Penguin unveils Linux-based HPC in the cloud

Penguin Computing has begun allowing researchers, scientists and engineers to lease its high-performance computing capabilities through the cloud

Penguin Computing, a company that provides high-performance computing resources to researchers, scientists and engineers, has begun offering its services in the cloud.

Penguin On Demand (POD) became available on Tuesday. The company said the service is intended for those who need HPC capabilities without having to acquire the clustered infrastructure required for that level of computing.

"The most popular cloud infrastructures today, such as Amazon EC2, are not optimized for the high-performance parallel computing often required in the research and simulation sciences," Penguin chief executive Charles Wuischpard said in a statement. "POD delivers immediate access to high-density HPC computing, a resource that is difficult or impossible for many users to utilise in a timely and cost-effective way."

Wuischpard added that POD would bring high-performance computing capabilities to "a much broader market".

HPC involves the use of clusters that run in parallel, combining the processing power of each node to run heavy loads. This approach is mostly used in scientific research and engineering, and for financial tasks, where huge amounts of data need to be processed quickly.

Penguin's Linux clusters use high-density Xeon-based compute nodes, together high-speed storage. According to the company, this approach allows customers to access the full resources of its servers at once for maximum performance, as opposed to the virtualisation approach used in most cloud computing systems.

Cloud-based HPC capabilities are also set to be provided in the UK sometime this year, when Cambridge University starts allowing small- and medium-sized businesses to lease processing time on its Darwin supercomputer.


You have been successfully signed up. To sign up for more newsletters or to manage your account, visit the Newsletter Subscription Center.
See All
See All