Dynamic Stripes: Exploiting the Dynamic Precision Requirements of Activation Values in Neural Networks

06/01/2017

∙

by   Alberto Delmas, et al.

∙

0

∙

share

Stripes is a Deep Neural Network (DNN) accelerator that uses bit-serial computation to offer performance that is proportional to the fixed-point precision of the activation values. The fixed-point precisions are determined a priori using profiling and are selected at a per layer granularity. This paper presents Dynamic Stripes, an extension to Stripes that detects precision variance at runtime and at a finer granularity. This extra level of precision reduction increases performance by 41