Feeds

Boffins look down back of Amazon Web Services, find a SUPERCOMPUTER

Few clicks here, few thousands dollars there - bingo, a 1.21PFLOP beast in the cloud

Boost IT visibility and business value

What runs faster than the majority of the world's supercomputers, costs less, and was used to research organic solar-power cells? The answer is Megarun, a 1.21-petaflop super that was spun up by Cycle Computing in the AMAZON CLOUD.

Cycle Computing revealed its Megarun beast on Tuesday before the kickoff of Amazon Web Services's re:Invent conference in Las Vegas this week.

Megarun uses three times as many CPU cores as the company's last 50,000 core whopper in 2012, and was tasked with divining new organic photovoltaic compounds from 205,000 molecules.

The virty super used Schrödinger's Materials Science software suite to analyze the molecules, and was able to study thousands at once through the use of Cycle Computing's top-secret "Jupiter" job scheduler.

Jupiter was able to marshal some 156,314 compute cores across 16,788 AWS instances slathered across all eight of Amazon's public regions for an 18-hour compute job. It is designed to eventually run "millions of cores" performing tens of millions of tasks, according to a company slide.

The system's peak performance of 1.21 petaflops would rank it as the planet's 29th most powerful computer in the top 500 supers of the world as of June 2013, Cycle Computing said.

The majority of the system ran on Amazon's CC2 instances due to the performance of Intel's Sandy Bridge processors, Cycle told El Reg, though it did also use second-generation M3 processors, and the graphical-heavy C1 systems as well. Megarun's compute resources cost $33,000 through the use of Amazon's low-cost spot instances, we're told, compared with the millions and millions of dollars you'd have to spend to buy an on-premises rig.

"While this run broke records, we continue to explore the limits of scalability and faster time to market and time to result for scientific computing and analytics in Life sciences, Financial Services, Manufacturing, Energy, and Media," Cycle Computing wrote in a blog post.

Though Amazon is most famous for throwing a wrench into the high-margin businesses operated by HP, Dell, EMC, IBM, and others, it seems that bit-flippers such as Cray and SGI should now be worried as well. ®

The essential guide to IT transformation

More from The Register

next story
The Return of BSOD: Does ANYONE trust Microsoft patches?
Sysadmins, you're either fighting fires or seen as incompetents now
Microsoft: Azure isn't ready for biz-critical apps … yet
Microsoft will move its own IT to the cloud to avoid $200m server bill
Oracle reveals 32-core, 10 BEEELLION-transistor SPARC M7
New chip scales to 1024 cores, 8192 threads 64 TB RAM, at speeds over 3.6GHz
Docker kicks KVM's butt in IBM tests
Big Blue finds containers are speedy, but may not have much room to improve
US regulators OK sale of IBM's x86 server biz to Lenovo
Now all that remains is for gov't offices to ban the boxes
Flash could be CHEAPER than SAS DISK? Come off it, NetApp
Stats analysis reckons we'll hit that point in just three years
Object storage bods Exablox: RAID is dead, baby. RAID is dead
Bring your own disks to its object appliances
prev story

Whitepapers

5 things you didn’t know about cloud backup
IT departments are embracing cloud backup, but there’s a lot you need to know before choosing a service provider. Learn all the critical things you need to know.
Implementing global e-invoicing with guaranteed legal certainty
Explaining the role local tax compliance plays in successful supply chain management and e-business and how leading global brands are addressing this.
Build a business case: developing custom apps
Learn how to maximize the value of custom applications by accelerating and simplifying their development.
Rethinking backup and recovery in the modern data center
Combining intelligence, operational analytics, and automation to enable efficient, data-driven IT organizations using the HP ABR approach.
Next gen security for virtualised datacentres
Legacy security solutions are inefficient due to the architectural differences between physical and virtual environments.