@inproceedings{a658bfb6c2ef4578b47a5aa37abc71f6,
title = "A locality-aware dynamic thread scheduler for GPGPUs",
abstract = "Modern GPGPUs implement on-chip shared cache to better exploit the data reuse of various general purpose applications. Given the massive amount of concurrent threads in a GPGPU, striking the balance between Data Locality and Load Balance has become a critical design concern. To achieve the best performance, the trade-off between these two factors needs to be performed concurrently. This paper proposes a dynamic thread scheduler which co-optimizes both the data locality and load balance on a GPGPU. The proposed approach is evaluated using three applications with various input datasets. The results show that the proposed approach reduces the overall execution cycles by up to 16% when compared with other approaches concerning only one objective.",
keywords = "Data Locality, GPU, parallel computing",
author = "Huang, {Yu Hao} and Tseng, {Ying Yu} and Kuo, {Hsien Kai} and Yen, {Ta Kan} and Lai, {Bo Cheng Charles}",
year = "2014",
month = sep,
day = "18",
doi = "10.1109/PDCAT.2013.46",
language = "English",
series = "Parallel and Distributed Computing, Applications and Technologies, PDCAT Proceedings",
publisher = "IEEE Computer Society",
pages = "254--258",
editor = "Shi-Jinn Horng",
booktitle = "Parallel and Distributed Computing, Applications and Technologies, PDCAT Proceedings",
address = "美國",
note = "14th International Conference on Parallel and Distributed Computing, Applications and Technologies, PDCAT 2013 ; Conference date: 16-12-2013 Through 18-12-2013",
}