A GPU Implementation of Computing Euclidean Distance Map with Efficient Memory Access

摘要

Recent Graphics Processing Units (GPUs), which have many processing units, can be used for general purpose parallel computation. To utilize the powerful computing ability, GPUs are widely used for general purpose processing. Since GPUs have very high memory bandwidth, the performance of GPUs greatly depends on memory access. The main contribution of this paper is to present a GPU implementation of computing Euclidean Distance Map (EDM) with efficient memory access. Given a 2-D binary image, EDM is a 2-D array of the same size such that each element is storing the Euclidean distance to the nearest black pixel. In the proposed GPU implementation, we have considered many programming issues of the GPU system such as coalescing access of global memory, shared memory bank conflicts and partition camping. In practice, we have implemented our parallel algorithm in the following two modern GPU systems: Tesla C1060 and GTX 480, respectively. The experimental results have shown that, for an input binary image with size of $9216times 9216$, our implementation can achieve a speedup factor of 52 over the sequential algorithm implementation.