Run-time resource allocation for embedded Multiprocessor System-on-Chip using tree-based design space exploration

The dynamic nature of application workloads in modern MPSoC-based embedded systems is growing. To cope with the dynamism of application workloads at run time and to improve the efficiency of the underlying system architecture, this paper presents a novel run-time resource allocation algorithm for multimedia applications with the objective of minimizing energy consumption for predefined deadlines. This algorithm is based on a novel tree-based design space exploration (DSE) method, which is performed in two phases: design-time and run-time. During design time, application clustering is combined with the tree-based DSE, and after that, feature extraction and application classification is performed during run-time based on well-known machine learning techniques. We evaluated our algorithm using a heterogeneous MPSoC system with several applications that have different communication and computation behaviors. Our experimental results revealed that during runtime, more than 91% of the applications were classified correctly by our proposed algorithm to select the best resources for allocation. Therefore the results clearly confirm that our algorithm is effective.