The first full-fat GPU based on Nvidia’s all-new Pascal architecture is here. And while the Tesla P100 is aimed at professionals and deep learning systems rather than consumers, if consumer Pascal GPUs are anything like it—and there’s a very good chance they will be—gamers and enthusiasts alike are going to see a monumental boost in performance. The Tesla P100 is the first full-size Nvidia GPU based on the TSMC 16nm FinFET manufacturing process—like AMD, Nvidia has been stuck using an older 28nm process since 2012—and the first to feature the second generation of High Bandwidth Memory (HBM2). Samsung began mass production of faster and higher capacity HBM2 memory back in January. While recent rumours suggested that both Nvidia and AMD wouldn’t use HMB2 this year due to it being prohibitively expensive—indeed, AMD’s recent roadmap suggests that its new Polaris GPUs won’t use HBM2 —Nvidia has at least taken the leap with its professional line of GPUs. The result of the P100’s more efficient manufacturing process, architecture upgrades, and HBM2 is a big boost in performance over Nvidia’s current performance champs like the Maxwell-based Tesla M40 and the Titan X/Quadro M6000. Nvidia says the P100 reaches 21.2 teraflops of half-precision (FP16) floating point performance, 10.6 teraflops of single precision (FP32), and 5.3 teraflops (1/2 rate) of double precision. By comparison, the Titan X and Tesla M40 offer just 7 teraflops of single precision floating point performance. Read 9 remaining paragraphs | Comments
Continue Reading:
Nvidia unveils first Pascal graphics card, the monstrous Tesla P100
