UCNN: Exploiting computational reuse in deep neural networks via weight repetition

Kartik Hegde, Jiyong Yu, Rohit Agrawal, Mengjia Yan, Michael Pellauer, Christopher W. Fletcher

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Convolutional Neural Networks (CNNs) have begun to permeate all corners of electronic society (from voice recognition to scene generation) due to their high accuracy and Machine efficiency per operation. At their core, CNN computations are made up of multi-dimensional dot products between weight and input vectors. This paper studies how weight repetition—when the same weight occurs multiple times in or across weight vectors—can be exploited to save energy and improve performance during CNN inference. This generalizes a popular line of work to improve efficiency from CNN weight sparsity, as reducing computation due to repeated zero weights is a special case of reducing computation due to repeated weights. To exploit weight repetition, this paper proposes a new CNN accelerator called the Unique Weight CNN Accelerator (UCNN). UCNN uses weight repetition to reuse CNN sub-computations (e.g., dot products) and to reduce CNN model size when stored in off-chip DRAM—both of which save energy. UCNN further improves performance by exploiting sparsity in weights. We evaluate UCNN with an accelerator-level cycle and energy model and with an RTL implementation of the UCNN processing element. On three contemporary CNNs, UCNN improves throughput-normalized energy consumption by 1.2× ∼ 4×, relative to a similarly provisioned baseline accelerator that uses Eyeriss-style sparsity optimizations. At the same time, the UCNN processing element adds only 17-24% area overhead relative to the same baseline.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 ACM/IEEE 45th Annual International Symposium on Computer Architecture, ISCA 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages674-687
Number of pages14
ISBN (Electronic)9781538659847
DOIs
StatePublished - Jul 19 2018
Event45th ACM/IEEE Annual International Symposium on Computer Architecture, ISCA 2018 - Los Angeles, United States
Duration: Jun 2 2018Jun 6 2018

Publication series

NameProceedings - International Symposium on Computer Architecture
ISSN (Print)1063-6897

Other

Other45th ACM/IEEE Annual International Symposium on Computer Architecture, ISCA 2018
Country/TerritoryUnited States
CityLos Angeles
Period6/2/186/6/18

ASJC Scopus subject areas

  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'UCNN: Exploiting computational reuse in deep neural networks via weight repetition'. Together they form a unique fingerprint.

Cite this