The Use of Functional Programming Library for Parallel Computing on CUDA.

Modern graphics accelerators (GPUs) can significantly speed up the execution of numerical problems. However, porting programs to graphics accelerators is not an easy task, sometimes requiring their almost complete rewriting. CUDA graphics accelerators, thanks to technology developed by NVIDIA, allow one to have a single source code for both conventional processors (CPUs) and CUDA. However, parallelization on shared memory is still done differently and should be specified explicitly. The use of a functional programming library developed by the authors makes it possible to hide the use of one or another parallelization mechanism on shared memory within the library and make the user's source code completely independent of the computing device used (CPU or CUDA). This article shows how this can be done. [ABSTRACT FROM AUTHOR]