HC31-S4: ML Training

Session 4, Hot Chips 31 (2019), Monday, August 19, 2019. A Scalable Unified Architecture for Neural Network Computing from Nano-level to High Performance Computing Liao Heng, Huawei Deep Learning Training at Scale — Spring Crest Deep Learning Accelerator Andrew Yang, Nitin Garegrat, Connie Miao & Karthik Vaidyanathan, Intel Wafer Scale Deep Learning Sean Lie, Cerebras Habana Labs Approach to Scaling AI Training Eitan Medina, Habana