Computer Graphics World

September 2009 22 n n n n Graphics Cards Parallel processing has been so successful that more recent graphics cards can now sport GPUs with hundreds of processors each. While these processors are primar- ily tuned for graphics applications, they are still processors, and like every proces- sor, they can crunch numbers. In fact, the processors on graphics cards are especially good at floating-point math, which makes them very suitable for tasks like simulation and other math-intensive applications. More Power, More Work e first applications to use this processing power for work other than graphics were the gaming companies. ey moved com- plex calculations, such as particle systems and physics, to the graphics card, which al- lowed for faster games with richer content. e fact that this processing happened on the graphics card saved the CPU from get- ting bogged down and also saved band- width on the graphics interface. Soon, a number of industries were us- ing the power of graphics cards to aug- ment their applications, and graphics card vendors were quick to offer tools to help these developers tap into the power of their cards. ese days, graphics cards can be used as parallel computing platforms, per- forming such tasks as physical simulation, finance, fluid dynamics, and particle-sys- tem generation. e line where the com- puter stops and the graphics card begins has become very blurred, indeed. In fact, a whole new term has been coined for this: general-purpose graphics processing units, or GPGPUs. Nvidia has jumped headfirst into the GPGPU pool, and actually sells a gen- eral-purpose supercomputer called Tesla. is computer is essentially one of Nvidia's top-of-the-line graphics cards stripped of the display connectors and configured as either an upgrade card or an external box. e high-end version, dubbed the S1070, is a rack-mount system that offers its users four teraflops of computing power—sev- eral hundred times that of a standard PC. Many of these can be connected together to create a very powerful supercomputer. In fact, just a few years ago, Nvidia claimed that four of its S1070s connect- ed together would have enough comput- ing power to qualify it as one of the top 100 supercomputers. ese days, who knows how it would stack up, but it still represents an enormous amount of com- puting power for the desktop. With graphics cards encroaching on territory formerly the domain of systems vendors, there is also movement in the other direction. Intel, famously known for its x86 CPU platform, which drives the vast majority of desktops, is no stranger to graphics. In the consumer space, Intel does very well with its integrated graph- ics chips. ese chips are great for the average home user, but those who need higher-end graphics, such as gamers and content creators, will usually add a third- party card from Nvidia or ATI to boost graphics performance. A New Game? Intel is trying to take on the major graph- ics players not by competing directly with them, but by subtly changing the rules of the game. is will happen when Intel's new Larrabee chipset is set to ship at the end of this year. e chipset is designed primarily as a high-end graphics card, but with a twist. e Larrabee chip takes a completely different approach than tradi- tional graphics cards in that it doesn't use a dedicated graphics processor, but instead uses a massively parallel version of Intel's x86 chip geared toward graphics. Larrabee will include very little specialized graphics hardware, instead performing tasks like z-buffering, clipping, and blending in software—using a tile-based rendering ap- proach. is simple method could change the rules as to how high-end graphics are developed, because such processes as ren- dering will be left to software rather than the hardware traditionally used on graphics cards. is means developers would be free to customize the way an application renders its images, allowing for a much wider palette in the way the graphics look. Having x86-based processors on the graphics card also hits directly at the desk- top supercomputer paradigm put forth by Nvidia. e problem with a dedicated graphics processor is that it requires a dif- Developers in markets such as medical, bioscience, finance, oil and gas, and others can build programs using standard C language to run on Nvidia's graphics processors via the company's CUDA development environment.

• Cover