@inproceedings{Castro-Penna-ICCS:2017,
abstract = {The input workload of an irregular application must be evenly distributed among its threads to enable cutting-edge performance. To address this need in OpenMP, several loop scheduling strategies were proposed. While having this ever-increasing number of strategies at disposal is helpful, it has become a non-trivial task to select the best one for a particular application. Nevertheless, this challenge becomes easier to be tackled when existing scheduling strategies are extensively evaluated. Therefore, in this paper, we present a performance and scalability evaluation of the recently-proposed loop scheduling strategy named Smart Round-Robin (SRR). To deliver a comprehensive analysis, we coupled a synthetic kernel benchmarking technique with several rigorous statistical tools, and considered OpenMP's Static and Dynamic loop schedulers as our baselines. Our results unveiled that $\backslash${\{}SRR$\backslash${\}} performs better on irregular applications with symmetric workloads and coarse-grained parallelization, achieving up to 1.9x and 1.5x speedup over OpenMP's Static and Dynamic schedulers, respectively.},
address = {Z{\"{u}}rich, Switzerland},
author = {Penna, Pedro H. and Inacio, Eduardo C. and Castro, M{\'{a}}rcio and Plentz, Patricia D. M. and Freitas, Henrique C. and Broquedis, Fran{\c{c}}ois and M{\'{e}}haut, Jean-Fran{\c{c}}ois},
booktitle = {International Conference on Computational Science (ICCS)},
doi = {10.1016/j.procs.2017.05.222},
issn = {1877-0509},
pages = {255--264},
publisher = {Elsevier},
title = {{Assessing the Performance of the SRR Loop Scheduler with Irregular Workloads}},
url = {http://www.sciencedirect.com/science/article/pii/S187705091730830X},
volume = {108},
year = {2017}
}