SIMD-реализация алгоритма SAXPY на GPU

С. Ю. Скрупский, Р. К. Кудерметов


Research of architecture of kernel CPU and GPU is executed. Algorithm SAXPY on GPU is realised. Dependences of the performance time of algorithm on CPU and GPU from the sizes of vectors are received. The conclusion is drawn on expediency of application GPU for SIMD–calculations


CPU; GPU; SAXPY; core; architecture; block; thread


Берилло А. NVIDIA CUDA — неграфические вычисления на графических процессорах / А. Берилло. // – 2008. - №4. –с. 18-25.

NVIDIA Corporation. NVIDIA CUDA Compute Unified Device Architecture Programming Guide. Ver 2.1. / NVIDIA Corporation. – [S.I.] : NVIDIA, 2008. – 111 p.

GOST Style Citations

Copyright (c) 2014 С. Ю. Скрупский, Р. К. Кудерметов

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

ISSN (print) 1729-3774, ISSN (on-line) 1729-4061