Fujitsu Labs has found a better way to parallel graphics processors (GPU) for deep learning applications. Using ‘AlexNet’, 64 GPUs in parallel achieve 27x the speed of a single GPU for, as far as Fujitsu can determine, the world’s fastest processing. A conventional method to accelerate deep learning is to use multiple computers equipped with ...
Read full article: Better parallel performance for artificial inteligence
from News – Electronics Weekly http://ift.tt/2bVCcKC
via Yuichun
沒有留言:
張貼留言