Eli Lilly uses Amazon Web Services and other cloud services to provide high-performance computing, as needed, to hundreds of its scientists. With AWS, Powers said, a new server can be up and running in three minutes (it used to take Eli Lilly seven and a half weeks to deploy a server internally) and a 64-node Linux cluster can be online in five minutes (compared with three months internally). "The deployment time is really what impressed us," Powers said. "It's just shy of instantaneous."
Looking ahead, Powers foresees the possibility of using cloud services from a half dozen different vendors, and he wants to head off a scenario where Eli Lilly has to configure and manage each of those separately. He describes the need for an "orchestration layer" that sits between Eli Lilly and the various cloud services to which it subscribes. That layer, provided by an intermediary company and not Eli Lilly itself, would comprise algorithms that determine the best cloud service for a particular job based on lowest cost, highest performance, or other requirement. Such an approach would make it possible for Eli Lilly and other users to write to a single API rather than many, while optimizing service usage.
He also talks about the potential to use cloud computing for external collaboration. Eli Lilly already is doing some of this, but Powers envisions going further, to the point where the cloud becomes "a point of integration" between Eli Lilly and outside researchers. "We have work going on right now that starts to fit into this collaborative scheme," he said.
To hear more about what Eli Lilly is doing with cloud computing and where it goes from here, log in to our recent Webcast, which is available for replay. In addition to Dave, I give an overview of cloud services in the Webcast, and Amazon VP Adam Selipsky describes Amazon Web Services. You can sign in here.