Towards native code offloading based MCC frameworks for multimedia applications: A survey. (November 2016)

• Record Type: Journal Article
• Authors: Shuja, Junaid; Gani, Abdullah; Rehman, Muhammad Habib ur; Ahmed, Ejaz; Madani, Sajjad A.; Khan, Muhammad Khurram; Ko, Kwangman
• Is Part Of: Journal of network and computer applications. Volume 75(2016)
• Page Start: 335
• Page End: 354
• Publication Date: 2016-11
• Subjects: ARM -- Virtualization -- Emulation -- Mobile Cloud Computing -- Dynamic Binary Translation -- SIMD; Microcomputers -- Periodicals; Computer networks -- Periodicals; Application software -- Periodicals; Micro-ordinateurs -- Périodiques; Réseaux d'ordinateurs -- Périodiques; Logiciels d'application -- Périodiques; Application software; Computer networks; Microcomputers; Periodicals; 004.05; 004
• DOI: 10.1016/j.jnca.2016.08.021
• Languages: English
• ISSNs: 1084-8045

Abstract

Abstract: A number of resource-intensive applications, such as augmented reality, natural language processing, object recognition, and multimedia-based software are pushing the computational and energy boundaries of smartphones. Cloud-based services augment the resource-scare capabilities of smartphones while offloading compute-intensive methods to resource-rich cloud servers. The amalgam of cloud and mobile computing technologies has ushered the rise of Mobile Cloud Computing (MCC) paradigm which envisions operating smartphones and modern mobile devices beyond their intrinsic capabilities. System virtualization, application virtualization, and dynamic binary translation (DBT) techniques are required to address the heterogeneity of smartphone and cloud architectures. However, most of the current research work has only focused on the offloading of virtualized applications while giving limited consideration to native code offloading. Moreover, researchers have not attended to the requirements of multimedia based applications in MCC offloading frameworks. In this study, we present a survey and taxonomy of state-of-the-art MCC frameworks, DBT techniques for native offloading, and cross-platform execution techniques for multimedia based applications. We survey the MCC frameworks from the perspective of offload enabling techniques. We focus on native code offloading frameworks and analyze the DBT and emulation techniques of smartphones (ARM) on a cloud server (x86) architectures. Furthermore, we debate the open research issues and challenges to native offloading of multimedia based smartphone applications. Highlights: We deliberate on DBT techniques for cross-platform heterogeneous smartphone and cloud architectures. DBT and emulation techniques are an essential part of native code based MCC offloading frameworks. We discuss techniques of cross-platform SIMD instruction translation and porting for multimedia based MCC applications. We provide a detailed taxonomy and parametric comparison of all the state-of-the-art studies discussed in the aforementioned directions. We identify research issues in current MCC offloading techniques, DBT optimization for process code migration based MCC offloading, and DBT optimizations for translation of SIMD instructions