DESCNet: Developing Efficient Scratchpad Memories for Capsule Network Hardware

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F21%3APU138926" target="_blank" >RIV/00216305:26230/21:PU138926 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9222370" target="_blank" >https://ieeexplore.ieee.org/document/9222370</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TCAD.2020.3030610" target="_blank" >10.1109/TCAD.2020.3030610</a>

Jazyk výsledku

angličtina

Název v původním jazyce

DESCNet: Developing Efficient Scratchpad Memories for Capsule Network Hardware

Popis výsledku v původním jazyce

Deep Neural Networks (DNNs) have been established as the state-of-the-art method for advanced machine learning applications. Recently proposed by the Google Brain's team, the Capsule Networks (CapsNets) have improved the generalization ability, as compared to DNNs, due to their multi-dimensional capsules and preserving the spatial relationship between different objects. However, they pose significantly high computational and memory requirements, making their energy-efficient inference a challenging task. This paper provides, for the first time, an in-depth analysis to highlight the design- and run-time challenges for the (on-chip scratchpad) memories deployed in hardware accelerators executing fast CapsNets inference. To enable an efficient design, we propose an application-specific memory architecture, called DESCNet, which minimizes the off-chip memory accesses, while efficiently feeding the data to the hardware accelerator executing CapsNets inference. We analyze the corresponding on-chip memory requirement, and leverage it to propose a methodology for exploring different scratchpad memory designs and their energy/area trade-offs. Afterwards, an application-specific power-gating technique for the on-chip scratchpad memory is employed to further reduce its energy consumption, depending upon the mapped dataflow of the CapsNet and the utilization across different operations of its processing.  We integrated our DESCNet memory design, as well as another state-of-the-art memory design for comparison studies, with an open-source DNN accelerator executing Google's CapsNet model for the MNIST dataset. We also enhanced the design to execute the recent deep CapsNet model for the CIFAR10 dataset. Note: we use the same benchmarks and test conditions for which these CapsNets have been proposed and evaluated by their respective teams. The complete hardware is synthesized for a 32nm CMOS technology using the ASIC-design flow with Synopsys tools a

Název v anglickém jazyce

DESCNet: Developing Efficient Scratchpad Memories for Capsule Network Hardware

Popis výsledku anglicky

Deep Neural Networks (DNNs) have been established as the state-of-the-art method for advanced machine learning applications. Recently proposed by the Google Brain's team, the Capsule Networks (CapsNets) have improved the generalization ability, as compared to DNNs, due to their multi-dimensional capsules and preserving the spatial relationship between different objects. However, they pose significantly high computational and memory requirements, making their energy-efficient inference a challenging task. This paper provides, for the first time, an in-depth analysis to highlight the design- and run-time challenges for the (on-chip scratchpad) memories deployed in hardware accelerators executing fast CapsNets inference. To enable an efficient design, we propose an application-specific memory architecture, called DESCNet, which minimizes the off-chip memory accesses, while efficiently feeding the data to the hardware accelerator executing CapsNets inference. We analyze the corresponding on-chip memory requirement, and leverage it to propose a methodology for exploring different scratchpad memory designs and their energy/area trade-offs. Afterwards, an application-specific power-gating technique for the on-chip scratchpad memory is employed to further reduce its energy consumption, depending upon the mapped dataflow of the CapsNet and the utilization across different operations of its processing.  We integrated our DESCNet memory design, as well as another state-of-the-art memory design for comparison studies, with an open-source DNN accelerator executing Google's CapsNet model for the MNIST dataset. We also enhanced the design to execute the recent deep CapsNet model for the CIFAR10 dataset. Note: we use the same benchmarks and test conditions for which these CapsNets have been proposed and evaluated by their respective teams. The complete hardware is synthesized for a 32nm CMOS technology using the ASIC-design flow with Synopsys tools a

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA19-10137S" target="_blank" >GA19-10137S: Navrhování a využívání knihoven aproximativních obvodů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS

ISSN

0278-0070

e-ISSN

1937-4151

Svazek periodika

40

Číslo periodika v rámci svazku

9

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

14

Strana od-do

1768-1781

Kód UT WoS článku

000686757700007

EID výsledku v databázi Scopus

2-s2.0-85092935204