A Performance Analysis of a Real-time Jet Engine Performance Calculator Executing in Arm Cortex-A Multicore Processors
José Eduardo Thums, Areeb Sherjil, Germano Girondi, Antonio Junior, Jonas Gava, Geancarlo Abich, Ricardo A. L. Reis, Luciano Copello Ost · 2024
The performance of multicore processors plays a crucial role in meeting the safety standards requirements (e.g., response time) for safety-critical edge devices, affecting aspects such as resource allocation, fault tolerance, management, and real-time processing. In this regard, benchmarks are needed to assess the performance and underlying real-time aspects. This work contributes by extending a multithreaded real-time Jet Engine benchmark, which provides better performance and fewer missed deadlines w.r.t. other parallel solutions. The paper presents a detailed performance analysis considering different Jet Engine benchmark parallel models executed in four Arm Cortex-A processors. Results show an average performance improvement of 3.83% to 66.01% when compared to the original parallel models executing in the Cortex A-76 processor. Results also show that the extended version using a 32-bit SIMD floating-point technology has eliminated all missed deadlines when executed in the Arm Cortex-A53, A72, and A76.