Study on CS Algorithm for SAR Imaging Based on CUDA
Gao Yue · Computer & Network · 2012
A parallel implementing method for synthetic aperture radar(SAR) imaging algorithm based on compute unified device architecture(CUDA) is proposed in order to solve the low efficiency of SAR imaging algorithm on general computing platform.CUDA principle and chirp scaling(CS) algorithm parallel feature are analyzed.On the basis of this,the CUDA implementation of each algorithm step is described in detail.Experimental results show that the optimized CS algorithm is 10～20 times faster.Therefore,the algorithm is effective.