May 13th, 2015
Kate Keahey, Senior Fellow of the Computation Institute, University of Chicago, and a Scientist in the Mathematics and Computer Science Division of Argonne National Laboratory presents her research in cloud computing infrastructure and services at EVL.
Wednesday, May 3, 2015. 1:00PM
EVL Cyber-Commons, Room 2068 ERF
Chameleon Open Science Cloud
Cloud computing services have become critical to all major 21st-century economic activities - yet, we are only beginning to understand this new important paradigm. Questions persist regarding applicability of the cloud platform to emergent data-intensive and sensor-based applications, its suitability for high-performance computing (HPC) applications, and its potential to leverage major emergent technologies such as Software Defined Networking (SDN). Answering these questions requires the ability to perform experiments at scale - in other words, an experimental testbed that can support experimentation with Big Data, Big Compute, and Big Instrument problems.
This talk introduces the NSF-funded Chameleon project that will provide such a large-scale platform to the open research community, allowing its users to explore transformative concepts in deeply programmable cloud services, design, and core technologies. Its high reconfigurability will allow users to work on challenges ranging from the creation of Software as a Service to kernel support for virtualization. The talk describes the areas research and types of experiments the testbed will support, hardware facilities it will offer, supported modes of user interaction with this facility, as well as rollout timeline.
Keahey is one of the pioneers of infrastructure cloud computing. She created and leads the development of the Nimbus project, recognized as the first open source Infrastructure-as-a-Service implementation, and engages in many application projects popularizing the use of the cloud computing platform in science. She also leads the Chameleon project, a distributed experimental platform for cloud computing research.