research-article

Public Access

Accelerating parallel graph computing with speculation

Authors:

Qing YiAuthors Info & Claims

CF '19: Proceedings of the 16th ACM International Conference on Computing Frontiers

Pages 115 - 124

https://doi.org/10.1145/3310273.3323049

Published: 30 April 2019 Publication History

Abstract

Nowadays distributed graph computing is widely used to process large amount of data on the internet. Communication overhead is a critical factor in determining the overall efficiency of graph algorithms. Through speculative prediction of the content of communications, we develop an optimization technique to significantly reduce the amount of communications needed for a class of graph algorithms. We have evaluated our optimization technique using five graph algorithms, Single-source shortest path, Connected Components, PageRank, Diameter, and Random Walk, on the Amazon EC2 clusters using different graph datasets. Our optimized implementations have reduced communication overhead by 21--93% for these algorithms, while keeping the error rates under 5%.

References

[1]

Apache. 2012. Apache Giraph. http://giraph.apache.org/.

[2]

Apache. 2012. Apache Hama. https://www.hama.com/.

[3]

Ziv Baryossef and Lital Mashiach. 2008. Local approximation of PageRank and reverse PageRank. ACM Conference on Information and Knowledge Management, California, USA.

Digital Library

[4]

Rong Chen, Jiaxin Shi, Yanzhe Chen, and Haibo Chen. 2015. PowerLyra: differentiated graph computation and partitioning on skewed graphs. European Conference on Computer Systems, Bordeaux, France.

Digital Library

[5]

DIMACS. 2006. USA Road Network. http://www.dis.uniroma1.it/challenge9/download.shtml.

[6]

Matthew Gardner, Andrew McNabb, and Kevin Seppi. 2012. A speculative approach to parallelization in particle swarm optimization. Swarm Intelligence 6, 2 (2012), 77--116.

[7]

Joseph E Gonzalez, Yucheng Low, Haijie Gu, Danny Bickson, and Carlos Guestrin. 2012. PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs. Operating Systems Design and Implementation (OSDI), Hollywood, CA.

Digital Library

[8]

Joseph E Gonzalez, Reynold S Xin, Ankur Dave, Daniel Crankshaw, Michael J Franklin, and Ion Stoica. 2014. GraphX: Graph processing in a distributed dataflow framework. Operating Systems Design and Implementation (OSDI), Broomfield, CO.

Digital Library

[9]

Imranul Hoque and Indranil Gupta. 2013. LFGraph: Simple and fast distributed graph analytics. ACM SIGOPS Conference on Timely Results in Operating Systems, PA, USA.

Digital Library

[10]

Hakbeom Jang, Channoh Kim, and Jae W Lee. 2013. Practical speculative parallelization of variable-length decompression algorithms. Languages, Compilers, and Tools for Embedded Systems 48, 5 (2013), 55--64.

Digital Library

[11]

Jeff Kahn, Nathan Linial, Noam Nisan, and Michael E Saks. 1989. On the cover time of random walks on graphs. Journal of Theoretical Probability 2, 1 (1989), 121--128.

[12]

U Kang, Charalampos E Tsourakakis, Ana Paula Appel, Christos Faloutsos, and Jure Leskovec. 2011. HADI: Mining Radii of Large Graphs. ACM Transactions on Knowledge Discovery From Data 5, 2 (2011), 8.

Digital Library

[13]

Zuhair Khayyat, Karim Awara, Amani Alonazi, Hani Jamjoom, Dan Williams, and Panos Kalnis. 2013. Mizan: a system for dynamic load balancing in large-scale graph processing. ACM European Conference on Computer Systems, New York, USA.

Digital Library

[14]

LAW. 2002. Large Graphs. http://law.di.unimi.it/datasets.php.

[15]

Yucheng Low, Joseph E Gonzalez, Aapo Kyrola, Danny Bickson, Carlos Guestrin, and Joseph M Hellerstein. 2010. GraphLab: a new framework for parallel machine learning. Uncertainty in Artificial Intelligence, California, USA.

Digital Library

[16]

Grzegorz Malewicz, Matthew H Austern, Aart JC Bik, James C Dehnert, Ilan Horn, Naty Leiser, and Grzegorz Czajkowski. 2010. Pregel: a system for large-scale graph processing. ACM SIGMOD International Conference on Management of data, Indiana, USA.

Digital Library

[17]

Robert Ryan McCune, Tim Weninger, and Greg Madey. 2015. Thinking like a vertex: a survey of vertex-centric frameworks for large-scale distributed graph processing. ACM Computing Surveys (CSUR) 48, 2 (2015), 1--39.

Digital Library

[18]

Flajolet Philippe and Martin G. Nigel. 1985. Probabilistic Counting Algorithms for Data Base Applications. J. Comput. System Sci. 31, 2 (1985), 182--209.

Digital Library

[19]

Semih Salihoglu and Jennifer Widom. 2013. Gps: A graph processing system. International Conference on Scientific and Statistical Database Management, Edinburgh, Scotland, UK.

Digital Library

[20]

Atish Das Sarma, Sreenivas Gollapudi, and Rina Panigrahy. 2008. Estimating PageRank on graph streams. Symposium on Principles of Database Systems, Vancouver, Canada.

