Communications of the ACM
GPUs Reshape Computing
NVidia's Titan X graphics card, featuring the company's Pascal-powered graphics processing unit driven by 3,584 CUDA cores running at 1.5GHz.
Credit: GeForce.com
As researchers continue to push the boundaries of neural networks and deep learning—particularly in speech recognition and natural language processing, image and pattern recognition, text and data analytics, and other complex areas—they are constantly on the lookout for new and better ways to extend and expand computing capabilities. For decades, the gold standard has been high-performance computing (HPC) clusters, which toss huge amounts of processing power at problems—albeit at a prohibitively high cost. This approach has helped fuel advances across a wide swath of fields, including weather forecasting, financial services, and energy exploration.
However, in 2012, a new method emerged. Although researchers at the University of Illinois had previously studied the possibility of using graphics processing units (GPUs) in desktop supercomputers to speed processing of tasks such as image reconstruction, a group of computer scientists and engineers at the University of Toronto demonstrated a way to significantly advance computer vision using deep neural nets running on GPUs. By plugging in GPUs, previously used primarily for graphics, it was suddenly possible to achieve huge performance gains on computing neural networks, and these gains were reflected in superior results in computer vision.
No entries found