Cloud Computing
We have two project underway that explore cloud computing, the first is working on semi-automatic partitioning of application for migration to the cloud. This project is exploring the use of run-time analysis of Java programs to determine program structure, which is then used as input to partitioning algorithms that consider cost, resource and performance constraints to determine effective partitioning.
A second small project (Dynamic Instrumentation for Configuration Extraction) is using low level run time analysis (PIN based) to determine structure, dependencies and configuration to provide input to a migration tool being developed by a local SME (Metafor)
Publications:
Profiling-as-a-Service: Adaptive Scalable Resource Profiling for the Cloud in the Cloud Nima Kaviani, Eric Wohlstadter, Rodger Lea To appear In Proceedings of the 9th International Conference on Service Oriented Computing, Paphos, Cyprus, 2011.