The Register® — Biting the hand that feeds IT

Feeds

Yahoo! outsources! India's! giant! supercomputer!

14,000 Pig-powered processors

Magic Quadrant for Enterprise Backup/Recovery

Yahoo! will start leasing computer scientists some quality time with the fourth fastest supercomputer in the world, courtesy of India-based Computational Research Laboratories (CRL).

Under the agreement announced today, Yahoo! will make available CRL's enormous system to Indian academic institutions so long as they make use of Yahoo!-supported software such as Apache Hadoop.

Hadoop is an open source distributed computing platform heavily funded by Yahoo! and managed by the Apache Software Foundation. CRL's computer will also be running company projects such as the Pig parallel programming language developed by Yahoo! Research.

According to the most recent Top 500 list of supercomputers, CRL's machine dubbed EKA, ranks number four in the world. The machine is a Hewlett-Packard-based cluster, sporting 14,400 processors, 28TB of memory, and 140TB of disk storage. EKA has a peak performance of 180 trillion calculations per second, has a sustained computation capacity of 120 teraflops, and is even able to run Crysis on medium mode.

"This partnership brings together Yahoo!'s leadership role in the development of Hadoop and CRL's expertise in high performance computing, and will help bridge the gap between traditional supercomputing and cloud computing research in India," said S. Ramadorai, chairman of CRL in a statement.

Cloud computing is a beastly term heaved from the oily anus of Silicon Valley marketing departments. It has managed to wriggle its way into standard IT lexicon to describe using large pools of shared systems to deliver software and computational power over the internet. El Reg is not terribly fond of the phrase. You might have picked up on that.

Opening gigantor supercomputers to academia has been the all rage amongst tech companies of late. For instance, Sun Microsystems, AMD, and the Texas Advanced Computer Center (TACC) are offering able bodied scientists time on the enormous 15,744 processor Ranger system.

Yahoo has been putting its weight behind the Hadoop platform to help battle Google's own cluster computing plans, the Google File System (GFS) and MapReduce technologies.

Yahoo is also pushing its first-ever Hadoop Summit, which opens tomorrow in Santa Clara, California. The event aims to bring leaders of the Hadoop developer and user community together to drink heavily in the conference center lobby, as well as rudely browse the internet and check their e-mails during keynote speeches. That's how most of these kind of things go anyway. ®

Agentless Backup is Not a Myth

Latest Comments

Sad days for supercomputing

Seymour Cray would be ashamed of current "supercomputers", if it turns out that the 4th most powerful supercomputer is just a bunch of el-cheapo x86 blade boxen.

It seems that the "1024 chicken" philosophy won after all, and we're now doomed to use mediocre hardware for all eternity!

Mine is the one with the liquid N2 cooling system ;)

0
0
Anonymous Coward

All that computing power...

and the answer is still:

101010

Isn't there such a small market for these cluster machines, and really when you start dealing with such astronomic numbers or iterations of computation how sure can you really be the answer is accurate.

'Computer says "no" '

0
0

Pile of blades?

Is it really a pile of blades? then it is a piece of s***, as HP blades share Ethernet fabric.. I would (and do) design these things as piles of Proliant doalprocessor servers.. and hey, you can put multiple multi-giga-ethernet adapters there!!

0
0

More from The Register

SCO vs. IBM battle resumes over ownership of Unix
Zombie lawsuit back and wants to suck the brains out of Linux
 breaking news
You don't need phone lines or cable for ANYTHING, says Dish
The satellite-dish man can sort you out with phone and broadband over the air too
 breaking news
What's HP got under wraps? Looks awfully flash and tape shaped
What happens in Vegas won't stay there - we've got the details
AMD lifts the veil on Opteron, ARM chip plans for 2014
Not much action going on in 2013, though
Microsoft borks botnet takedown in Citadel snafu
Stupid Redmond kicked over our honeypots, wail white hats
IBM's $1bn layoffs latest: Now axe swings in US, Canada - reports
Union claims 121 storage bods canned after dismal sales
NetApp musters muscular cluster bluster for ONTAP busters
Storage array OS overhauled to juggle more nodes, go down on you, er, less
HP adds 'Haswell' Xeon E3s to entry ProLiant servers
Gussies up MicroServer for SMBs, adds baby switches