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 journalArticle

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 languageEnglish (US)
Article number8768342
Pages (from-to)64-72
Number of pages9
JournalIEEE Micro
Volume39
Issue number5
DOIs
StatePublished - Sep 1 2019

Fingerprint

High level languages
Learning algorithms
Particle accelerators
Energy efficiency
Learning systems
Signal processing

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

An Energy-Efficient Programmable Mixed-Signal Accelerator for Machine Learning Algorithms. / Kang, Mingu; Srivastava, Prakalp; Adve, Vikram; Kim, Nam Sung; Shanbhag, Naresh R.

In: IEEE Micro, Vol. 39, No. 5, 8768342, 01.09.2019, p. 64-72.

Research output: Contribution to journalArticle

Kang, Mingu ; Srivastava, Prakalp ; Adve, Vikram ; Kim, Nam Sung ; Shanbhag, Naresh R. / An Energy-Efficient Programmable Mixed-Signal Accelerator for Machine Learning Algorithms. In: IEEE Micro. 2019 ; Vol. 39, No. 5. pp. 64-72.
@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.}",
year = "2019",
month = "9",
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

VL - 39

SP - 64

EP - 72

JO - IEEE Micro

JF - IEEE Micro

SN - 0272-1732

IS - 5

M1 - 8768342

ER -