Gunrock: a high-performance graph processing library on the GPU

By Yangzihao Wang, Andrew A. Davidson, Yuechao Pan, Yuduo Wu, Andy T. Riffel, John Douglas Owens. ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming, 2015

587 citations recorded by the source corpus.

For large-scale graph analytics on the GPU, the irregularity of data access/control flow and the complexity of programming GPUs have been two significant challenges for developing a programmable high-performance graph library. "Gunrock," our high-level bulk-synchronous graph-processing system targeting the GPU, takes a new approach to abstracting GPU graph analytics: rather than designing an abstraction around computation, Gunrock instead implements a novel data-centric abstraction centered on operations on a vertex or edge frontier. Gunrock achieves a balance between performance and expressiveness by coupling high-performance GPU computing primitives and optimization strategies with a high-level programming model that allows programmers to quickly develop new graph primitives with small code size and minimal GPU programming knowledge. We evaluate Gunrock on five graph primitives (BFS, BC, SSSP, CC, and PageRank) and show that Gunrock has on average at least an order of magnitude speedup over Boost and PowerGraph, comparable performance to the fastest GPU hardwired primitives, and better performance than any other GPU high-level graph library.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/923da3bc69c6ed6a2b0b155b6cd759ede373d933

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Hardware and Architecture

Citations in the corpus

HyGCN: A GCN Accelerator with Hybrid Architecture (2020, background): “In this work, we identify that the execution patterns of these two phases are distinct, even almost opposite, which requires separate design requirements.”
Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks. (2019, background): “pone et al., 2017), advanced parallel pattern (Yang et al., 2018) to tiling and reordering (Yang et al., 2011; Baskaran & Bordawekar, 2009) in the context of graph analytics (Ashari et al., 2014; Wang et al., 2016) or scientiﬁc computing applications (LeVeque, 2007), just to name a few. Our work”
PowerLyra: Differentiated Graph Computation and Partitioning on Skewed Graphs (2019, background): “There are also a few systems considering GPU [45, 80, 81], NUMA [100], RDMA [64, 83], stream processing [17, 55, 96], and temporal graphs [27].”
Graphicionado: A high-performance and energy-efficient accelerator for graph analytics (2016, methodology): “GPU-based Graph Processing Frameworks There are a few graph analytics software frameworks and libraries specifically optimized for GPUs; Gunrock [49], MapGraph [14], nvGraph [39], and Enterprise [32] are representative examples.”