Newsletter‎ > ‎

Newsletter - Volume 2, Issue 4 - October 2013

Monthly bulletin of the IEEE Computer Society Special Technical Community on Sustainable Computing

Providing quick access to timely information on sustainable computing.

Sponsored by:




Community Highlights: Luiz André Barroso

In this feature we ask a prominent researcher in the field of sustainable computing to share their journey and lessons along the way with the broader community. In this issue we have the privilege to sit down with Dr. Luiz André Barroso, perhaps most known for his research on large-scale systems and his highly influential work on energy proportional computing.



    Luiz André Barroso
    Google Fellow, Google Inc.
 
    Education:
    University of Southern California
    Pontifícia Universidade Católica, Rio de Janeiro





Currently working on:


Building very very very large computers that run useful Internet services.

Favorite memory as a student/advisor/researcher:

Two phone calls were big: getting a phone call from Norm Jouppi in my grad student office on a Saturday afternoon in 1995 asking me if I would like to interview for a research position at DEC WRL; and calling my friend Jeff Dean in 2001 asking him to convince me to accept the offer to join Google (his winning argument was "have you considered our crème brûlées?"). As a researcher, being asked to write the Foreword to the 5th edition of Hennessy & Patterson's book over a year ago still seems unreal today.

Could you share a research contribution from your research, and explain why this is something that you are
particularly proud?


Our 2007 article on energy proportional computing has probably had the most impact. It's a really obvious concept that perhaps Urs and I were the first to articulate clearly enough in a wide distribution venue (IEEE Computer). I believe that if I have any talent that is above average it is my keen appreciation for the obvious. I am also proud of my first research publication in a top tier conference, a paper at ISCA 1993 on cache-coherent ring-based interconnects.

Explain one thing that makes your work exciting for you?

Brilliant colleagues. In that category I may be one of the luckiest guys in our field. I've had the chance to work with people like Kourosh Gharachorloo, Andreas Nowatzyk, Susan Eggers, Jeff Dean, Sanjay Ghemawat, Mike Burrows, Dick Sites, Urs Hölzle, Alan Eustace, Amin Vahdat, Eric Brewer, Sean Quinlan, David Presotto, and many others at Google as talented but perhaps less known (yet). I've also had an insanely great list of interns over the years, including Partha Ranganathan (HP Fellow), Rob Stets and Gautham Thambidorai (both Distinguished Engineers at Google), Ed Buginion (co-founder of VMware), Jack Lo (Sr. Director at VMware), Alex Ramirez (UPC Professor) and recently David Meisner (just graduated and joined Facebook).

What do you think is (are) the important problem(s) to be solved in the next 10 years within sustainable
computing?


I think the world needs more useful, intelligent computing. The greatest potential for computing to contribute to a sustainable planet is more than simply making computing more energy efficient. Although those improvements are absolutely necessary, their impact is dwarfed by the smart application of computing technology in increasing efficiencies in other industries (transportation, manufacturing, etc.). We forget how much computers already make our daily lives more efficient. For example, in 2009 the computer that controlled traffic lights in Montgomery  County, Maryland went down. Even though all traffic lights were still working, the system lost its ability to make subtle adjustments to the timing of multiple lights and to adapt to the flow of commute patterns. That little computer was the difference between normal busy traffic and a 40 hour long national news story about traffic chaos.

What courses and skills are most important for students wanting to work in this area?

Not sure what to say regarding academic courses. A good skill to develop early on is the ability to pick good problems. Developing that kind of judgment is the single most important ability bounding how much impact you can have. Pick a mediocre problem and you are bound to have mediocre impact, regardless of the brilliance of your solution. Pick a big important problem, solve 10% of it, and you have something to be proud of.


STC Updates

 
By Danilo Ardagna, Politecnico di Milano





Membership: 528

Officers reports from July 31, 2013 to October 31, 2013

Report from Secretary/Treasurer (Danilo Ardagna):

  • Collected officers' activity reports and prepared monthly STC report

Report from Conferences Chair (Diwakar Krishnamurthy):

  • Solicited collaborations from Middleware 2013, MICRO 2013, CloudCom 2013, and HiPC 2013 conference organizers.
  • Continued to update and expand list of conferences related to the STC

Report from Academic Chair (Niklas Carlsson):

  • Working with the industry chair on the next community highlight feature(s)
  • Report from Membership Chair and vice-Chair (Sergey Blagodurov, Matthew Forshaw):
  • Counted the number of members every week for the past month and updated the STC-SC dashboard of our website. As of October 27th 2013, we have 528 members
  • Gradually sent invitations to the potential STC-SC members and continues to work on the new invitation list

Report from Communications Chair (Abhishek Chandra):

  • Working with the communications vice-chair to compile the list of upcoming events and deadlines for inclusion in the newsletter

Report from Industry Chair (Canturk Isci):

  • Finalizing the next community highlights feature with the Academic Chair

Report from Information Officers (Danilo Ardagna, David Carrera, Fan Dongrui, Guillaume Jourjon):

  • Contributed material for newsletter and blogs

Report from the Newsletter Editor (Christopher Stewart):

  • Put out October newsletter
  • Devising more sustainable model for article contributions


Upcoming Events

By Abhishek Chandra, University of Minnesota

Conference, Workshop & Symposium Call For Papers





Short Name Main Topic Location Dates Abstracts Due Papers Due Notification URL
Smart Greens

Smart Grids and Green IT systems

Barcelona, Spain

Apr. 3-4, 2014

Oct. 3, 2013
Jan. 29, 2014

IPDPS
Parallel and Distributed Processing

Phoenix, Arizona

May 19-23,
2014

Oct. 18, 2013
Dec. 09, 2013

ICDCS

Distributed Computing

Madrid, Spain

June/July 2014 Nov

Nov. 15, 2013
Feb. 24, 2014

Sigmetrics

Performance Modeling and Simulation

Austin, Texas

June 2014

Dec. 2, 2013
Feb. 17, 2014

 eEnergy Future Energy Systems
Cambridge, UK
June 2014  Jan 15, 2014
 Mar. 21, 2014
 

Journal and Special Issue Call For Papers






Journal



Papers Due Notification URL
Sustainable Computing





























Conference, Workshop & Symposium Call for Participation





Short Name Main Topic Location Dates


URL
HotPower Power management of computer systems
Farmington, PA Nov. 3, 2013




SOSP Operating Systems
Farmington, PA
Nov. 3-6, 2013