By Lionel Gibbons | February 10, 2016 | OpenStack
Voting is now open for the Spring 2016 OpenStack Summit in Austin!
Bright has submitted two session abstracts we think you'd like to see. One talks about our product, Bright OpenStack. The other talks about how to use OpenStack to build a dynamic HPC-on-demand environment.
We’ve summarized each talk and provided a link to its page on the voting site. You have to be a member of the OpenStack Foundation to vote, but don't worry – joining is free. If you’re not already a member, just click here to join. Then, help shape the OpenStack Summit agenda by voting up the sessions that you want to see.
Voting closes Wednesday, February 17 at 11:59pm PST (February 18 at 7:59am UTC) so make your choices soon.
We look forward to seeing you in Austin!
Cluster-as-a-Service (CaaS) is an innovative concept that empowers end users of an OpenStack private cloud to easily create sophisticated, isolated, and secure High Performance Computing (HPC) clusters inside of that cloud. CaaS deploys a ready-to-use HPC cluster preconfigured with all required HPC libraries (e.g. MPI, OpenMP, CUDA), compilers, workload managers (e.g. Slurm, LSF, Torque, Grid Engine) and other tools that a user needs to quickly start running HPC workloads.
We will cover how Cluster-as-a-Service can be used to spin up not only virtualized HPC clusters, but also virtualized Ceph / Spark / Hadoop / OpenStack clusters; all within minutes. But wait, there’s more! We will also show how all of this can form the basis for an “Anything-as-a-Service” approach to building your own distributed application(s).
There are many ways to implement OpenStack, but few provide everything you need to run a cloud. Other solutions typically focus narrowly on OpenStack, providing little help in setting up the (very important) areas that surround it. Bright OpenStack takes a different approach. We've taken years of experience in deploying and managing 1000+ node HPC clusters and applied it to deploying and managing OpenStack clouds, both small and large.
We will demonstrate an easy to use, but extremely powerful, single-pane-of-glass solution for managing OpenStack and its entire ecosystem. We will also discuss how combining Hadoop, Spark, HPC, Ceph and OpenStack can benefit your end users.