Boosting Edge Computing Performance Through Heterogeneous Manycore Systems

The rapid development of advanced mobile applications, Internet of Things (IoT), and mobile communication technology has led to the emergence of edge computing. The paradigm shift from centralized cloud computing towards edge computing has been driven by the need to efficiently support compute intensive and delay sensitive tasks for resource and capacity constrained mobile devices and sensors, by running the applications in close proximity to the users. A number of hardware, software and hyper converged infrastructure solutions have been proposed for supporting edge computing. However, supporting massively parallel workloads for increasingly large number of mobile devices and applications can be a challenging issue. In this paper, we highlight how the features and capabilities of manycore servers can be leveraged to provide efficient edge computing services. We also discuss the key features and research challenges for supporting the computation, communication and caching (i.e. 3C) services on manycore systems.

[1]  Mahadev Satyanarayanan,et al.  Cloudlets: at the leading edge of mobile-cloud convergence , 2014, 6th International Conference on Mobile Computing, Applications and Services.

[2]  Marco Levorato,et al.  eBPF-based content and computation-aware communication for real-time edge computing , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[3]  Changwoo Min,et al.  Scaling Guest OS Critical Sections with eCS , 2018, USENIX Annual Technical Conference.

[4]  Mark D. Hill,et al.  Amdahl's Law in the Multicore Era , 2008 .

[5]  Daniel Raumer,et al.  Comparison of frameworks for high-performance packet IO , 2015, 2015 ACM/IEEE Symposium on Architectures for Networking and Communications Systems (ANCS).

[6]  Soumya Kanti Datta,et al.  Comparison of edge computing implementations: Fog computing, cloudlet and mobile edge computing , 2017, 2017 Global Internet of Things Summit (GIoTS).