Abstract

This article is a ten-year retrospective of the rise of the accelerators since the authors coedited a 2008 IEEE MICRO special issue on Accelerator Architectures. It identifies the most prominent applications using the accelerators to date: high-performance computing, crypto currencies, and machine learning. For the two most popular types of accelerators, GPUs and FPGAs, the article gives a concise overview of the important trends in their compute throughput, memory bandwidth, and system interconnect. The article also articulates the importance of education for growing the adoption of accelerators. It concludes by identifying emerging types of accelerators and making a few predictions for the coming decade.

Original languageEnglish (US)
Article number8585394
Pages (from-to)56-62
Number of pages7
JournalIEEE Micro
Volume38
Issue number6
DOIs
StatePublished - Nov 1 2018

Fingerprint

Particle accelerators
Learning systems
Field programmable gate arrays (FPGA)
Education
Throughput
Bandwidth
Data storage equipment

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Accelerator architectures : A ten-year retrospective. / Hwu, Wen-Mei W; Patel, Sanjay Jeram.

In: IEEE Micro, Vol. 38, No. 6, 8585394, 01.11.2018, p. 56-62.

Research output: Contribution to journalArticle

@article{36f96bc0665b42029dff342352b88ae0,
title = "Accelerator architectures: A ten-year retrospective",
abstract = "This article is a ten-year retrospective of the rise of the accelerators since the authors coedited a 2008 IEEE MICRO special issue on Accelerator Architectures. It identifies the most prominent applications using the accelerators to date: high-performance computing, crypto currencies, and machine learning. For the two most popular types of accelerators, GPUs and FPGAs, the article gives a concise overview of the important trends in their compute throughput, memory bandwidth, and system interconnect. The article also articulates the importance of education for growing the adoption of accelerators. It concludes by identifying emerging types of accelerators and making a few predictions for the coming decade.",
author = "Hwu, {Wen-Mei W} and Patel, {Sanjay Jeram}",
year = "2018",
month = "11",
day = "1",
doi = "10.1109/MM.2018.2877839",
language = "English (US)",
volume = "38",
pages = "56--62",
journal = "IEEE Micro",
issn = "0272-1732",
publisher = "IEEE Computer Society",
number = "6",

}

TY - JOUR

T1 - Accelerator architectures

T2 - A ten-year retrospective

AU - Hwu, Wen-Mei W

AU - Patel, Sanjay Jeram

PY - 2018/11/1

Y1 - 2018/11/1

N2 - This article is a ten-year retrospective of the rise of the accelerators since the authors coedited a 2008 IEEE MICRO special issue on Accelerator Architectures. It identifies the most prominent applications using the accelerators to date: high-performance computing, crypto currencies, and machine learning. For the two most popular types of accelerators, GPUs and FPGAs, the article gives a concise overview of the important trends in their compute throughput, memory bandwidth, and system interconnect. The article also articulates the importance of education for growing the adoption of accelerators. It concludes by identifying emerging types of accelerators and making a few predictions for the coming decade.

AB - This article is a ten-year retrospective of the rise of the accelerators since the authors coedited a 2008 IEEE MICRO special issue on Accelerator Architectures. It identifies the most prominent applications using the accelerators to date: high-performance computing, crypto currencies, and machine learning. For the two most popular types of accelerators, GPUs and FPGAs, the article gives a concise overview of the important trends in their compute throughput, memory bandwidth, and system interconnect. The article also articulates the importance of education for growing the adoption of accelerators. It concludes by identifying emerging types of accelerators and making a few predictions for the coming decade.

UR - http://www.scopus.com/inward/record.url?scp=85059799396&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059799396&partnerID=8YFLogxK

U2 - 10.1109/MM.2018.2877839

DO - 10.1109/MM.2018.2877839

M3 - Article

VL - 38

SP - 56

EP - 62

JO - IEEE Micro

JF - IEEE Micro

SN - 0272-1732

IS - 6

M1 - 8585394

ER -