@inproceedings{0d24ddb31247484faabe03f05ce9ac8e,
title = "Amortised deep parameter optimisation of GPGPU work group size for OpenCV",
abstract = "GPGPU (General Purpose computing on Graphics Processing Units) enables massive parallelism by taking advantage of the Single Instruction Multiple Data (SIMD) architecture of the large number of cores found on modern graphics cards. A parameter called local work group size controls how many work items are concurrently executed on a single compute unit. Though critical to the performance, there is no deterministic way to tune it, leaving developers to manual trial and error. This paper applies amortised optimisation to determine the best local work group size for GPGPU implementations of OpenCV template matching feature. The empirical evaluation shows that optimised local work group size can outperform the default value with large effect sizes.",
author = "Jeongju Sohn and Seongmin Lee and Shin Yoo",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG 2016.; 8th International Symposium on Search Based Software Engineering, SSBSE 2016 ; Conference date: 08-10-2016 Through 10-10-2016",
year = "2016",
doi = "10.1007/978-3-319-47106-8_14",
language = "English",
isbn = "9783319471051",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "211--217",
editor = "Federica Sarro and Kalyanmoy Deb",
booktitle = "Search Based Software Engineering - 8th International Symposium, SSBSE 2016, Proceedings",
address = "Germany",
}