HPCaaS experiment becomes commercial service
UberCloud Marketplace goes live
After 18 months of experimentation, UberCloud has launched a commercial service to help academic HPC users find cloud-accessible resources for their projects: a kind of HPC-as-a-service matchmaker.
The project follows two lines of thought: although there's plenty of compute cycles already sitting on the cloud courtesy of Amazon et al, more specialised workloads work better on optimised machines; and second, that someone with a project like fluid dynamics also needs to call on experts to get their project running on one of those specialised machines.
UberCloud says its original free HPC Experiment attracted “hundreds” of service providers and “independent experts” (or, perhaps, 125 organisations, since its announcement gives that number as well).
The user has to register at the UberCloud site to request quotes from providers, giving details of their project, software requirements, machine specs like CPUs, GPUs, memory, and storage requirements, network connection requirements, and project timing.
Applications the company cites as candidates for the service include fluid dynamics, finite element material analysis, physics, chemistry, biology and (because it has to be included in any computing checklist of 2014), big data.
And yes, Amazon is included among the providers offering cycles via the UberCloud Marketplace. ®