Comparison of acceleration the parallel version of the bitonic sort algorithm on the CUDA architecture and MPI standard

Автор: Kadyrov P.A.

Журнал: Мировая наука @science-j

Статья в выпуске: 3 (3), 2017 года.

Бесплатный доступ

This article discusses two implementations of the bitonic sort algorithm in parallel on the CUDA technology and MPI standard. Experiments are conducted for each implementation and compares the results of the work time for identifying best implementation of the algorithm.

Cuda, gpu, mpi, algorithm, bitonic sort, parallel execution, sorting algorithm

Короткий адрес: https://sciup.org/140262799

IDR: 140262799

Статья научная