Work‐efficient parallel union‐find

Simsiri, Natcha; Tangwongsan, Kanat; Tirthapura, Srikanta

doi:10.1002/cpe.4333

Cited by 9 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When adding v to λ, we check ∀ρ ∈ λ which ρ ∩ v > 0 and split those ρ into ρ v and ρ v ′ . In order to remove v from λ it's normal to keep a union-find data structure [6], however, we instead incrementally store λ, λ ⊢ M, M ∈ (U i ; 1 ≤ i ≤ j); 1 < j < U which collectively form Λ. This approach scales well because of some domain specific simplifications we can make to Λ.…”

Section: A Bottom-up Attempt At Counting Unreachable Diagramsmentioning

confidence: 99%

Counting Unreachable Single-Side Pawn Diagrams with Limitless Captures

McDonagh¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

Section: A Bottom-up Attempt At Counting Unreachable Diagramsmentioning

confidence: 99%

Counting Unreachable Single-Side Pawn Diagrams with Limitless Captures

McDonagh¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Incremental Connectivity. As many real-world graphs are being updated frequently, many connectivity algorithms have been proposed for dynamic graphs [1,28,30,64,76,80]. Many of our algorithms are a natural fit for the incremental setting, where edges are inserted but not deleted.…”

Section: Gconn Frameworkmentioning

confidence: 99%

Exploring the Design Space of Static and Incremental Graph Connectivity Algorithms on GPUs

Hong

Dhulipala

Shun

2020

Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques

View full text Add to dashboard Cite

Connected components and spanning forest are fundamental graph algorithms due to their use in many important applications, such as graph clustering and image segmentation. GPUs are an ideal platform for graph algorithms due to their high peak performance and memory bandwidth. While there exist several GPU connectivity algorithms in the literature, many design choices have not yet been explored. In this paper, we explore various design choices in GPU connectivity algorithms, including sampling, linking, and tree compression, for both the static as well as the incremental setting. Our various design choices lead to over 300 new GPU implementations of connectivity, many of which outperform state-ofthe-art. We present an experimental evaluation, and show that we achieve an average speedup of 2.47x speedup over existing static algorithms. In the incremental setting, we achieve a throughput of up to 48.23 billion edges per second. Compared to state-of-the-art CPU implementations on a 72-core machine, we achieve a speedup of 8.26-14.51x for static connectivity and 1.85-13.36x for incremental connectivity using a Tesla V100 GPU.

show abstract

“…Incremental Connectivity. Due to the frequency of updates to graphs, various parallel streaming algorithms for connected components have been developed [1,32,37,72,86,92]. Motivated by this, the ConnectIt framework supports a combination of edge insertions and connectivity queries in the graph.…”

Section: Connectit Overviewmentioning

confidence: 99%

“…Their algorithm also supports edge deletions, which makes it more general than our algorithms. As far as we know, the only existing parallel algorithm designed for incremental connectivity is by Simsiri et al [92], but unfortunately we were unable to obtain the code from the authors.…”

Section: Streaming Parallel Graph Connectivitymentioning

confidence: 99%

ConnectIt

Dhulipala¹,

Hong²,

Shun³

2020

Proc. VLDB Endow.

View full text Add to dashboard Cite

Connected components is a fundamental kernel in graph applications. The fastest existing multicore algorithms for solving graph connectivity are based on some form of edge sampling and/or linking and compressing trees. However, many combinations of these design choices have been left unexplored. In this paper, we design the ConnectIt framework, which provides different sampling strategies as well as various tree linking and compression schemes. ConnectIt enables us to obtain several hundred new variants of connectivity algorithms, most of which extend to computing spanning forest. In addition to static graphs, we also extend ConnectIt to support mixes of insertions and connectivity queries in the concurrent setting. We present an experimental evaluation of ConnectIt on a 72-core machine, which we believe is the most comprehensive evaluation of parallel connectivity algorithms to date. Compared to a collection of state-of-the-art static multicore algorithms, we obtain an average speedup of 12.4x (2.36x average speedup over the fastest existing implementation for each graph). Using ConnectIt, we are able to compute connectivity on the largest publicly-available graph (with over 3.5 billion vertices and 128 billion edges) in under 10 seconds using a 72-core machine, providing a 3.1x speedup over the fastest existing connectivity result for this graph, in any computational setting. For our incremental algorithms, we show that our algorithms can ingest graph updates at up to several billion edges per second. To guide the user in selecting the best variants in ConnectIt for different situations, we provide a detailed analysis of the different strategies. Finally, we show how the techniques in ConnectIt can be used to speed up two important graph applications: approximate minimum spanning forest and SCAN clustering.

show abstract

Work‐efficient parallel union‐find

Cited by 9 publications

References 24 publications

Counting Unreachable Single-Side Pawn Diagrams with Limitless Captures

Counting Unreachable Single-Side Pawn Diagrams with Limitless Captures

Exploring the Design Space of Static and Incremental Graph Connectivity Algorithms on GPUs

ConnectIt

Contact Info

Product

Resources

About