A Synchronization Mechanism between CUDA Blocks for GPU

DOI

10.2991/caai-17.2017.56How to use a DOI?

Keywords

GPU; synchronization mechanism; SSSP; parallel computing; delta-stepping; CUDA

Abstract

GPU(Graphic Processing Unit) provides a promising solution with massive threads and its advantage is high performance computing. The emergence of CUDA(Compute Unified Device Architecture) opens the door of using GPU's powerful computing power. However, because of the limitation of CUDA itself, direct communication is not supported between SMs(streaming multiprocessors) on GPU. It is time-consuming by atomic operation or barrier synchronization. A synchronization mechanism has been proposed in this paper, that is, on the premise of result available, the times of kernel launched should be reduced. Each kernel launched, it should be computed enough on GPU, the results back to the CPU. Based on SSSP, the validity of this method is illustrated by delta-stepping. For facebook dataset, compared with atomic operation, the speedup ratio is about 1.8. For New York map dataset, compared with atomic operation and barrier synchronization, the speedup ratio is about 9.3 and 1.7 separately.

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  - Bingru Wang
AU  - Changyou Zhang
AU  - Feng Wang
AU  - Jun Feng
PY  - 2017/06
DA  - 2017/06
TI  - A Synchronization Mechanism between CUDA Blocks for GPU
BT  - Proceedings of the 2017 2nd International Conference on Control, Automation and Artificial Intelligence (CAAI 2017)
PB  - Atlantis Press
SP  - 251
EP  - 254
SN  - 1951-6851
UR  - https://doi.org/10.2991/caai-17.2017.56
DO  - 10.2991/caai-17.2017.56
ID  - Wang2017/06
ER  -