Array operations are useful in a large number of important scientific codes, such as molecular dynamics, finite-element methods, climate modeling, etc. It is a challenging problem to provide an efficient data distribution for irregular problems. Multi-dimensional (MD) sparse array operations can be used in atmosphere and ocean sciences, image processing, etc., and have been an extensively investigated problem. In our previous work, a data distribution scheme, Encoding-Decoding (ED), was proposed for two-dimensional (2D) sparse arrays. In this paper, ED is extended to be useful for MD sparse arrays first. Then, the performance of ED is compared with that of Send Followed Compress (SFC) and Compress Followed Send (CFS). Both theoretical analysis and experimental tests were conducted and then shown that ED is superior to SFC and CFS for all of evaluated criteria.