Containers in HPC - what they fix and what they break (and how to fix that, too)

Today we’re joined by Christian Kniep who is one of our senior developer advocates in HPC Engineering. Christian is leading the cause for containerization in HPC, and helping our engineering and product teams focus on enabling that path on AWS.

We know containers are a ‘mixed’ topic for HPC folks, and so we’re starting a series of Tech Shorts to talk about what they are, what problems they solve, what new problems they create, and what solutions exist to address those.

Today is part 1, where we talk about how containers work generally, how they work on AWS, with things like AWS Nitro and GPUs in play.

Next week, we’ll talk about containers in shared infrastructure and multi-node parallelism, too.

The FOSDEM devroom we spoke about is here: and you can find Christian on twitter here - pick up the conversation with him if you have some thoughts about containers and how they work for you (or not).

If you have ideas for technical topics you’d like to see us cover in a future show, let us know by finding us on Twitter (@TechHpc) and DM’ing us with your idea.