We live in interesting times: new ideas and technological opportunities emerge at ever increasing rates in AI, edge computing and IoT, and programmable networking to name just a few. These innovations require a platform where they can be deployed and investigated -- and where new solutions -- that those disruptive ideas enable -- can be developed, tested, and shared. To support a breadth of experimentation such a platform has to provide access to a diversity of hardware, support deployments at scale, as well as deep reconfigurability so that a wide range of experiments can be supported. It also has to provide mechanisms for easy and direct sharing of repeatable digital artifacts so that new experiments and results can be easily replicated and help enable further innovation. Most importantly -- since science does not stand still – these types of instruments require the capability for constant adaptation to support an ever increasing range of experiments driven by emergent ideas and opportunities.
In this talk, I will describe the goals, the design strategy, and the capabilities of two NSF-funded scientific research platforms -- Chameleon and FLOTO – as well as some of the research and education projects our users are working on.
First, I will describe Chameleon which provides a large diversity of edge to cloud resources including Fugaku nodes, a range of accelerators, and disaggregated hardware (Liqid, GigaIO) with reconfigurability at bare metal level. Chameleon is currently distributed over two core sites at the University of Chicago and the Texas Advanced Computing Center (TACC) connected by 100 Gbps network. To date, the testbed has supported 10,000+ users and 1,100+ projects in research, education, and emergent applications.
FLOTO deploys 1,000 Raspberry PIs nationwide for broadband research. The FLOTO infrastructure implements “zero touch” installation for the devices such that they can be managed without physical access. Users can answer research different questions by deploying the devices in different configurations; running different applications (i.e., in this case, different types of broadband tests); or processing the data returned by the devices in different ways. Increasingly, users are also using FLOTO to answer different questions by customizing the infrastructure itself by e.g., combining it with new IoT sensors.
Scientist at Argonne National Laboratory and Senior fellow at the computation institutes at the University of Chicago, Argonne National Laboratory and the University of Chicago
