tlb
Volume 5, Number 19 -- May 13, 2008

NASA Taps SGI and Intel for Pleiades 10 Petaflops Super

Published: May 13, 2008

by Timothy Prickett Morgan

Forget breaking the petaflops barrier, which by the way no supercomputer cluster has done officially yet but probably will on the next iteration in the fall of the Top 500 semi-annual listing of global supers. Supercomputer makers are setting their sights on 10 petaflops and beyond already. Last week, NASA's Ames Research Center announced that it has picked long-time partner Silicon Graphics and chip maker Intel to build its next generation supercomputer, called Pleiades, based on Xeon processors.

The fact that NASA Ames has chosen SGI to help it build the next big supercomputer is no surprise. The NASA facility has been a stalwart customer of SGI for many years and has helped SGI scale up the shared global memory that is at the heart of the company's Altix brand of Linux-Itanium servers. The NASA facility is where the Columbia supercomputer runs, formerly the fastest machine in the world. Today, the Columbia machine is comprised of 10,160 1.5 GHz "Madison" Itanium processors and has a peak rating of 61 teraflops on the Linpack Fortran benchmark test. Columbia was installed to get NASA back on track with the Space Shuttle program after Columbia exploded and has also been used to run various weather and cosmology models.

The Pleiades machine, named after the famous star cluster in Taurus that goes by many names (Suburu in Japanese, for instance), is being made out of clusters of SGI's most recent Altix ICE Xeon-based blade servers rather than on the Itanium-based Altix servers. The initial Pleiades machine will be based on Intel's current "Harpertown" quad-core Xeon processors, and will have over 40 racks linked together in a parallel cluster (not using NUMA and global shared memory). Each rack will have 512 processor cores (that's 128 sockets and, presuming that these are two-socket blades, 64 blades) and a total of 512 GB of main memory (presumably 8 GB of memory per blade). That is a total of 20,480 Harpertown cores, 20 TB of main memory, and 450 TB of InfiniteStorage disk arrays linked to the servers through an InfiniBand fabric, which also links the blades to each other in the cluster. The initial Pleiades configuration will be rated at 245 teraflops of peak performance, according to SGI. According to Intel, the Pleiades machine will be upgraded to future "Nehalem" Xeons, which will be based on the QuickPath Interconnect scheme and will have integrated memory controllers on the chip (resulting in higher bandwidth and greater energy efficiency per teraflops than current Xeons can deliver). After that, to get to the 10 petraflops level, Intel and SGI will work together to create a machine based on a future Xeon processors.

It is important to note that the quad-core "Tukwila" Itanium is not being used in the system, despite its very good number-crunching performance and its code compatibility with the Columbia supercomputer. Intel is also not pitching its six-core "Dunnington" Xeon chips in the machines, but jumping from Harpertown straight to Nehalem, which will deliver a factor of 16 times more performance, or 3.92 petaflops. Intel has said publicly that the Nehalem chips will have at least eight cores per socket, so that is 2X of the performance right there. The extra memory bandwidth and chip-to-chip interconnect alone in the QuickPath Interconnect could account for a lot of the jump in performance, too. HyperThreading is being put back into the Xeon chips, too, and that is another maybe 50 percent in performance. The shrink from 45 nanometer to 32 nanometer processes that happens in 2009, after the Nehalems have been in the field for a year, could account for another 50 percent hump in performance over the Harpertown chips, since Intel could crank up the clocks and still stay in the Harpertown thermal envelope; it could also move to 16 cores and do the same. The rest of the performance gain to that 3.92 petaflops in performance will probably come through adding nodes. My best guess is that SGI can double the number of racks to 80 and hit the target with the Nehalems.

Going up by a factor of 2.5 to hit the 10 petaflops performance with the Nehalem kicker Xeon in the 2012 timeframe is a bit harder to speculate about.

To date, SGI's largest Altix ICE cluster is the 14,336-core box named Encanto installed at the New Mexico Computing Applications Center, which has a peak rating of 172 gigaflops.

Like the Columbia Altix machine, the Pleiades machine will run Novell's SUSE Linux Enterprise Server 10 operating system and will presumably be upgraded with kickers as SLES 11 and 12 make it into the field over the next four years.


RELATED STORIES

Intel Shows Off Future Penryn and Nehalem Chip Designs



                     Post this story to del.icio.us
               Post this story to Digg
    Post this story to Slashdot


Sponsored By
NUBRIDGES

nuBridges, Inc. is the secure
eBusiness authority

Thousands of companies worldwide use nuBridges software and services to connect electronically with business partners, protect information in transit and at rest, and comply with legislative and industry mandates for data security.

nuBridges technology drives B2B transactions worth $884 billion every year.

For more information on nuBridges, visit www.nubridges.com.


Editor: Timothy Prickett Morgan
Contributing Editors: Dan Burger, Joe Hertvik, Kevin Vandever,
Shannon O'Donnell, Victor Rozek, Hesh Wiener, Alex Woodie
Publisher and Advertising Director: Jenny Thomas
Advertising Sales Representative: Kim Reed
Contact the Editors: To contact anyone on the IT Jungle Team
Go to our contacts page and send us a message.

