EAGER: Collaborative Research: Toward An Adaptive Programming System for Cloud-Enabled Smartphone Applications

点击翻译按钮获取中文摘要

Smartphones are fast becoming a full-fledged computing platform thatour society depends upon. Smartphone applications that access dataand computing resources in the "cloud" are inevitable given theprocessing and storage limitations on the phones. Today the burden ofpartitioning smartphone applications between the phone and the cloudlies squarely with the programmer. This manual approach topartitioning applications is fundamentally limited and will not scaleup to allow smartphones to become a truly rich and robust computingplatform. Manual partitioning is tedious and error prone. Moreover,manual partitioning requires the programmer to make importantdecisions that cannot be properly made until run time.This project explores the requirements, design, and implementation ofa programming system for cloud-enabled smartphone applications that isinherently adaptive, partitioning applications transparently in orderto cope with a diverse set of dynamic constraints. The project isstudying cloud-enabled smartphone applications from a variety ofdomains in order to understand application requirements, constraints,and tradeoffs in practice. The project is also pursuing programmingmodels that allow developers to flexibly and declaratively express anapplication's components along with their dependencies andconstraints. Finally, the project is developing a prototype systemarchitecture that collaboratively executes an application on the phoneand the cloud subject to the application's requirements. Within adecade, smartphones will transform the way health and lifestylechoices are delivered to much of the population. This project ishelping to enable this transformation by making a rich class ofsmartphone applications much easier to create, adapt, and understand.