Open AccessProgramming in CUDA for Kepler and Maxwell Architecture
Author(s) -
Esteban Clua,
Marcelo Zamith
Publication year - 2015
Publication title -
revista de informática teórica e aplicada
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.11
H-Index - 1
eISSN - 2175-2745
pISSN - 0103-4308
DOI - 10.22456/2175-2745.56384
Subject(s) - cuda , kepler , computer science , architecture , parallel computing , general purpose computing on graphics processing units , parallelism (grammar) , computational science , computer architecture , computer graphics (images) , graphics , art , stars , visual arts , computer vision
Since the first version of CUDA was launch, many improvements were made in GPU computing. Every new CUDA version included important novel features, turning this architecture more and more closely related to a typical parallel High Performance Language. This tutorial will present the GPU architecture and CUDA principles, trying to conceptualize novel features included by NVIDIA, such as dynamics parallelism, unified memory and concurrent kernels. This text also includes some optimization remarks for CUDA programs.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom