120 teraflop architecture
NVIDIA CEO Jensen Huang presented the first Tesla V100 GPUs to the top 15 AI research institutions in his NVIDIA AI Labs (NVAIL) program, and handed them over afterward.
September 11, 2017
This text has been automatically translated from German to English.
Among the research institutions were the German Research Center for Artificial Intelligence (DFKI) and the Max Planck Institute for Intelligent Systems.
The presentation took place at the Computer Vision and Pattern Recognition Conference in Honolulu at the end of July and was one of the highlights of the event for the more than 150 visitors.
The Tesla V100 GPUs are based on the NVIDIA Volta architecture, which Huang presented at the GPU Technology Conference (GTC) in Silicon Valley in May.
Volta is designed to enable massive advances in artificial intelligence and high-performance computing. The architecture is equipped with 21 billion transistors and delivers deep learning performance of 120 teraflops.
DE
EN
ES
FR
