Supercomputing speeds up deep learning training

(University of Texas at Austin, Texas Advanced Computing Center) Researchers from UC Berkeley, UC Davis and TACC used Stampede2 to complete a 100-epoch ImageNet deep neural network training in 11 minutes -- the fastest time recorded to date. Using 1600 Skylake processors they also bested Facebook's prior results by finishing a 90-epoch ImageNet training with ResNet-50 in 32 minutes. Given TACC's large user base and huge capacity, this capability will have a major impact across all fields of scie