Nvidia claims that its Tesla boards and CUDA programming environment have revolutionized high-performance computing. Martin hasn't been able to try this himself and would like to hear from people who have. I’ve been getting a steady stream of press releases about GPU-based supercomputers using Nvidia Tesla and CUDA. A summary of this year’s milestones came in a year-end letter from Nvidia: Launched the Tesla Personal Supercomputer – the world’s first desktop system to deliver cluster class performance at a conventional workstation price, opening up supercomputing to the masses. The Nvidia Tesla-powered TSUBAME supercomputer at the Tokyo Institute of Technology was ranked 29th in the world in the latest Top 500, making it the first GPU enabled cluster to enter the listing. Mathematica, the world’s most powerful general computation software announced that Mathematica 7 will be GPU accelerated through CUDA and will deliver performance improvements up to 100X to more than 3 million users. Nvidia Tesla and CUDA technologies are recognized by HPCWire and students and professionals clean up at SC08 industry awards demonstrating work based on Nvidia GPUs and the CUDA architecture. Nvidia’s CUDA toolkit and SDK hit key milestones – 150K downloads, 150 applications published on CUDA Zone, more than 50 schools now teach the CUDA programming model and more than 750 research papers now published. Given my background in scientific and engineering computing, I’ve been dying to try this stuff out first-hand, at least on a small scale, but as I’ve discussed previously my attempts to build a new programming workstation with a CUDA-compatible video card have been delayed by the economic meltdown and the need to remodel a bathroom at home.My past hands-on experience is that writing efficient parallel programs is hard, and that writing efficient parallel programs on a non-symmetric architecture is even harder. Nvidia claims to have made it easier. I’d love to hear directly from people who have done CUDA programming or used CUDA-enabled applications, whether or not it was on Tesla boards. What programs, tools and libraries did you use? How hard was it? What did it buy you? Were your speed-ups anything like the performance boosts claimed by Nvidia?I’d also love to hear directly from people who have used competitors to CUDA.Comment here, or write to me at martin_heller@infoworld.com. Software Development