CycleCloud Builds a 30,000-core HPC Cluster

Multicore workstations are driving faster design engineering innovation, especially when clustered together as DE explained in its September 2011 cover story and accompanying white paper. A cluster with just 32 cores can have an amazing impact on productivity and allow engineers to create more design iterations.

So just imagine what building a cluster with 30,000 cores could do. That’s what Cycle Computing did using the Amazon EC2 cloud service. Was this some kind of ridiculous publicity stunt? No. Its Nekomata cluster was created for a top 5 pharmaceutical company to perform molecular modeling. It cost $1,279 an hour to operate, according to Cycle Computing.

The company has a great blog post about the challenges of creating such a massive cluster in the cloud. It is chock-full of technical details and ends with a look at the benefits this technology can bring to science and engineering.

While we are excited about the ability to scale clusters to larger and larger core counts and forging new frontiers in cloud computing, we are most excited about the possibilities we are creating by enabling scientists to spin up such large clusters with minimal effort to answer questions that they would never have considered asking a year ago because they didn’t have access to resources that could answer those questions. — Compute Cycles blog

Source: Compute Cycles

Print Friendly

Comments are closed.


Become a fan of DE on Facebook