An Energy-Efficient Programmable Mixed-Signal Accelerator for Machine Learning Algorithms

Mingu Kang; Prakalp Srivastava; Vikram Adve; Nam Sung Kim; Naresh R. Shanbhag

doi:10.1109/MM.2019.2929502

An Energy-Efficient Programmable Mixed-Signal Accelerator for Machine Learning Algorithms

Mingu Kang, Prakalp Srivastava, Vikram Adve, Nam Sung Kim, Naresh R. Shanbhag

Research output: Contribution to journal › Article › peer-review

Abstract

We propose PROMISE, the first end-to-end design of a PROgrammable MIxed-Signal accElerator from Instruction Set Architecture to high-level language compiler for acceleration of diverse machine learning algorithms by exploiting the advantage of the superior energy efficiency from analog/mixed-signal processing.

Original language	English (US)
Article number	8768342
Pages (from-to)	64-72
Number of pages	9
Journal	IEEE Micro
Volume	39
Issue number	5
DOIs	https://doi.org/10.1109/MM.2019.2929502
State	Published - Sep 1 2019

ASJC Scopus subject areas

Software
Hardware and Architecture
Electrical and Electronic Engineering

Online availability

10.1109/MM.2019.2929502

Library availability

Discover UIUC Full Text

Cite this

@article{ced489058eae466a9a1788506e2a3a4e,

title = "An Energy-Efficient Programmable Mixed-Signal Accelerator for Machine Learning Algorithms",

abstract = "We propose PROMISE, the first end-to-end design of a PROgrammable MIxed-Signal accElerator from Instruction Set Architecture to high-level language compiler for acceleration of diverse machine learning algorithms by exploiting the advantage of the superior energy efficiency from analog/mixed-signal processing.",

author = "Mingu Kang and Prakalp Srivastava and Vikram Adve and Kim, {Nam Sung} and Shanbhag, {Naresh R.}",

note = "Publisher Copyright: {\textcopyright} 1981-2012 IEEE.",

year = "2019",

month = sep,

day = "1",

doi = "10.1109/MM.2019.2929502",

language = "English (US)",

volume = "39",

pages = "64--72",

journal = "IEEE Micro",

issn = "0272-1732",

publisher = "IEEE Computer Society",

number = "5",

}

TY - JOUR

T1 - An Energy-Efficient Programmable Mixed-Signal Accelerator for Machine Learning Algorithms

AU - Kang, Mingu

AU - Srivastava, Prakalp

AU - Adve, Vikram

AU - Kim, Nam Sung

AU - Shanbhag, Naresh R.

PY - 2019/9/1

Y1 - 2019/9/1

N2 - We propose PROMISE, the first end-to-end design of a PROgrammable MIxed-Signal accElerator from Instruction Set Architecture to high-level language compiler for acceleration of diverse machine learning algorithms by exploiting the advantage of the superior energy efficiency from analog/mixed-signal processing.

AB - We propose PROMISE, the first end-to-end design of a PROgrammable MIxed-Signal accElerator from Instruction Set Architecture to high-level language compiler for acceleration of diverse machine learning algorithms by exploiting the advantage of the superior energy efficiency from analog/mixed-signal processing.

UR - http://www.scopus.com/inward/record.url?scp=85069905254&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069905254&partnerID=8YFLogxK

U2 - 10.1109/MM.2019.2929502

DO - 10.1109/MM.2019.2929502

M3 - Article

AN - SCOPUS:85069905254

SN - 0272-1732

VL - 39

SP - 64

EP - 72

JO - IEEE Micro

JF - IEEE Micro

IS - 5

M1 - 8768342

ER -

An Energy-Efficient Programmable Mixed-Signal Accelerator for Machine Learning Algorithms

Abstract

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this