Issue link: https://digital.copcomm.com/i/6960
ested parties. OpenCL is also a development language, and Nvidia is evolving CUDA to co-exist with OpenCL; in a subtle bit of mar- keting eloquence, Nvidia now refers to CUDA as CUDA for CL. Nvidia arch rival ATI has developed the Stream architecture for GPGPU and has committed to OpenCL. e company has been somewhat schizophrenic about its commitment to GPU compute, probably be- cause it has had to pick its fi ghts more care- fully than its wealthier competitors, Intel and Nvidia. Now, however, AMD seems to be con- centrating on its Stream initiative. e rewards for GPU compute are huge: ere are applica- tions that are seeing a speed up of 300x, and improvements of 10x are common. The Once and Future Larrabee Intel has not always been solely an x86 processor builder. e company has had other semicon- ductor architectures, most notably the ARM- based XScale which was eventually spun off to Marvell. When Intel sold its XScale technology, it was based on the longevity of the x86, and the company's position is that there is nothing you can't do with x86 cores, including graphics. Larrabee, which Intel hoped to be selling as a graphics processor in 2010, has multiple x86 cores. Intel has not announced how many, but it is generally believed there are 32 to 48 x86 cores in Larrabee. e advantage Larrabee has, says Intel, is in being more easily programma- ble for traditional computer programs, but In- tel had something of the same problem mak- ing x86 cores behave like graphics processors as the GPU guys have making GPUs handle CPU-type jobs. A GPU is an SIMD (single instruction, multiple data) processor, while a multi- or many-core x86 processor is designed for MIMD (mul- tiple instructions, multiple data) operations. e com- pute world has both prob- lems, and neither is more important than the other, a fact that has gotten lost in the competition between the big players: AMD, Intel, and Nvidia. Larrabee generated a lot of excitement as a rendering engine that might be able to reduce the cost, size, and power consumption of huge rendering farms, but as is now well known, Intel has pulled back from the brink. e company built the chip and demonstrated it reaching 1 terafl op per- formance on a single precision (SGEMM) test at SC09. Unfortunately, Intel was pushing develop- ment of Larrabee as a strong competitor to graphics processors, much to the bemuse- ment of outsiders who can clearly perceive the strength of Larrabee for a much broader type of computing. At the Super Computing conference, Intel CEO Justin Rattner seemed to be repositioning Larrabee, stressing the im- portance of MIMD operations. As Intel was reaching an internal deadline for Larrabee, the stakehold- ers called for a major time- out. ey had not worked out the diffi culties of pro- gramming Larrabee. Above all, Intel wanted Larrabee to come out a winner, and to do that, the fi rm had to meet the high expectations it had set for graphics per- formance and give devel- opers tools that would be easy to use. at was not happening as the managers thought it should. e Larrabee name is probably tainted, but Intel's work in this fi eld is part of an ongoing initia- tive that's not going away. Almost concurrent with the announcement that Intel would pause in the creation a graphics chip, the compa- ny announced a 48-core, tera-scale proces- sor developed in India as a cloud computer in a chip. Meanwhile, Fusion Fusion, AMD's grand vision, combines the GPU and the CPU. In one sense, it is a de- sign that will enable low-cost computers and mobile devices to take the idea of an integrat- ed processor one step further than the inte- grated graphics processors that have come to dominate mainstream and low-end comput- ing. But, AMD also sees the potential for a raft of Fusion processors all lined up and working hard on parallel and linear problems. e fact of the matter is that the world needs both CPUs and GPUs to handle the diff erent problems that are out there. In most applications, the CPU and GPU are working in tandem. It's All in the Language e challenge in high-performance comput- ing is not necessarily in building the biggest, baddest, most effi cient processor—though that's by no means easy; it's also necessary to build something on which applications can be developed. e HPC applications of today are fabulous—truly fabulous, the stuff of myth and magic …they will cure cancer and re-create universes. However, the fi rst applications were built by dedicated scientists who have been able to twist their brains around the challenge of restating problems in ways the processors will understand. Here, an image of the Satellite Tobacco Mosaic Virus is colored by the electrostatic fi eld created by the virus capsid and contained RNA. The electrostatic fi eld was calculated on an Nvidia Tesla C1060 GPU, which ran 26 times faster than a single-core CPU or 6.6 times faster than a typical four-core CPU. Researchers are then able to work with the model and run simulations on GPU-accelerated workstations. February 2010 38 ■ ■ ■ ■ Computing Supercomputers are vital to scientifi c research. Here, positive (red) and negative (green) ions are placed into a ribosome in an effort to kill it. This process requires very large scale calculations of ribosome electrostatics that have been made possible by GPU computing. Image courtesy ECE at the University of Illinois at Champage-Urbana. Courtesy Nvidia.