Computer ScienceEngineering

Yu-hsin Chen, T. Krishna, J. Emer, V. Sze

2016.2.1IEEE JOURNAL OF SOLID-STATE CIRCUITS

DOI: 10.1109/jssc.2016.2616357

tlooto Summary

Eyeriss is an accelerator for state-of-the-art deep convolutional neural networks (CNNs) that optimizes for the energy efficiency of the entire system, including the accelerator chip and off-chip DRAM, for various CNN shapes by reconfiguring the architecture.

Abstract

Abstract is not available.

Citation format

CHEN, Yu-hsin, et al. Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE JOURNAL OF SOLID-STATE CIRCUITS, 2016, 52: 127–138.