Search

According to the characteristics of the 21CMA correlator algorithm, we propose a novel high-efficient method to implement this specific algorithm on the Hadoop+CUDA platform, and it out-­performs the MPI alone and MPI+CUDA solutions. The proposed method improves the parallel model of the correlator. Compared to the earlier MPI solution, it greatly enhances the running performance by utilizing the advantages of GPU for FFT processing, vector multiplication and vector addition. The Hadoop software architecture, a big-data platform, is employed in the method by using Hadoop Streaming tool to realize parallel execution of non-Java programs running on distributed systems, and linear speed-ups on clusters are easily obtained. In addition, the resutt data and procedure logs can be flexibly managed in the parallel file system of the Hadoop HDFS, which provides a well precondition for future big-data analysis. [ABSTRACT FROM AUTHOR]

To analyze the work capacity of spread-spectrum communication system under interference environment, the essence of DS-SS is studied. Aiming at the implementation complexity of DD-SS by pure hardware, a DD-SS proposal which can be applied in CPLD chip is proposed. A simulation model is established and the design of correlator and search and acquisition by sequence phase are described in detail. The work of system under various kinds of interference is designed and analyzed. The results show that even if the spread spectrum signal has interference error code to 22.8 per cent, the system still dispread correctly. The analysis method and result have some reference value for practical applications. [ABSTRACT FROM AUTHOR]