GraphicsChip
Latest
NVIDIA launches Fermi next-gen GPGPU architecture, CUDA and OpenCL get even faster
NVIDIA had told us it would be accelerating its CUDA program to try and get an advantage over its competitors as OpenCL brings general-purpose GPU computing to the mainstream, and it looks like that effort's paying off -- the company just announced its new Fermi CUDA architecture, which will also serve as the foundation of its next-gen GeForce and Quadro products. The new features are all pretty technical -- the world's first true cache hierarchy in a GPU, anyone? -- but the big takeaway is that CUDA and OpenCl should run even faster on this new silicon, and that's never a bad thing. Hit up the read links for the nitty-gritty, if that's what gets you going. Read - NVIDIA Fermi siteRead - Hot Hardware analysis Read - PC Perspective analysis
ATI's R600 graphics chip hits snag
We've had our eye on ATI"s new top-end R600 graphics chip for some time now, first getting a look at some impressive early benchmarks and then being taken aback by the foot-long graphics card the chips will call home (at least in some configurations). Sadly, it seems that those with money and power (as in 270W) to spare will have to wait a bit longer to slot one of the behemoths into their own PCs, with The Inquirer reporting that the R600 chips, and consequently the graphics cards based on 'em, have been delayed yet again, now pushed back to sometime in the second quarter of this year. There doesn't seem to be any word on the reason for the delay, but the news apparently came straight from ATI parent company AMD. Given what the cards are likely to cost, however, we're guessing that at least some won't be too disappointed in the delay, with the extra time allowing you to save up some more money and make some more excuses for why you're spending so much on a graphics card.[Via TG Daily]
