Murom, Vladimir, Russian Federation
In this paper is presented an extended algorithm of audio streams mixing for computations on graphic processors which combines many stages of mixing by means of twopass rendering use which reduces considerably switching time between buffers. By the method of experimental computer com-parative researches was carried out the assessment of the algorithm developed productivity. The results of investigations have shown that the application of the algorithm developed results in computation productivity increase up to six times.
GPGPPU, parallel computations, heterogeneous computer systems, graphic processors, audio data mixing
1. Lindholm, Е. NVIDIA Tesla: A unified graphics and computing architecture / E. Lindholm, J. Nick-olls, S. Oberman, J. Montrym. IEEE Micro. – 2008. – 28(2). – С. 39-55.
2. Luebke, D. GPGPU: general purpose computation on graphics hardware / D. Luebke, M. Harris, J. Kr´uger, T. Purcell, N. Govindaraju, I. Buck, C. Woolley, A. Lefohn // In SIGGRAPH ´04: ACM SIGGRAPH 2004 Course Notes, New York, USA. – 2004. – С. 33.
3. Kolpakov, А.А. Optimization of genetic algorithms using computations on graphic processors by example of problem of zero bit vectors / А.А. Kolpakov // Information Systems in Technology. - 2013. – №2(76). – pp. 22-28.
4. Kolpakov, А.А. Theoretical assessment of increase in efficiency of computation system at use of some computation devices / А.А. Kolpakov // In the World of Scientific Discoveries. - 2012. – №1. – pp. 206-209.
