Inside Nvidia’s GP100 Pascal GPU

On Tuesday at Nvidia’s 2016 GPU Technology Conference in San Jose, California, company CEO Jen-Hsun Huang took the stage and announced Tesla P100, the world’s most powerful workstation based on Pascal, its new 16-nanometer FinFET architecture.Nvidia’s GP100, based on 16nm Pascal architecture The chip has a stunning 15 billion transistors, up from the 8 billion found in last year’s Tesla M40 and 7.1 billion from the Tesla K40 in 2013. Nvidia claims the total chip has 150 billion transistors, so there are at least another 135 billion transistors in the wafer and memory dies.After the keynote, we had the opportunity to attend a session called “Inside Pascal,” hosted by Lars Nyland, a senior Nvidia architect who worked on Pascal, and Mark Harris, Nvidia’s chief technologist for GPU computing.Lars Nyland (left),…

Link to Full Article: Inside Nvidia’s GP100 Pascal GPU

Pin It on Pinterest

Share This

Join Our Newsletter

Sign up to our mailing list to receive the latest news and updates about and the Informed.AI Network of AI related websites which includes Events.AI, Neurons.AI, Awards.AI, and Vocation.AI

You have Successfully Subscribed!