NVIDIA's CUDA will be an "interesting footnote" in h

Speaking with CustomPC, Intel Senior Vice President Pat Gelsinger said that NVIDIA's CUDA initiative and other programming models like CUDA, which harnesses the power of the GPU to perform tasks that have traditionally been handled by CPUs will be an "interesting footnote in the history of computing annals". According to Gelsinger, developers aren't willing to learn to program for it: "The problem that we’ve seen over and over and over again in the computing industry is that there’s a cool new idea, and it promises a 10x or 20x performance improvements, but you’ve just got to go through this little orifice called a new programming model,’ Gelsinger explained to Custom PC. Those orifices, says Gelsinger, have always been ‘insurmountable as long as the general purpose computing models evolve into the future.’" Gelsinger goes on to state that Intel's approach with Larrabee -- taking multiple x86 compatible processing cores and using them for graphics -- is more developer friendly as they're already familiar with x86.

Of course, what Gelsinger doesn't mention is that CUDA and ATI's equivalent, Brook+ are largely based on C+, a programming language that all developers have coded for at some point in time. OpenCL is another standard that is compatible with AMD and NVIDIA GPUs.

In any case, with all the buzz surrounding Larrabee years before it has even been launched, Intel is definitely setting expectations high for their upcoming GPU.