English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The ever-increasing computation complexity of fastgrowing Deep NeuralNetworks (DNNs) has requested new computing paradigms to overcome the memorywall in conventional Von Neumann computing architectures. The emergingComputing-In-Memory (CIM) architecture has been a promising candidate toaccelerate neural network computing. However, data movement between CIM arraysmay still dominate the total power consumption in conventional designs. Thispaper proposes a flexible CIM processor architecture named Domino and"Computing-On-the-Move" (COM) dataflow, to enable stream computing and localdata access to significantly reduce data movement energy. Meanwhile, Dominoemploys customized distributed instruction scheduling within Network-on-Chip(NoC) to implement inter-memory computing and attain mapping flexibility. Theevaluation with prevailing DNN models shows that Domino achieves1.77-to-2.37$\times$ power efficiency over several state-of-the-art CIMaccelerators and improves the throughput by 1.28-to-13.16$\times$.

A Customized NoC Architecture to Enable Highly Localized Computing-On-the-Move DNN Dataflow