TRUST: Triangle Counting Reloaded on GPUs

arXiv2103.08053MaRDI QIDQ6362836

Sheng Zhong, Hang Liu, Zhibin Wang, Adolfy Hoisie, Bolong Zheng, Caiwen Ding, Chen Tian, Lingda Li, Santosh Pandey, Xiaoye Li, Dong Li

Publication date: 14 March 2021

Abstract: Triangle counting is a building block for a wide range of graph applications. Traditional wisdom suggests that i) hashing is not suitable for triangle counting, ii) edge-centric triangle counting beats vertex-centric design, and iii) communication-free and workload balanced graph partitioning is a grand challenge for triangle counting. On the contrary, we advocate that i) hashing can help the key operations for scalable triangle counting on Graphics Processing Units (GPUs), i.e., list intersection and graph partitioning, ii)vertex-centric design reduces both hash table construction cost and memory consumption, which is limited on GPUs. In addition, iii) we exploit graph and workload collaborative, and hashing-based 2D partitioning to scale vertex-centric triangle counting over 1,000 GPUswith sustained scalability. In this work, we present TRUST which performs triangle counting with the hash operation and vertex-centric mechanism at the core. To the best of our knowledge, TRUSTis the first work that achieves over one trillion Traversed Edges Per Second (TEPS) rate for triangle counting.

Has companion code repository: https://github.com/wzbxpy/TRUST

This page was built for publication: TRUST: Triangle Counting Reloaded on GPUs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6362836)