Skip to main content
USENIX
  • Conferences
  • Students
Sign in
  • HotPower '12 Home
  • Workshop Organizers
  • Registration Information
  • Workshop Program
  • Hotel & Travel Information
  • Sponsorship
  • Students
  • Help Promote
  • For Participants
  • Call for Papers
  • Past Workshops

twitter

Tweets by @usenix

usenix conference policies

  • Event Code of Conduct
  • Conference Network Policy
  • Statement on Environmental Responsibility Policy

You are here

Home » Reducing Data Movement Costs Using Energy-Efficient, Active Computation on SSD
Tweet

connect with us

http://twitter.com/usenix
https://www.facebook.com/events/324177104321350/

Reducing Data Movement Costs Using Energy-Efficient, Active Computation on SSD

Authors: 

Devesh Tiwari, North Carolina State University; Sudharshan S. Vazhkudai and Youngjae Kim, Oak Ridge National Laboratory; Xiaosong Ma, North Carolina State University and Oak Ridge National Laboratory; Simona Boboila and Peter J. Desnoyers, Northeastern University

Abstract: 

Modern scientific discovery often involves running complex application simulations on supercomputers, followed by a sequence of data analysis tasks on smaller clusters. This offline approach suffers from significant data movement costs such as redundant I/O, storage bandwidth bottleneck, and wasted CPU cycles, all of which contribute to increased energy consumption and delayed end-to- end performance. Technology projections for an exascale machine indicate that energy-efficiency will become the primary design metric. It is estimated that the energy cost of data movement will soon rival the cost of computation. Consequently, we can no longer ignore the data movement costs in data analysis.

To address these challenges, we advocate executing data analysis tasks on emerging storage devices, such as SSDs. Typically, in extreme-scale systems, SSDs serve only as a temporary storage system for the simulation output data. In our approach, Active Flash, we propose to conduct in-situ data analysis on the SSD controller without degrading the performance of the simulation job. By migrating analysis tasks closer to where the data resides, it helps reduce the data movement cost. We present detailed energy and performance models for both active flash and offline strategies, and study them using extreme-scale application simulations, commonly used data analytics kernels, and supercomputer system configurations. Our evaluation suggests that active flash is a promising approach to alleviate the storage bandwidth bottleneck, reduce the data movement cost, and improve the overall energy efficiency. 

Devesh Tiwari, North Carolina State University

Sudharshan S. Vazhkudai, Oak Ridge National Laboratory

Youngjae Kim, Oak Ridge National Laboratory

Xiaosong Ma, North Carolina State University and Oak Ridge National Laboratory

Simona Boboila, Northeastern University

Peter J. Desnoyers, Northeastern University

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX
@inproceedings {179448,
author = {Devesh Tiwari and Sudharshan S. Vazhkudai and Youngjae Kim and Xiaosong Ma and Simona Boboila and Peter J. Desnoyers},
title = {Reducing Data Movement Costs Using {Energy-Efficient}, Active Computation on {SSD}},
booktitle = {2012 Workshop on Power-Aware Computing and Systems (HotPower 12)},
year = {2012},
address = {Hollywood, CA},
url = {https://www.usenix.org/conference/hotpower12/workshop-program/presentation/Tiwari},
publisher = {USENIX Association},
month = oct,
}
Download
Tiwari PDF

Presentation Video

Presentation Audio

MP3 Download OGG Download

Download Audio

  • Log in or    Register to post comments

© USENIX

  • Privacy Policy
  • Contact Us