We present a graphics processing unit(GPU)cluster-based Monte Carlo simulation of photon transport in multi-layered tissues.The cluster is composed of multiple computing nodes in a local area network where each node is a personal computer equipped with one or several GPU(s)for parallel computing.In this study,the MPI(Message Passing Interface),the OpenMP(Open Multi-Processing)and the CUDA(Compute Unified Device Architecture)technologies are employed to develop the program.It is demonstrated that this designing runs roughly N times faster than that using single GPU when the GPUs within the cluster are of the same type,where N is the total number of the GPUs within the cluster.
