STAR: A Mixed Analog Stochastic In-DRAM Convolutional Neural Network Accelerator

Salma Afifi; Ishan Thakkar; Sudeep Pasricha

doi:10.1109/MDAT.2024.3447580

STAR: A Mixed Analog Stochastic In-DRAM Convolutional Neural Network Accelerator

Salma Afifi
, Ishan Thakkar
, Sudeep Pasricha

Producción científica: Article › revisión exhaustiva

1 Cita (Scopus)

Resumen

Editor's notes: This article addresses the optimization of data movement in accelerating machine learning workloads, one of the most critical issues of state-ofthe- art computing platforms. It presents a novel in-DRAM accelerator for convolutional neural networks using mixed analog-stochastic optimizations and shows significant energy-efficiency improvements. - Umit Ogras, University of Wisconsin, USA.

Idioma original	English
Páginas (desde-hasta)	47-55
Número de páginas	9
Publicación	IEEE Design and Test
Volumen	42
N.º	1
DOI	https://doi.org/10.1109/MDAT.2024.3447580
Estado	Published - 2025

Nota bibliográfica

Publisher Copyright:
© 2013 IEEE.

ODS de las Naciones Unidas

Este resultado contribuye a los siguientes Objetivos de Desarrollo Sostenible

Affordable and clean energy

ASJC Scopus subject areas

Software
Hardware and Architecture
Electrical and Electronic Engineering

Acceder al documento

10.1109/MDAT.2024.3447580

Otros archivos y enlaces

Citar esto

@article{fc4c605caa344ccabb8989a2008c994e,

title = "STAR: A Mixed Analog Stochastic In-DRAM Convolutional Neural Network Accelerator",

abstract = "Editor's notes: This article addresses the optimization of data movement in accelerating machine learning workloads, one of the most critical issues of state-ofthe- art computing platforms. It presents a novel in-DRAM accelerator for convolutional neural networks using mixed analog-stochastic optimizations and shows significant energy-efficiency improvements. - Umit Ogras, University of Wisconsin, USA.",

keywords = "convolution neural networks, in-DRAM processing, stochastic computing",

author = "Salma Afifi and Ishan Thakkar and Sudeep Pasricha",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2025",

doi = "10.1109/MDAT.2024.3447580",

language = "English",

volume = "42",

pages = "47--55",

number = "1",

}

TY - JOUR

T1 - STAR

T2 - A Mixed Analog Stochastic In-DRAM Convolutional Neural Network Accelerator

AU - Afifi, Salma

AU - Thakkar, Ishan

AU - Pasricha, Sudeep

PY - 2025

Y1 - 2025

N2 - Editor's notes: This article addresses the optimization of data movement in accelerating machine learning workloads, one of the most critical issues of state-ofthe- art computing platforms. It presents a novel in-DRAM accelerator for convolutional neural networks using mixed analog-stochastic optimizations and shows significant energy-efficiency improvements. - Umit Ogras, University of Wisconsin, USA.

AB - Editor's notes: This article addresses the optimization of data movement in accelerating machine learning workloads, one of the most critical issues of state-ofthe- art computing platforms. It presents a novel in-DRAM accelerator for convolutional neural networks using mixed analog-stochastic optimizations and shows significant energy-efficiency improvements. - Umit Ogras, University of Wisconsin, USA.

KW - convolution neural networks

KW - in-DRAM processing

KW - stochastic computing

UR - https://www.scopus.com/pages/publications/85202722158

UR - https://www.scopus.com/pages/publications/85202722158#tab=citedBy

U2 - 10.1109/MDAT.2024.3447580

DO - 10.1109/MDAT.2024.3447580

M3 - Article

AN - SCOPUS:85202722158

SN - 2168-2356

VL - 42

SP - 47

EP - 55

JO - IEEE Design and Test

JF - IEEE Design and Test

IS - 1

ER -

STAR: A Mixed Analog Stochastic In-DRAM Convolutional Neural Network Accelerator

Resumen

Nota bibliográfica

ODS de las Naciones Unidas

ASJC Scopus subject areas

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto