Singularity Containers for Enterprise Performance Computing (EPC)
Container engines like Docker are great for microservices, but in this talk, Eduardo Arango shows why Sylabs thinks their Singularity container is best for HPC and other workloads.
Speakers
- Eduardo ArangoSoftware Engineer, Sylabs Inc
Software containers continue to evolve at a rapid pace. Two distinct classes of open source container solution have appeared - one that chiefly supports microservices, and one that also supports batch, interactive, and multi-user environments for use cases such as HPC, modeling, and machine learning.
In the latter class, Singularity has emerged as the leading solution, with a strong and vibrant open source community of users and contributors. At runtime, Singularity blurs the lines between the container and the host system allowing users to read and write persistent data and leverage hardware like GPUs and Infiniband with ease.
The Singularity security model is also unique among container solutions. This talk will examine why there are two classes of container solutions and present the features of Singularity that make it the preferred solution for non-microservice workloads.