cuTranspose is a library to transpose 3D arrays in Nvidia CUDA GPUs. It is written in CUDA C and all its functionality is exposed through C functions. The library is based on the transpositions described in this article: Jose L. Jodra, Ibai Gurrutxaga and Javier Muguerza. "Efficient 3D Transpositions in Graphics Processing Units" International Journal of Parallel Programming, 43:4, pp. 876-891, 2015. Please cite them in your publications if you use cuTranspose.