papers AI Learner
The Github is limit! Click to go to the new site.

A Simple Method to Reduce Off-chip Memory Accesses on Convolutional Neural Networks

2019-01-28
Doyun Kim, Kyoung-Young Kim, Sangsoo Ko, Sanghyuck Ha

Abstract

For convolutional neural networks, a simple algorithm to reduce off-chip memory accesses is proposed by maximally utilizing on-chip memory in a neural process unit. Especially, the algorithm provides an effective way to process a module which consists of multiple branches and a merge layer. For Inception-V3 on Samsung’s NPU in Exynos, our evaluation shows that the proposed algorithm makes off-chip memory accesses reduced by 1/50, and accordingly achieves 97.59 % reduction in the amount of feature-map data to be transferred from/to off-chip memory.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.09614

PDF

http://arxiv.org/pdf/1901.09614


Similar Posts

Comments