Skip to main content

Cycle Computing Builds 10000-Core Supercomputer On Amazon EC2 Cloud

Cycle Computing has created a 10,000 core high performance computing supercomputer on the Amazon EC2 cloud computing platform.

The supercomputer, designed for San Francisco based biotech company Genentech, is comprised of 1,250 instances with 8 cores each, Network World reveals.

The entire cluster, which took 45 minutes to come online, comes with 8.75TB of RAM and 2PB disk space. The powerful HPC system would have ranked 114th in the Top 500 Supercomputer list based on the November ratings.

Creating such a massive cluster using on-premise servers, switching and storage gear could cost millions of dollars, but by running the HPC machine on the cloud, the costs have come down significantly. It cost Genentech merely $8,500 to run the cluster for eight hours, including the fees charged by Amazon and Cycle Computing.

“We're really trying to democratize this so any researcher can get a grant and run their code. Rather than buying two servers and waiting several months for a simulation to complete, they can spend less money and get their results in a matter of hours,” Jason Stowe, the CEO and founder of Cycle Computing said in a statement to The Register.

"We're already working on scaling up larger," Stowe said. All we need is a customer with "a use case to take advantage of it."