Rebooting the data access hierarchy of computing systems

Wen-Mei W Hwu, Izzat El Hajj, Simon Garcia De Gonzalo, Carl Pearson, Nam Sung Kim, Deming Chen, Jinjun Xiong, Zehra Sura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We have been experiencing two very important movements in computing. On the one hand, a tremendous amount of resource has been invested into innovative applications such as first-principle-based methods, deep learning and cognitive computing. On the other hand, the industry has been taking a technological path where application performance and energy efficiency vary by more than two orders of magnitude depending on their parallelism, heterogeneity, and locality. We envision that a “perfect storm” is coming because of the interaction between these two movements. Many of these new and high-valued applications need to touch a very large amount of data with little data reuse and data movement has become the dominating factor for both power and performance of these applications. It will be critical to match the compute throughput to the data access bandwidth and to locate the compute near data. Much has been and continuously needs to be learned about algorithms, languages, compilers and hardware architecture in this movement. What are the killer applications that may become the new driver for future technology development? How hard is it to program existing systems to address the data movement issues today? How will we program these systems in the future? How will innovations in memory devices present further opportunities and challenges in designing new systems? What is the impact on long-term software engineering cost of applications? In this paper, we present some lessons learned as we design the IBM-Illinois C3SR (Center for Cognitive Computing Systems Research) Erudite system inside this perfect storm.

Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-4
Number of pages4
ISBN (Electronic)9781538615539
DOIs
StatePublished - Nov 28 2017
Event2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Washington, United States
Duration: Nov 8 2017Nov 9 2017

Publication series

Name2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings
Volume2017-January

Other

Other2017 IEEE International Conference on Rebooting Computing, ICRC 2017
CountryUnited States
CityWashington
Period11/8/1711/9/17

Fingerprint

hierarchies
compilers
touch
reuse
lessons learned
learning
Energy efficiency
Software engineering
resources
hardware
Innovation
industries
Throughput
bandwidth
costs
Hardware
Bandwidth
Data storage equipment
Costs
Industry

Keywords

  • Big data
  • Heterogeneous computing
  • Low-complexity algorithms
  • Memory bandwidth
  • Throughput oriented computing

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Statistical and Nonlinear Physics
  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Hardware and Architecture
  • Software

Cite this

Hwu, W-M. W., Hajj, I. E., De Gonzalo, S. G., Pearson, C., Kim, N. S., Chen, D., ... Sura, Z. (2017). Rebooting the data access hierarchy of computing systems. In 2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings (pp. 1-4). (2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings; Vol. 2017-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRC.2017.8123667

Rebooting the data access hierarchy of computing systems. / Hwu, Wen-Mei W; Hajj, Izzat El; De Gonzalo, Simon Garcia; Pearson, Carl; Kim, Nam Sung; Chen, Deming; Xiong, Jinjun; Sura, Zehra.

2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1-4 (2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings; Vol. 2017-January).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hwu, W-MW, Hajj, IE, De Gonzalo, SG, Pearson, C, Kim, NS, Chen, D, Xiong, J & Sura, Z 2017, Rebooting the data access hierarchy of computing systems. in 2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings. 2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings, vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-4, 2017 IEEE International Conference on Rebooting Computing, ICRC 2017, Washington, United States, 11/8/17. https://doi.org/10.1109/ICRC.2017.8123667
Hwu W-MW, Hajj IE, De Gonzalo SG, Pearson C, Kim NS, Chen D et al. Rebooting the data access hierarchy of computing systems. In 2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1-4. (2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings). https://doi.org/10.1109/ICRC.2017.8123667
Hwu, Wen-Mei W ; Hajj, Izzat El ; De Gonzalo, Simon Garcia ; Pearson, Carl ; Kim, Nam Sung ; Chen, Deming ; Xiong, Jinjun ; Sura, Zehra. / Rebooting the data access hierarchy of computing systems. 2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1-4 (2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings).
@inproceedings{b155d2d454b5482782739dc6fa1aaf57,
title = "Rebooting the data access hierarchy of computing systems",
abstract = "We have been experiencing two very important movements in computing. On the one hand, a tremendous amount of resource has been invested into innovative applications such as first-principle-based methods, deep learning and cognitive computing. On the other hand, the industry has been taking a technological path where application performance and energy efficiency vary by more than two orders of magnitude depending on their parallelism, heterogeneity, and locality. We envision that a “perfect storm” is coming because of the interaction between these two movements. Many of these new and high-valued applications need to touch a very large amount of data with little data reuse and data movement has become the dominating factor for both power and performance of these applications. It will be critical to match the compute throughput to the data access bandwidth and to locate the compute near data. Much has been and continuously needs to be learned about algorithms, languages, compilers and hardware architecture in this movement. What are the killer applications that may become the new driver for future technology development? How hard is it to program existing systems to address the data movement issues today? How will we program these systems in the future? How will innovations in memory devices present further opportunities and challenges in designing new systems? What is the impact on long-term software engineering cost of applications? In this paper, we present some lessons learned as we design the IBM-Illinois C3SR (Center for Cognitive Computing Systems Research) Erudite system inside this perfect storm.",
keywords = "Big data, Heterogeneous computing, Low-complexity algorithms, Memory bandwidth, Throughput oriented computing",
author = "Hwu, {Wen-Mei W} and Hajj, {Izzat El} and {De Gonzalo}, {Simon Garcia} and Carl Pearson and Kim, {Nam Sung} and Deming Chen and Jinjun Xiong and Zehra Sura",
year = "2017",
month = "11",
day = "28",
doi = "10.1109/ICRC.2017.8123667",
language = "English (US)",
series = "2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1--4",
booktitle = "2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings",
address = "United States",

