Parallelised Multithreaded Applications on a 4-core Field Programmable Gate Array (FPGA) Architecture

Abstract

Background: The challenges in real-time multithreading, particularly in the efficiency of multithreaded applications running concurrently on multiple cores, have evolved significantly due to the increase in IoT, cloud and edge computing applications. The continuous increase in cores depth adds further research issues related to the efficiency of such multicore systems and their applications. Therefore, further research is still required. Multicore systems can achieve higher performance running in parallel multiple multithreaded applications. However, efficient parallelisation of multiple threads among many cores is not an easy task. Field Programmable Gate Arrays (FPGAs) is a preferred technology for the rapid design and experimentation with such architectures, based primarily on softcore processors. Objectives: The purpose of this research is to investigate the efficiency of running in parallel and concurrently multithreaded applications on a 4-core FPGA multicore architecture. Methods: The design of a 4-core FPGA architecture is implemented with Nios II/f soft processors on a Cyclone IV series chip, having real-time Linux operating system (OS) support. A multithreaded application with specific compute-intensive tasks is developed in C, and is used to obtain measurements in specific efficiency metrics under different core configurations. Results: The reliability of the proposed 4-core FPGA architecture is validated against 4-core and 2core development platforms, respectively, on Raspberry Pi4 and BeagleBone AI single board computers. The results have been analysed and evaluated upon performance metrics, including execution time, response time, speedup, and cores usage. The experimental tests demonstrate the validity and efficiency of the approach to using FPGA for experimentations with multithreaded applications. Conclusion: The obtained results show that the proposed FPGA architecture stands well both in terms of timing and efficiency metrics. Execution times are about 50% lower, and the average speedup at 21% is fairly close to that of 33% for the Raspberry Pi4, and higher than BeagleBone AI (10%). The proposed measurements approach and evaluation methodology could benefit the design and development of real-time systems utilizing operating systems with real-time support in emerging areas, such as embedded devices in real-time control. © 2022 Bentham Science Publishers.