'NO TEARS HPC - honest-to-goodness research-ready HPC clusters in under 10 minutes.

When COVID-19 struck in 2020, lots of scientists all over the world had to drop EVERYTHING and get busy solving some very big problems, very quickly. AWS became a founding member of the COVID-19 HPC Consortium, which is a White House-led initiative to provide COVID-19 researchers worldwide with free compute time and huge resources on leading industry, government, and academic HPC systems. In short, we all threw the kitchen sink at the problem of speeding up the pace of scientific discovery in the fight to stop the virus.

From AWS’s point of view, global reach and capacity are solved problems. Our challenge was to onboard researchers quickly, with no specialized knowledge necessary … so they could get computing on AWS as fast as humanly possible. To that end we developed the NoTearsHPC cluster solution for 1-click launches.

Evan Bollig and Sean Smith from the team who built No Tears join us to talk about how it work, what it provides and show us how easy it is to do really complicated things really fast. They used AWSome things like AWS ParallelCluster and awesome things like Spack to make all that possible. And with the help of our friends at Intel, we all helped the Spack team make package installation even faster still.

if you have an AWS account, you can launch a No Tears cluster, as per the talk by going to it’s GitHub page here:

https://github.com/aws-samples/no-tears-cluster

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.