About
Registration
Conference
Technical Program
Exhibits
News & Press
Travel
Advisory Committee
Contact Information
History
SC07 Committees
Sponsoring Societies
Steering Committee
Overview
Overview
Schedule
Last-Minute Schedule Updates and Changes
My Itinerary
Keynote
Broader Engagement
Cluster Challenge
Education
Important Dates
SCinet
Student Volunteers
SC Fellowship
Overview
Awards
BOFs
Challenges
Disruptive Technologies
Doctoral Showcase
Keynote & Invited Speakers
Masterworks
Panels
Papers
Posters
Tutorials
Workshops
Overview
Exhibitor Forum
Exhibitor Information
Floor Plan
Industry Exhibits
Research Exhibits
Exhibitor List
Overview
Press Releases
Newsletters
For Media Professionals
Overview
Conference Hotels
About Reno
Maps and Directions
Conference Shuttle Schedule
SCHEDULE: NOV 10-16, 2007
Warning: It appears you do not have Javascript enabled.
If so, you will have trouble creating and viewing your itinerary information.
A Massively Parallel Simulator for Nano-Electronics
Session:
Posters Reception
Event Type:
Poster
Time:
5:15pm - 7:00pm
Session Chair
:
Tamara K Grimmett
Author(s)
:
Hansang Bae, Steve Clark, Gerhard Klimeck, Sunhee Lee, Maxim Naumov, Faisal Saied
Location:
Ballroom Lobby
Abstract:
Simulating realistic nano-electronic devices using an atomistic, quantum mechanical model leads to very large scale problems for the electronic structure. NEMO 3-D is scalable code that can model devices such as quantum dots. We present new performance analyses that demonstrate that our electronic structure code scales effectively on the Cray XT3, the BlueGene, and an Intel Woodcrest cluster.
We are especially interested in exploiting petascale compute power for nano-electronic applications. Through an in-depth performance analysis of NEMO3d on the most advanced architectures, we show that our code achieves a very favourable balance between computation and communication for a relatively small number of atoms per core, in the weak scaling context.
Our results, including some up to 8192 processors, show that NEMO 3-D is very well-suited for scaling up significantly and computations with 50 to 100 millions of atoms could be routinely performed on a petascale machine.
Chair/Author Details:
Tamara K Grimmett (Chair)
INL
Hansang Bae
Purdue University
Steve Clark
Purdue University
Gerhard Klimeck
Purdue University
Sunhee Lee
Purdue University
Maxim Naumov
Purdue University
Faisal Saied
Purdue University
Home
|
About
|
Contact Us
|
Registration