Open AccessADVANCED FEATURES OF NVIDIA KEPLER ARCHITECTURE AND PARALLEL COMPUTATION PLATFORM CUDA FOR DEVELOPING SCIENTIFIC COMPUTE-INTENSIVE APPLICATIONS
Author(s) -
V.A. Dudnik,
V.I. Kudryavtsev,
S.A. Us,
M.V. Shestakov
Publication year - 2019
Publication title -
problems of atomic science and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.216
H-Index - 17
eISSN - 1562-6016
pISSN - 1682-9344
DOI - 10.46813/2019-121-105
Subject(s) - cuda , computer science , parallel computing , computation , kepler , set (abstract data type) , computer architecture , architecture , fortran , realization (probability) , computational science , instruction set , programming language , mathematics , art , stars , statistics , visual arts , computer vision
The paper describes additional features oered by new Kepler architecture of NVIDIA graphic processors, and their usage for creating high performance programs in a wide range of scientic compute-intensive applications. Recommendations are given for their use at realization of sci-tech computation algorithms by means of graphic processors. New capabilities of the parallel computation platform CUDA are also described, in particular, regarding a set of program development tool extensions for the Fortran, C and C++ languages. The extended capabilities make it possible to minimize the time of application development and to increase the programming productivity.