. CUDA simplifies parallel computing on the GPU by using the standard C language to create programs that process large quantities of data in parallel. Programs written with CUDA and run on Tesla can process thousands of threads simultaneously.

The GPU Computing processor ($1499), available in August,  includes a single 8-series GPU and delivers 518 gigaflops of computing power. Also available in the same period is the GPU Computing Deskside Supercomputer ($7500) whose two 8-series GPUs deliver 1 teraflop of computing power. The GPU Computing Server ($12,000  for a standard 1u server configuration) includes four 8-series GPUs delivering 2 teraflops of computing power. Qualification samples of the server will be available in September, with product availability late in the year.