Parallel Computing Optimization for Ground-based TT&C Network Situational Data Processing
Junchao Chen, Yibing Dong, Yuanyuan Li, Feng Wang · 2021
With the development of China's aerospace industry, the aerospace ground-based TT&C Network Situation Awareness System (TNSAS) has become an indispensable part of completing aerospace daily detection tasks and emergency support tasks. However, traditional calculation methods have been difficult to meet the real-time update needs of massive data processing, which has become the bottleneck of TNSAS. Aiming at this bottleneck, this paper abstracts data processing into matrix multiplication and optimizes it with parallel computing technology, such as SIMD, OpenMP, MPI, and GPU multi-threading in different scenarios to achieve high performance. Experimental results show that using these four methods in different scenarios can greatly improve the overall data processing performance by 56 times, and reduce the overall data processing time to 2%, which can effectively meet the data processing requirements of TNSAS, and deal with massive target data in the complex aerospace environment.