"Apple knows a lot about CUDA," Huang said, implying the company might be ready to formally embrace Nvidia's technology to make it easier to exploit graphics chips inside Macs. Apple's implementation "won't be called CUDA, but it will be called something else," Huang said in an interview here at Nvidia's headquarters on Wednesday.
Software developers are interested in the potential of graphics chips because of their ability to embrace parallelism, or the simultaneous execution of different types of problems. CPUs from Intel and AMD are designed as general-purpose processors, able to handle any kind of code a programmer can throw at the chip. But until multicore chips became all the rage, those CPUs were basically designed to tackle one problem, and then move onto the next problem: and software for those chips has been designed accordingly.
GPUs, on the other hand, break up a problem into much smaller bits and process it in parallel with other problems at a very high rate of speed. To this point, however, only specialized applications such as graphics software or high-performance computing applications have been able to take advantage of that raw horsepower. Nvidia, AMD, and Intel are all working on ways to allow everyday programmers to exploit the unique characteristics of graphics processors.
Apple to adopt NVIDIA's CUDA technology?
Posted on Friday, Jun 06 2008 @ 23:58 CEST by Thomas De Maesschalck