This has been a fantastic year for Chameleon and we go over all the major features the project acquired. We also have a couple of new tidbits: the long awaited CHI@Edge Xena upgrade which will be interesting to our edge users and an announcement of the Chameleon JupyterHub infrastructure upgrade coming up first thing in the New Year. Have a fantastic Holiday and Happy New Year!
This month, we talk to Rick Anderson from Rutgers University about his experience using Chameleon to experiment with autonomous vehicles!
To help make your spirits bright we will continue our “Chameleon for Christmas” tradition with end of the year 14 day leases – you get twice as much time for being twice as nice! This feature will be available for a limited time only. Also, a reminder that HelpDesk will be closed during the Holidays – please, read the post for all the details and plan accordingly. Happy Holidays!
As has become holiday tradition, we review some of our most common tickets of 2022, and provide answers and context that we hope is a helpful gift for all of our experimenters in the coming year.
We are hiring! Come and join the team to help us build and operate the kick-ass Chameleon experimental platform as well as develop new ideas in edge computing and reproducibility. You will be working on the bleeding edge, state-of-the-art technologies, evaluating and extending open source systems and tools, and developing new features -- and most importantly working with our amazing community of users who take our breath away every day with their cool resaerch ideas!
We hope everybody's had a great Thanksgiving! We've been busy bees this month supporting IndySCC and the many supercomputing projects and demos but still have a little something we can all be thankful for: we now have InfiniBand on the A100 nodes so you can build sophisticated data systems of components connected via RDMA fabric -- and we also have better filters for hardware so you can find those components more easily!
Today's Tips&Tricks blog spotlights one of the Chameleon Associate Sites: the Electronic Visualization Laboratory (EVL) at the University of Illinois Chicago. Learn about the hardware availability at the site, the motivation behind creating it, and some hands on insights gained in the process of deploying CHI in a Box on the site!
In this month's user experiment blog we get a fascinating insight into how much power training deep neural networks (DNNs) consumes – and how to make it less. The authors’ discuss research presented as part of their NSDI ’23 paper, describe how they structured their experiments on Chameleon, and explain why bare metal resources are essential for power management research.
Watch the IndySCC finals in real-time from today until Sunday 11/06 at 9 AM EST
Things were pretty scary yesterday but we managed to pull a few tricks and bring you some new treats to enjoy in November! Between new Fugaku nodes, the ability to experiment with SGX, and a better way to work with networking at CHI@Edge, we hope to keep you busy and entertained this next month!