Sponsored Links

Storix:  Easily recover an entire system onto dissimilar hardware with SBAdmin for Linux and AIX
COMMON:  Join us at the annual 2009 conference, April 26 - April 30, in Reno, Nevada
NowWhatJobs.net:  NowWhatJobs.net is the resource for job transitions after age 40


 

IT Jungle Store Top Book Picks

Getting Started with PHP for i5/OS: List Price, $59.95
The System i RPG & RPG IV Tutorial and Lab Exercises: List Price, $59.95
The System i Pocket RPG & RPG IV Guide: List Price, $69.95
The iSeries Pocket Database Guide: List Price, $59.00
The iSeries Pocket Developers' Guide: List Price, $59.00
The iSeries Pocket SQL Guide: List Price, $59.00
The iSeries Pocket Query Guide: List Price, $49.00
The iSeries Pocket WebFacing Primer: List Price, $39.00
Migrating to WebSphere Express for iSeries: List Price, $49.00
iSeries Express Web Implementer's Guide: List Price, $59.00
Getting Started with WebSphere Development Studio for iSeries: List Price, $79.95
Getting Started With WebSphere Development Studio Client for iSeries: List Price, $89.00
Getting Started with WebSphere Express for iSeries: List Price, $49.00
WebFacing Application Design and Development Guide: List Price, $55.00
Can the AS/400 Survive IBM?: List Price, $49.00
The All-Everything Machine: List Price, $29.95
Chip Wars: List Price, $29.95


 
The Four Hundred
The i Platform Roadmap Is a Work in Progress

IBM Loses Two Key Executives to Retirement--Really

Java Performance Is OS Agnostic on Power6 Gear

As I See It: Soothing the Savage Programmer

IBM Goes Stateless and Cooler with iDataPlex Servers

Four Hundred Stuff
GDCM Seeks to 'Defrag' the Data Center for Higher Efficiency

Bsafe Updates Security Tools for i OS

GeneXus Brings Web 2.0 Home with Version X

Terminix Overcomes Hurdle to New B2B System, Thanks to LANSA

NSPI Launches CBU as a Service Offering

Big Iron
Micro Focus to Acquire NetManage for $73.3 Million in Cash

Top Mainframe Stories From Around the Web

Chats, Webinars, Seminars, Shows, and Other Happenings

Four Hundred Guru
Accurate Program References

Replace the Contents of a Physical File That Has Triggers

Admin Alert: How to Recreate/Restore a System Distribution Directory

System i PTF Guide
May 3, 2008: Volume 10, Number 18

April 26, 2008: Volume 10, Number 17

April 19, 2008: Volume 10, Number 16

April 12, 2008: Volume 10, Number 15

April 5, 2008: Volume 10, Number 14

March 29, 2008: Volume 10, Number 13

The Windows Observer
Microsoft Withdraws Yahoo Bid, Won't Go Hostile

GDCM Seeks to 'Defrag' the Data Center for Higher Efficiency

Hey ASA: Microsoft Delivers New Automated Service Agent

The X Factor: Everybody Wants Citrix Systems?

SugarCRM Supports Smart Phones, Including Windows Mobile

The Unix Guardian
Sun Delivers OpenSolaris Development Distro, Plus Support

AMD Revises Opteron Roadmaps, Pushes Out Rev Gs

IBM Loses Two Key Executives to Retirement--Really

GDCM Seeks to 'Defrag' the Data Center for Higher Efficiency

Power Systems: The Feeds and Speeds

Four Hundred Monitor
Four Hundred Monitor's
Full iSeries Events Calendar

THIS ISSUE SPONSORED BY:

Bytware
nuBridges
Egenera
Guild Companies
Vibrant Technologies


Printer Friendly Version


TABLE OF CONTENTS
AMD Revises Opteron Roadmaps, Pushes Out Rev Gs

New and Updated Barcelona Boxes Debut from Sun

Java Performance Is OS Agnostic on Power6 Gear

As I See It: Soothing the Savage Programmer

Virtual Server Sprawl Reeled In with Tideway Foundation 7.1

But Wait, There's More:

Live Migration Will Make Virtualization Mainstream . . . NASA Taps SGI and Intel for Pleiades 10 Petaflops Super . . . IBM and HP Do SAP ERP Bundles for SMBs . . . IBM Loses Two Key Executives to Retirement--Really . . . Avnet Expands in the United Kingdom and Ireland with Horizon Buy . . .

The Linux Beacon

BACK ISSUES





 
Subscription Information:
You can unsubscribe, change your email address, or sign up for any of IT Jungle's free e-newsletters through our Web site at http://www.itjungle.com/sub/subscribe.html.

Copyright © 1996-2008 Guild Companies, Inc. All Rights Reserved.
Guild Companies, Inc., 50 Park Terrace East, Suite 8F, New York, NY 10034

Privacy Statement