Digital Library

[21]

Zechao Shang and Jeffrey Xu Yu. 2014. Auto-approximation of graph computing. Proceedings of the VLDB Endowment 7, 14 (2014), 1833--1844.

Digital Library

[22]

Stanford. 2009. Large Network Dataset. https://snap.stanford.edu/.

[23]

Isabelle Stanton and Gabriel Kliot. 2012. Streaming graph partitioning for large distributed graphs. ACM SIGKDD international conference on Knowledge discovery and data mining, Beijing, China.

Digital Library

[24]

Charalampos Tsourakakis, Christos Gkantsidis, Bozidar Radunovic, and Milan Vojnovic. 2014. Fennel: Streaming graph partitioning for massive scale graphs. ACM international conference on Web search and data mining, New York, USA.

Digital Library

[25]

Leslie G Valiant. 1990. A bridging model for parallel computation. Commun. ACM 33, 8 (1990), 103--111.

Digital Library

[26]

Luis M Vaquero, Felix Cuadrado, Dionysios Logothetis, and Claudio Martella. 2014. Adaptive partitioning for large-scale dynamic graphs. International Conference on Distributed Computing Systems (ICDCS), Madrid, Spain.

Digital Library

[27]

Chenning Xie, Rong Chen, Haibing Guan, Binyu Zang, and Haibo Chen. 2015. Sync or async: Time to fuse for distributed graph-parallel computation. ACM Sigplan Symposium on Principles and Practice of Parallel Programming, California, USA.

Digital Library

[28]

Raphael Yuster. 2012. Approximate shortest paths in weighted graphs. J. Comput. System Sci. 78, 2 (2012), 632--637.

Digital Library

[29]

Yanfeng Zhang, Qixin Gao, Lixin Gao, and Cuirong Wang. 2014. Maiter: an asynchronous graph processing framework for delta-based accumulative iterative computation. IEEE Transactions on Parallel and Distributed Systems 25, 8 (2014), 2091--2100.

Cited By

Ji SZhao YLi Y(2020)Performance prediction for distributed graph computingConcurrency and Computation: Practice and Experience10.1002/cpe.596134:12Online publication date: 12-Aug-2020
https://doi.org/10.1002/cpe.5961
Ji SZhao YLi Y(2019)Performance Prediction for Distributed Graph Computing2019 International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS)10.1109/HPBDIS.2019.8735449(7-13)Online publication date: May-2019
https://doi.org/10.1109/HPBDIS.2019.8735449

Index Terms

Accelerating parallel graph computing with speculation
1. Computing methodologies
  1. Distributed computing methodologies

Recommendations

GraphBench: A Benchmark Suite for Graph Computing Systems
Benchmarking, Measuring, and Optimizing
Abstract
In the Big data and IoT era, graph data processing is widely used. The graph data is a kind of structural data that defined entities as vertices and described dependencies between different entities as edges. Today, a lot of graph computing ...
Iterative Hypergraph Computation Based on Hyperedge-Connected Graphs
Web and Big Data
Abstract
A hypergraph allows a hyperedge to connect arbitrary number of vertices, which can be used to capture the complex and high-order relationships. By analyzing the iterative processing on bipartite graphs, a method of converting the original ...
Accelerating breadth-first graph search on a single server by dynamic edge trimming
Abstract
Breadth-first graph search (a.k.a., BFS) is one of the typical in-memory computing models with complicated and frequent memory accesses. Existing single-server graph computing systems fail to take advantage of access pattern of BFS for ...
Highlights
- A new approach that performs breadth-first graph search efficiently on a single server.

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

CF '19: Proceedings of the 16th ACM International Conference on Computing Frontiers

April 2019

414 pages

ISBN:9781450366854

DOI:10.1145/3310273

General Chairs:
Francesca Palumbo
Universit`a degli Studi di Sassari, IT
,
Michela Becchi
North Carolina State University
,
Program Chairs:
Martin Schulz
Technical University of Munich, DE
,
Kento Sato
RIKEN R-CCS, JP

Copyright © 2019 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGMICRO: ACM Special Interest Group on Microarchitectural Research and Processing

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 30 April 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

National Key R&D Program of China
National Science Foundation of USA

Conference

CF '19

Sponsor:

SIGMICRO

CF '19: Computing Frontiers Conference

April 30 - May 2, 2019

Alghero, Italy

Acceptance Rates

Overall Acceptance Rate 273 of 785 submissions, 35%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
279
Total Downloads

Downloads (Last 12 months)41
Downloads (Last 6 weeks)2

Reflects downloads up to 15 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Ji SZhao YLi Y(2020)Performance prediction for distributed graph computingConcurrency and Computation: Practice and Experience10.1002/cpe.596134:12Online publication date: 12-Aug-2020
https://doi.org/10.1002/cpe.5961
Ji SZhao YLi Y(2019)Performance Prediction for Distributed Graph Computing2019 International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS)10.1109/HPBDIS.2019.8735449(7-13)Online publication date: May-2019
https://doi.org/10.1109/HPBDIS.2019.8735449

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents