Abstract
This paper presents a model-based parallelization approach to parallelize embedded systems on single-ISA heterogeneous multicore processors, especially processors with the ARM big.LITTLE architecture, wherein the core assignment of the Simulink blocks is determined based on the control design constraints and characteristics of the big.LITTLE architecture. The proposed approach uses a hierarchical clustering method on Simulink blocks to reduce the problem scale, and an integer linear programming (ILP) formulation to determine the core assignment solution, considering load balancing and minimization of inter-core communication across cores with different performances. Finally, we generate the parallel code of the model based on the core assignment solution for execution on the processors. We evaluate the proposed approach by comparing it with existing methods and generating the parallel code on a single-board computer with the big.LITTLE architecture to determine its effectiveness.
Highlights
With the evolution of more complex embedded control systems, such as automotive control systems, modelbased development (MBD) with platforms such as MATLAB/Simulink [1] is becoming increasingly common in recent years
To implement the control models described in Simulink on a single-instruction set architecture (ISA) heterogeneous multicore processor, the partition of the generated control software based on control design constraints, and the parallelization of the software components based on the characteristics of single-ISA heterogeneous multicore processors for parallel execution is necessary
Among the single-ISA heterogeneous multi-core architectures, we focus on ARM big.LITTLE architecture [3] where cores are grouped by their parameters and they are homogeneous in all groups, except for the system core, if it exists
Summary
With the evolution of more complex embedded control systems, such as automotive control systems, modelbased development (MBD) with platforms such as MATLAB/Simulink [1] is becoming increasingly common in recent years. On a single-ISA heterogeneous multicore processor, cores may execute the same instruction set They offer different capabilities and performances, such as different clock frequencies and power consumption. A model-based parallelization approach is proposed to parallelize embedded systems built in the Simulink MBD environment on single-ISA heterogeneous multicore processors, especially those with ARM big.LITTLE architecture [3]. In this approach, a hierarchical clustering method is proposed to group blocks of the same attribute to top-level clusters. Our proposed approach contains code generation and user feedback, where model designers can implement their models for execution on the processor and comprehend the parallelization of the models in the MBD environment
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.