Yahoo! outsources! India's! giant! supercomputer!
14,000 Pig-powered processors
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. ®