NASA has just revamped the storage environment at the NASA Advanced Supercomputing (NAS) facility at Ames Research Center in Mountain View, Calif. This revamp consists of a new 450 TB storage network working in tandem with the massive Columbia supercomputer, which runs on Intel Itanium 2 and Linux. “All of the storage is within one […]
NASA has just revamped the storage environment at the NASA Advanced Supercomputing (NAS) facility at Ames Research Center in Mountain View, Calif. This revamp consists of a new 450 TB storage network working in tandem with the massive Columbia supercomputer, which runs on Intel Itanium 2 and Linux.
“All of the storage is within one big SAN fabric,” said Bob Ciotti, Terascale Systems Lead at NASA. “We now have 200 TB of data on Fibre Channel and 250 TB on SATA.”
The various system elements include:
“The shared file system handles the access of meta data through a proxy system so it is possible to read and write to FC storage directly,” said Ciotti.
Why Itanium 2 and Linux?
Why base the platform on Intel Itanium 2 processors and Linux rather than traditional RISC chips and UNIX? According to Ciotti, Itanium 2 has now reached the point where it can compete well with RISC.
“We get high bandwidth off out Itanium 2 chips,” he said. “It also has a large cache that suits our applications.”
Itanium 2 is based on the EPIC (explicitly parallel instruction computing) architecture. These chips come with Level 1 cache of 32KB, 256KB L2 cache, up to 9 MB L3 cache and clock speeds between 1.3 and 1.6 GHz. They are based upon the Intel E8870 chipset, system buses are either 400 or 533 MHz, and I/O bandwidth is 6.4 GB/sec.
Continued on Page 2.
Continued on Page 1.The operating system for Columbia is Red Hat Linux 2.4. Previously, NASA has been used IRIX for supercomputing on SGI Origin servers. It moved to Red Hat when SGI brought out its more powerful Altix server line that runs on Linux. SGI are now shifting to SUSE Linux and NASA will follow suit.
“Linux doesn’t yet have all the features of IRIX quite yet but it is getting there rapidly,” said Ciotti. “Linux is maturing more rapidly than IRIX.”
A total of 20 SGI Altix servers make up Columbia. NASA’s supercomputer includes eight of the latest Altix models. This is known as the Altix 3700 Bx2. This version doubles the processor density and available bandwidth. As well as Linux and Itanium 2, it has 9 MB cache, 64 processors per rack, and scales to 256 processors in a single system image (SSI).
“Such a large SSI creates really good environment for code development,” said Walt Brooks, division chief, advanced supercomputing division, NASA. It offers low latency and is user friendly.”
SGI NUMAlink 4 interconnect technology has been introduced to Altix produces 6.4GB/sec. Altix also uses a shared memory architecture called NUMAflex that overcomes bottlenecks. All nodes operate on one large shared memory space that eliminates data passing between nodes. Big data sets can fit entirely in memory and less memory per node is required.
Another feature of the storage environment is enhanced system cooling. The eight Altix 3700 Bx2’s have double the density of previous models posing worries about overheating.
“As we were stretching the limits of cooling, the server doors are specially designed to have cool air fed through them,” said Brooks. “Chilled water is brought in and coupled into radiator loops within the door to keep them cool.”
Columbia recently smoked the competition in recent LinPack benchmark tests. It achieved 42.7 trillion calculations per second, making it the fastest in the world at the time.
“The science that already has been produced has been extraordinary,” said Brooks. “Instead of scientists queuing up for supercomputing resources, we now have the enough capacity for everybody.”
He gives an example of simulations showing a decade’s worth of changes in ocean temperatures and sea levels that used to take a year to model. But using the modernized storage environment, scientists can now simulate this in a day or two.
Ethics and Artificial Intelligence: Driving Greater Equality
FEATURE | By James Maguire,
December 16, 2020
AI vs. Machine Learning vs. Deep Learning
FEATURE | By Cynthia Harvey,
December 11, 2020
Huawei’s AI Update: Things Are Moving Faster Than We Think
FEATURE | By Rob Enderle,
December 04, 2020
Keeping Machine Learning Algorithms Honest in the ‘Ethics-First’ Era
ARTIFICIAL INTELLIGENCE | By Guest Author,
November 18, 2020
Key Trends in Chatbots and RPA
FEATURE | By Guest Author,
November 10, 2020
FEATURE | By Samuel Greengard,
November 05, 2020
ARTIFICIAL INTELLIGENCE | By Guest Author,
November 02, 2020
How Intel’s Work With Autonomous Cars Could Redefine General Purpose AI
ARTIFICIAL INTELLIGENCE | By Rob Enderle,
October 29, 2020
Dell Technologies World: Weaving Together Human And Machine Interaction For AI And Robotics
ARTIFICIAL INTELLIGENCE | By Rob Enderle,
October 23, 2020
The Super Moderator, or How IBM Project Debater Could Save Social Media
FEATURE | By Rob Enderle,
October 16, 2020
FEATURE | By Cynthia Harvey,
October 07, 2020
ARTIFICIAL INTELLIGENCE | By Guest Author,
October 05, 2020
CIOs Discuss the Promise of AI and Data Science
FEATURE | By Guest Author,
September 25, 2020
Microsoft Is Building An AI Product That Could Predict The Future
FEATURE | By Rob Enderle,
September 25, 2020
Top 10 Machine Learning Companies 2021
FEATURE | By Cynthia Harvey,
September 22, 2020
NVIDIA and ARM: Massively Changing The AI Landscape
ARTIFICIAL INTELLIGENCE | By Rob Enderle,
September 18, 2020
Continuous Intelligence: Expert Discussion [Video and Podcast]
ARTIFICIAL INTELLIGENCE | By James Maguire,
September 14, 2020
Artificial Intelligence: Governance and Ethics [Video]
ARTIFICIAL INTELLIGENCE | By James Maguire,
September 13, 2020
IBM Watson At The US Open: Showcasing The Power Of A Mature Enterprise-Class AI
FEATURE | By Rob Enderle,
September 11, 2020
Artificial Intelligence: Perception vs. Reality
FEATURE | By James Maguire,
September 09, 2020
Drew Robb is a contributing writer for Datamation, Enterprise Storage Forum, eSecurity Planet, Channel Insider, and eWeek. He has been reporting on all areas of IT for more than 25 years. He has a degree from the University of Strathclyde UK (USUK), and lives in the Tampa Bay area of Florida.
Datamation is the leading industry resource for B2B data professionals and technology buyers. Datamation's focus is on providing insight into the latest trends and innovation in AI, data security, big data, and more, along with in-depth product recommendations and comparisons. More than 1.7M users gain insight and guidance from Datamation every year.
Property of TechnologyAdvice. © 2025 TechnologyAdvice. All Rights Reserved
Advertiser Disclosure: Some of the products that appear on this site are from companies from which TechnologyAdvice receives compensation. This compensation may impact how and where products appear on this site including, for example, the order in which they appear. TechnologyAdvice does not include all companies or all types of products available in the marketplace.
