@article{Shaikhislamov_Sozykin_Voevodin_2020, title={Survey on Software Tools that Implement Deep Learning Algorithms on Intel/x86 and IBM/Power8/Power9 Platforms}, volume={6}, url={https://superfri.org/index.php/superfri/article/view/298}, DOI={10.14529/jsfi190404}, abstractNote={<p>Neural networks are becoming more and more popular in scientific field and in the industry. It is mostly because new solutions using neural networks show state-of-the-art results in the domains previously occupied by traditional methods, eg. computer vision, speech recognition etc. But to get these results neural networks become progressively more complex, thus needing a lot more training. The training of neural networks today can take weeks. This problems can be solved by parallelization of the neural networks training and using modern clusters and supercomputers, which can significantly reduce the learning time. Today, a faster training for data scientist is essential, because it allows to get the results faster to make the next decision.</p><p>In this paper we provide an overview of distributed learning provided by the popular modern deep learning frameworks, both in terms of provided functionality and performance. We consider multiple hardware choices: training on multiple GPUs and multiple computing nodes.</p>}, number={4}, journal={Supercomputing Frontiers and Innovations}, author={Shaikhislamov, Denis and Sozykin, Andrey and Voevodin, Vadim}, year={2020}, month={Jan.}, pages={57–83} }