Abstract
The application workloads in modern MPSoC-based embedded systems are becoming increasingly dynamic. Different applications concurrently execute and contend for resources in such systems, which could cause serious changes in the intensity and nature of the workload demands over time. To cope with the dynamism of application workloads at runtime and improve the efficiency of the underlying system architecture, this article presents a hybrid task mapping algorithm that combines a static mapping exploration and a dynamic mapping optimization to achieve an overall improvement of system efficiency. We evaluate our algorithm using a heterogeneous MPSoC system with three real applications. Experimental results reveal the effectiveness of our proposed algorithm by comparing derived solutions to the ones obtained from several other runtime mapping algorithms. In test cases with three simultaneously active applications, the mapping solutions derived by our approach have average performance improvements ranging from 45.9% to 105.9% and average energy savings ranging from 14.6% to 23.5%.
Highlights
Modern embedded systems, which are more and more based on Multiprocessor Systemon-Chip (MPSoC) architectures, often require supporting an increasing number of applications and standards
We present several experimental results in which we investigate various aspects of our hybrid task mapping (HTM) algorithm
We have proposed a hybrid mapping algorithm, called HTM, for MPSoC-based embedded systems to improve their performance by capturing the dynamism of the application workloads executing on the system
Summary
Modern embedded systems, which are more and more based on Multiprocessor Systemon-Chip (MPSoC) architectures, often require supporting an increasing number of applications and standards. In these systems, multiple applications can run concurrently and are simultaneously contending for system resources. There are often different execution modes (or program phases) with different requirements. A video application could dynamically lower its resolution to decrease its computational demands in order to save the battery. The behavior of application workloads executing on the embedded system can change dramatically over time. ACM Transactions on Embedded Computing Systems, Vol 14, No 1, Article 14, Publication date: January 2015
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