}

TY - GEN

T1 - Rebooting the data access hierarchy of computing systems

AU - Hwu, Wen-Mei W

AU - Hajj, Izzat El

AU - De Gonzalo, Simon Garcia

AU - Pearson, Carl

AU - Kim, Nam Sung

AU - Chen, Deming

AU - Xiong, Jinjun

AU - Sura, Zehra

PY - 2017/11/28

Y1 - 2017/11/28

N2 - We have been experiencing two very important movements in computing. On the one hand, a tremendous amount of resource has been invested into innovative applications such as first-principle-based methods, deep learning and cognitive computing. On the other hand, the industry has been taking a technological path where application performance and energy efficiency vary by more than two orders of magnitude depending on their parallelism, heterogeneity, and locality. We envision that a “perfect storm” is coming because of the interaction between these two movements. Many of these new and high-valued applications need to touch a very large amount of data with little data reuse and data movement has become the dominating factor for both power and performance of these applications. It will be critical to match the compute throughput to the data access bandwidth and to locate the compute near data. Much has been and continuously needs to be learned about algorithms, languages, compilers and hardware architecture in this movement. What are the killer applications that may become the new driver for future technology development? How hard is it to program existing systems to address the data movement issues today? How will we program these systems in the future? How will innovations in memory devices present further opportunities and challenges in designing new systems? What is the impact on long-term software engineering cost of applications? In this paper, we present some lessons learned as we design the IBM-Illinois C3SR (Center for Cognitive Computing Systems Research) Erudite system inside this perfect storm.

AB - We have been experiencing two very important movements in computing. On the one hand, a tremendous amount of resource has been invested into innovative applications such as first-principle-based methods, deep learning and cognitive computing. On the other hand, the industry has been taking a technological path where application performance and energy efficiency vary by more than two orders of magnitude depending on their parallelism, heterogeneity, and locality. We envision that a “perfect storm” is coming because of the interaction between these two movements. Many of these new and high-valued applications need to touch a very large amount of data with little data reuse and data movement has become the dominating factor for both power and performance of these applications. It will be critical to match the compute throughput to the data access bandwidth and to locate the compute near data. Much has been and continuously needs to be learned about algorithms, languages, compilers and hardware architecture in this movement. What are the killer applications that may become the new driver for future technology development? How hard is it to program existing systems to address the data movement issues today? How will we program these systems in the future? How will innovations in memory devices present further opportunities and challenges in designing new systems? What is the impact on long-term software engineering cost of applications? In this paper, we present some lessons learned as we design the IBM-Illinois C3SR (Center for Cognitive Computing Systems Research) Erudite system inside this perfect storm.

KW - Big data

KW - Heterogeneous computing

KW - Low-complexity algorithms

KW - Memory bandwidth

KW - Throughput oriented computing

UR - http://www.scopus.com/inward/record.url?scp=85043526679&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043526679&partnerID=8YFLogxK

U2 - 10.1109/ICRC.2017.8123667

DO - 10.1109/ICRC.2017.8123667

M3 - Conference contribution

AN - SCOPUS:85043526679

T3 - 2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings

SP - 1

EP - 4

BT - 2017 IEEE International Conference on Rebooting Computing, ICRC 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -