Multicore triangle computations without tuning
13 Apr 2015-pp 149-160
TL;DR: This paper describes the design and implementation of simple and fast multicore parallel algorithms for exact, as well as approximate, triangle counting and other triangle computations that scale to billions of nodes and edges, and is much faster than existing parallel approximate triangle counting implementations.
Abstract: Triangle counting and enumeration has emerged as a basic tool in large-scale network analysis, fueling the development of algorithms that scale to massive graphs. Most of the existing algorithms, however, are designed for the distributed-memory setting or the external-memory setting, and cannot take full advantage of a multicore machine, whose capacity has grown to accommodate even the largest of real-world graphs.
Citations
More filters
23 Feb 2013
TL;DR: This paper presents a lightweight graph processing framework that is specific for shared-memory parallel/multicore machines, which makes graph traversal algorithms easy to write and significantly more efficient than previously reported results using graph frameworks on machines with many more cores.
Abstract: There has been significant recent interest in parallel frameworks for processing graphs due to their applicability in studying social networks, the Web graph, networks in biology, and unstructured meshes in scientific simulation. Due to the desire to process large graphs, these systems have emphasized the ability to run on distributed memory machines. Today, however, a single multicore server can support more than a terabyte of memory, which can fit graphs with tens or even hundreds of billions of edges. Furthermore, for graph algorithms, shared-memory multicores are generally significantly more efficient on a per core, per dollar, and per joule basis than distributed memory systems, and shared-memory algorithms tend to be simpler than their distributed counterparts.In this paper, we present a lightweight graph processing framework that is specific for shared-memory parallel/multicore machines, which makes graph traversal algorithms easy to write. The framework has two very simple routines, one for mapping over edges and one for mapping over vertices. Our routines can be applied to any subset of the vertices, which makes the framework useful for many graph traversal algorithms that operate on subsets of the vertices. Based on recent ideas used in a very fast algorithm for breadth-first search (BFS), our routines automatically adapt to the density of vertex sets. We implement several algorithms in this framework, including BFS, graph radii estimation, graph connectivity, betweenness centrality, PageRank and single-source shortest paths. Our algorithms expressed using this framework are very simple and concise, and perform almost as well as highly optimized code. Furthermore, they get good speedups on a 40-core machine and are significantly more efficient than previously reported results using graph frameworks on machines with many more cores.
816 citations
26 Jun 2017
TL;DR: In this paper, the authors investigate the applicability of push-pull dichotomy to various algorithms and its impact on complexity, performance, and the amount of used locks, atomics, and reads/writes.
Abstract: We reduce the cost of communication and synchronization in graph processing by analyzing the fastest way to process graphs: pushing the updates to a shared state or pulling the updates to a private state. We investigate the applicability of this push-pull dichotomy to various algorithms and its impact on complexity, performance, and the amount of used locks, atomics, and reads/writes. We consider 11 graph algorithms, 3 programming models, 2 graph abstractions, and various families of graphs. The conducted analysis illustrates surprising differences between push and pull variants of different algorithms in performance, speed of convergence, and code complexity; the insights are backed up by performance data from hardware counters. We use these findings to illustrate which variant is faster for each algorithm and to develop generic strategies that enable even higher speedups. Our insights can be used to accelerate graph processing engines or libraries on both massively-parallel shared-memory machines as well as distributed-memory systems.
124 citations
25 May 2015
TL;DR: This work presents a new primitive, masked matrix multiplication, that can be beneficial especially for the enumeration case and provides results from an initial implementation for the counting case along with various optimizations for communication reduction and load balance.
Abstract: Triangle counting and enumeration are important kernels that are used to characterize graphs. They are also used to compute important statistics such as clustering coefficients. We provide a simple exact algorithm that is based on operations on sparse adjacency matrices. By parallelizing the individual sparse matrix operations, we achieve a parallel algorithm for triangle counting. The algorithm is generalizable to triangle enumeration by modifying the semiring that underlies the matrix algebra. We present a new primitive, masked matrix multiplication, that can be beneficial especially for the enumeration case. We provide results from an initial implementation for the counting case along with various optimizations for communication reduction and load balance.
124 citations
Cites methods from "Multicore triangle computations wit..."
...Breakdown of time spent by (a) Triangle-basic and (b) Triangle-masked-bloom algorithms for different input graphs on 512 cores of Edison. such as PATRIC [20], which uses MPI, and the multicore implementation of Shun and Tangwongsan [21]....
[...]
...such as PATRIC [20], which uses MPI, and the multicore implementation of Shun and Tangwongsan [21]....
[...]
11 Jul 2018
TL;DR: It is shown that theoretically-efficient parallel graph algorithms can scale to the largest publicly-available graphs using a single machine with a terabyte of RAM, processing them in minutes.
Abstract: There has been significant recent interest in parallel graph processing due to the need to quickly analyze the large graphs available today. Many graph codes have been designed for distributed memory or external memory. However, today even the largest publicly-available real-world graph (the Hyperlink Web graph with over 3.5 billion vertices and 128 billion edges) can fit in the memory of a single commodity multicore server. Nevertheless, most experimental work in the literature report results on much smaller graphs, and the ones for the Hyperlink graph use distributed or external memory. Therefore, it is natural to ask whether we can efficiently solve a broad class of graph problems on this graph in memory. This paper shows that theoretically-efficient parallel graph algorithms can scale to the largest publicly-available graphs using a single machine with a terabyte of RAM, processing them in minutes. We give implementations of theoretically-efficient parallel algorithms for 13 important graph problems. We also present the optimizations and techniques that we used in our implementations, which were crucial in enabling us to process these large graphs quickly. We show that the running times of our implementations outperform existing state-of-the-art implementations on the largest real-world graphs. For many of the problems that we consider, this is the first time they have been solved on graphs at this scale. We provide a publicly-available benchmark suite containing our implementations.
100 citations
Cites methods from "Multicore triangle computations wit..."
...for TC on our larger graphs as the single-threaded times took too long due to the algorithm performing O(m3/2)work. There are a number of experimental papers that consider multicore triangle counting [1, 54, 72, 77, 112, 119]. We implement the algorithm from [119], and adapted it to work on compressed graphs. We note that in our experiments we intersect directed adjacency lists sequentially, as there was sufficient parall...
[...]
23 Aug 2017
TL;DR: The results show that on a single GPU, Gunrock has on average at least an order of magnitude speedup over Boost and PowerGraph, comparable performance to the fastest GPU hardwired primitives and CPU shared-memory graph libraries, and better performance than any other GPU high-level graph library.
Abstract: For large-scale graph analytics on the GPU, the irregularity of data access and control flow, and the complexity of programming GPUs, have presented two significant challenges to developing a programmable high-performance graph library. “Gunrock,” our graph-processing system designed specifically for the GPU, uses a high-level, bulk-synchronous, data-centric abstraction focused 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 characterize the performance of various optimization strategies and evaluate Gunrock’s overall performance on different GPU architectures on a wide range of graph primitives that span from traversal-based algorithms and ranking algorithms, to triangle counting and bipartite-graph-based algorithms. The results show that on a single GPU, Gunrock has on average at least an order of magnitude speedup over Boost and PowerGraph, comparable performance to the fastest GPU hardwired primitives and CPU shared-memory graph libraries, such as Ligra and Galois, and better performance than any other GPU high-level graph library.
99 citations
Cites background or methods from "Multicore triangle computations wit..."
...’s multicore CPU implementation [27], and Shun and Tangwongsan’s multicore CPU implementation [72]....
[...]
...-GPU”), Shun and Tangwongsan’s 40-core CPU implementation [72] (“Shun and Tangwongsan-T40”), and Green et al....
[...]
References
More filters
TL;DR: Simple models of networks that can be tuned through this middle ground: regular networks ‘rewired’ to introduce increasing amounts of disorder are explored, finding that these systems can be highly clustered, like regular lattices, yet have small characteristic path lengths, like random graphs.
Abstract: Networks of coupled dynamical systems have been used to model biological oscillators, Josephson junction arrays, excitable media, neural networks, spatial games, genetic control networks and many other self-organizing systems. Ordinarily, the connection topology is assumed to be either completely regular or completely random. But many biological, technological and social networks lie somewhere between these two extremes. Here we explore simple models of networks that can be tuned through this middle ground: regular networks 'rewired' to introduce increasing amounts of disorder. We find that these systems can be highly clustered, like regular lattices, yet have small characteristic path lengths, like random graphs. We call them 'small-world' networks, by analogy with the small-world phenomenon (popularly known as six degrees of separation. The neural network of the worm Caenorhabditis elegans, the power grid of the western United States, and the collaboration graph of film actors are shown to be small-world networks. Models of dynamical systems with small-world coupling display enhanced signal-propagation speed, computational power, and synchronizability. In particular, infectious diseases spread more easily in small-world networks than in regular lattices.
39,297 citations
"Multicore triangle computations wit..." refers background in this paper
...The local clustering coefficient [60] for a vertex v is defined to be the number of triangles incident on v divided by d(v)(d(v)−1)/2 (the number of potential triangles incident on v)....
[...]
TL;DR: Developments in this field are reviewed, including such concepts as the small-world effect, degree distributions, clustering, network correlations, random graph models, models of network growth and preferential attachment, and dynamical processes taking place on networks.
Abstract: Inspired by empirical studies of networked systems such as the Internet, social networks, and biological networks, researchers have in recent years developed a variety of techniques and models to help us understand or predict the behavior of these systems. Here we review developments in this field, including such concepts as the small-world effect, degree distributions, clustering, network correlations, random graph models, models of network growth and preferential attachment, and dynamical processes taking place on networks.
17,647 citations
Additional excerpts
...…on directed graphs • Numerous applications… • Social network analysis, Web structure, spam detection, outlier detection, dense subgraph mining, 3-way database joins, etc. 2 Triangle Computations Alice Bob Carol David Eve Fred Greg Hannah ✔ ✔ ✔ Count = 3 Need fast triangle computation…...
[...]
26 Apr 2010
TL;DR: In this paper, the authors have crawled the entire Twittersphere and found a non-power-law follower distribution, a short effective diameter, and low reciprocity, which all mark a deviation from known characteristics of human social networks.
Abstract: Twitter, a microblogging service less than three years old, commands more than 41 million users as of July 2009 and is growing fast. Twitter users tweet about any topic within the 140-character limit and follow others to receive their tweets. The goal of this paper is to study the topological characteristics of Twitter and its power as a new medium of information sharing.We have crawled the entire Twitter site and obtained 41.7 million user profiles, 1.47 billion social relations, 4,262 trending topics, and 106 million tweets. In its follower-following topology analysis we have found a non-power-law follower distribution, a short effective diameter, and low reciprocity, which all mark a deviation from known characteristics of human social networks [28]. In order to identify influentials on Twitter, we have ranked users by the number of followers and by PageRank and found two rankings to be similar. Ranking by retweets differs from the previous two rankings, indicating a gap in influence inferred from the number of followers and that from the popularity of one's tweets. We have analyzed the tweets of top trending topics and reported on their temporal behavior and user participation. We have classified the trending topics based on the active period and the tweets and show that the majority (over 85%) of topics are headline news or persistent news in nature. A closer look at retweets reveals that any retweeted tweet is to reach an average of 1,000 users no matter what the number of followers is of the original tweet. Once retweeted, a tweet gets retweeted almost instantly on next hops, signifying fast diffusion of information after the 1st retweet.To the best of our knowledge this work is the first quantitative study on the entire Twittersphere and information diffusion on it.
6,108 citations
08 Oct 2012
TL;DR: This paper describes the challenges of computation on natural graphs in the context of existing graph-parallel abstractions and introduces the PowerGraph abstraction which exploits the internal structure of graph programs to address these challenges.
Abstract: Large-scale graph-structured computation is central to tasks ranging from targeted advertising to natural language processing and has led to the development of several graph-parallel abstractions including Pregel and GraphLab. However, the natural graphs commonly found in the real-world have highly skewed power-law degree distributions, which challenge the assumptions made by these abstractions, limiting performance and scalability.In this paper, we characterize the challenges of computation on natural graphs in the context of existing graph-parallel abstractions. We then introduce the PowerGraph abstraction which exploits the internal structure of graph programs to address these challenges. Leveraging the PowerGraph abstraction we introduce a new approach to distributed graph placement and representation that exploits the structure of power-law graphs. We provide a detailed analysis and experimental evaluation comparing PowerGraph to two popular graph-parallel systems. Finally, we describe three different implementation strategies for PowerGraph and discuss their relative merits with empirical evaluations on large-scale real-world problems demonstrating order of magnitude gains.
1,710 citations
"Multicore triangle computations wit..." refers methods in this paper
...• Sequential algorithms for exact counting/listing • Naïve algorithm of trying all triplets O(V3) work • Node-iterator algorithm [Schank] O(VE) work • Edge-iterator algorithm [Itai-Rodeh] O(VE) work • Tree-lister [Itai-Rodeh], forward/compact-forward [Schank-Wagner, Lapaty] O(E1....
[...]
TL;DR: This paper gives the first provably good work-stealing scheduler for multithreaded computations with dependencies, and shows that the expected time to execute a fully strict computation on P processors using this scheduler is 1:1.
Abstract: This paper studies the problem of efficiently schedulling fully strict (i.e., well-structured) multithreaded computations on parallel computers. A popular and practical method of scheduling this kind of dynamic MIMD-style computation is “work stealing,” in which processors needing work steal computational threads from other processors. In this paper, we give the first provably good work-stealing scheduler for multithreaded computations with dependencies.Specifically, our analysis shows that the expected time to execute a fully strict computation on P processors using our work-stealing scheduler is T1/P + O(T ∞ , where T1 is the minimum serial execution time of the multithreaded computation and (T ∞ is the minimum execution time with an infinite number of processors. Moreover, the space required by the execution is at most S1P, where S1 is the minimum serial space requirement. We also show that the expected total communication of the algorithm is at most O(PT ∞( 1 + nd)Smax), where Smax is the size of the largest activation record of any thread and nd is the maximum number of times that any thread synchronizes with its parent. This communication bound justifies the folk wisdom that work-stealing schedulers are more communication efficient than their work-sharing counterparts. All three of these bounds are existentially optimal to within a constant factor.
1,202 citations