NK-GPGPU A GPGPU model for nested kernels

DOI

10.2991/amcce-17.2017.171How to use a DOI?

Keywords

GPGPU; Conceptual Model; Micro-architecture

Abstract

More and more scientific problems are now using GPGPU to solve. However , the existing GPGPU did not give a good solution for the problems such as recursive calls and multiple calls problems. Our proposed NKGPGPU model is a descriptive model that solves the key issues of the NK-GPGPU, including hardware architecture, task organization, task execution, and task scheduling. We also prove the validity of our model by optimizing an existing GPGPU performance prediction model.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - QianLi Xing
AU  - Liang Hu
AU  - Xilong Che
PY  - 2017/03
DA  - 2017/03
TI  - NK-GPGPU A GPGPU model for nested kernels
BT  - Proceedings of the 2017 2nd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 2017)
PB  - Atlantis Press
SP  - 971
EP  - 975
SN  - 2352-5401
UR  - https://doi.org/10.2991/amcce-17.2017.171
DO  - 10.2991/amcce-17.2017.171
ID  - Xing2017/03
ER  -