Realization of fixed-point SAR imaging based on embedded GPU

摘要

Aiming at the problem of insufficient memory in the real-time processing of SAR imaging on embedded TX2, this paper studies a design optimization scheme of fixed-point imaging algorithm on TX2. In order to ensure the accuracy, this paper only performs fixed-point processing on the FFT. According to the characteristics of the algorithm, the memory multiplexing method is adopted to effectively reduce the occupation of the work area buffer. A large number of registers are used to improve computing performance. The results show that the fixed-point FFT processing scheme can achieve a hundred times faster than the Intel Xeon CPU, and the memory footprint is less.