Application of the opportunities of tool system ”CUDA” for graphic processors programming in scientific and technical calculation tasks

摘要

The opportunities of technology CUDA (Compute Unified Device Architecture - the unified hardware-software decisionudfor parallel calculations on GPU)of the company NVIDIA were described. The basic differences of the programmingudlanguage ”C” for GPU from ”usual” language ”C” were selected. The examples of CUDA usage for accelerationudof development of applications and realization of algorithms of scientific and technical calculations were given whichudare carried out by the means of graphic processors (GPGPU) of accelerators GeForce of the eighth generation. Theudrecommendations on optimization of the programs using GPU were resulted.