An Improved Parallelized Random Linear Network Coding Algorithm on GPU

Network coding has been used widely in various networks for improved throughput and robustness. However, the computational overhead introduced by the network coding operations has become the obstacle for practical deployment of network coding. In this paper, we exploit the parallel computing power of GPU (graphics processing unit) to accelerate the network coding operations. In the INVIDIA's CUDA programming environment of general-purpose computing on GPU, we designed and implemented an improved parallel random linear network coding algorithm and obtained 36 times of speedup over the CPU counterpart.