University of Maryland has been recognized as a CUDA Center of Excellence. Amitabh Varshney‚ Professor of Computer Science‚ comments: "Maryland was one of the first universities to start integrating the use of GPUs and the CUDA architecture into our courses and research." Other CCOEs include Cambridge University‚ Chinese Academy of Sciences‚ Harvard‚ National Taiwan University‚ Tokyo Institute of Technology‚ Tsinghua University‚ University of Illinois at Urbana-Champaign‚ University of Tennessee and University of Utah. See: http://twitthis.com/zyjzci
Moldex3D is a 3D injection molding simulation software that helps users evaluate and optimize part and mold designs before manufacturing and production. "We are impressed with the computational speed up that we have seen with NVIDIA´s GPUs‚" says Dr. David Hsu‚ Vice President R&D of CoreTech System Co.‚ Ltd. See: http://bit.ly/9cLfnB
Bunkspeed‚ a provider of rendering and visualization software‚ has selected iray rendering technology from mental images to power its next-generation photorealistic rendering application‚ called Bunkspeed SHOT. Bunkspeed SHOT´s integration with iray will exploit the parallel processing power of CUDA-enabled GPUs. See: http://is.gd/7TQU1
In a recent nTersect blog entry‚ NVIDIA´s Mark Priscaro writes: "Adobe has redesigned their video rendering and playback engine to harness the CUDA parallel processing architecture of Quadro GPUs. The result is a fluid‚ real-time editing experience for adding additional effects‚ multiple layers‚ or ultra high resolution content. No more wasting time waiting for things like Encoding and Exporting progress bars to slowly fill the box." Read more about the Adobe Mercury Playback Engine here: http://is.gd/86HRt
Tech pub VentureBeat recently covered Moscow-based Kaspersky Lab‚ writing: "Kaspersky‚ which entered the U.S. market in 2005‚ protects 250 million users from cyber threats. It has to analyze tens of thousands of files each day to figure out if they´re variants of known computer viruses. To help with the process‚ it started using CUDA to assist in the filtering." See the article and video here: http://bit.ly/cKedjj
Neural networks‚ which are amazingly parallel‚ are used in pattern recognition‚ robotic controllers‚ and military applications‚ among others. For these networks to be useful they need to be trained; standard back-propagation is one of the common methods used to train them. In this study‚ CUDA is used to implement these algorithms on the GPU. Citation: A. Guzhva‚ S. Dolenko‚ I. Persiantse; Lomonosov Moscow State University. See: http://is.gd/885tF
"Programming Massively Parallel Processors: A Hands-on Approach‚" co-written by Dr. David B. Kirk‚ NVIDIA Fellow‚ and Professor Wen-mei Hwu of the University of Illinois‚ is available at: Elsevier or Amazon.