@inproceedings{4c82af6fbaac4074b84e27e0726802a1,
title = "Update on triangle counting on GPU",
abstract = "This work presents an update to the triangle-counting portion of the subgraph isomorphism static graph challenge. This work is motivated by a desire to understand the impact of CUDA unified memory on the triangle-counting problem. First, CUDA unified memory is used to overlap reading large graph data from disk with graph data structures in GPU memory. Second, we use CUDA unified memory hints to solve multi-GPU performance scaling challenges present in our last submission. Finally, we improve the single-GPU kernel performance from our past submission by introducing a work-stealing dynamic algorithm GPU kernel with persistent threads, which makes performance adaptive for large graphs without requiring a graph analysis phase.",
keywords = "GPU, Graph algorithms, Triangle counting",
author = "Carl Pearson and Mohammad Almasri and Omer Anjum and Mailthody, {Vikram S.} and Zaid Qureshi and Rakesh Nagi and Jinjun Xiong and Hwu, {Wen Mei}",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE High Performance Extreme Computing Conference, HPEC 2019 ; Conference date: 24-09-2019 Through 26-09-2019",
year = "2019",
month = sep,
doi = "10.1109/HPEC.2019.8916547",
language = "English (US)",
series = "2019 IEEE High Performance Extreme Computing Conference, HPEC 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE High Performance Extreme Computing Conference, HPEC 2019",
address = "United States",
}