Nvidia Rolls Out Kepler-based Quadro Workstation Cards By Jon K. Carroll August 14, 2012 12:50 AM Tags : Workstations Graphics Cards Hardware & Software GPUs Style Desktops Quadro Cloud Computing Memory Tom's Hardware Bandwidth Displays Nvidia Performance Dual Link Dvi Nvidia announced it first desktop workstation graphics card based on the Kepler GPU architecture. The Quadro K5000 features 4 GB of ECC GPU memory with 173GB/s of bandwidth, 1536 CUDA cores, two dual-link DVI and two DisplayPort 1.2 ports supporting up to four displays off of a single card. The card is specified to produce 2150 Gigaflops of single-precision floating point performance, and 90 Gigaflops of double precision floating-point performance. This represents a near doubling of single-precision performance over the previous Quadro 5000, but also represents a significant decrease in double-precision performance. The single-precision performance increase will greatly benefit some types of GPU acceleration, but the double-precision performance may hinder others. It would be a good idea to look at the performance figures for your specific application before deciding on a newer Kepler-based card over the previous-generation Fermi architecture. New to the K5000 series are bindless textures, which allows more textures to be available to shaders simultaneously, reducing the need for multiple render passes to render multiple textures. Pricing and availability information were not available at press time. Wolfgang Gruener is a contributor to Tom's IT Pro. He is currently principal analyst at Ndicio Research, a market analysis firm that focuses on cloud computing and disruptive technologies, and maintains the conceivablytech.com blog. An 18-year veteran in IT journalism and market research, he previously published TG Daily and was managing editor of Tom's Hardware news, which he grew from a link collection in the early 2000s into one of the most comprehensive and trusted technology news sources. See here for all of Wolfgang's Tom's IT Pro articles. Comment on this article ... Comment(s)| Comments