no code implementations • 3 May 2020 • Weitao Li, Pengfei Xu, Yang Zhao, Haitong Li, Yuan Xie, Yingyan Lin
Resistive-random-access-memory (ReRAM) based processing-in-memory (R$^2$PIM) accelerators show promise in bridging the gap between Internet of Thing devices' constrained resources and Convolutional/Deep Neural Networks' (CNNs/DNNs') prohibitive energy cost.
no code implementations • 23 Nov 2018 • Abbas Rahimi, Tony F. Wu, Haitong Li, Jan M. Rabaey, H. -S. Philip Wong, Max M. Shulaker, Subhasish Mitra
By exploiting the unique properties of the underlying nanotechnologies, we show that HD computing, when implemented with monolithic 3D integration, can be up to 420X more energy-efficient while using 25X less area compared to traditional silicon CMOS implementations.