Skywalker: Efficient Alias-Method-Based Graph Sampling and Random Walk on GPUs

Graph sampling and random walk operations, capturing the structural properties of graphs, are playing an important role today as we cannot directly adopt computing-intensive algorithms on large-scale graphs. Existing system frameworks for these tasks are not only spatially and temporally inefficient...

Full description

Saved in:
Bibliographic Details
Published in:2021 30th International Conference on Parallel Architectures and Compilation Techniques (PACT) pp. 304 - 317
Main Authors: Wang, Pengyu, Li, Chao, Wang, Jing, Wang, Taolei, Zhang, Lu, Leng, Jingwen, Chen, Quan, Guo, Minyi
Format: Conference Proceeding
Language:English
Published: IEEE 01.09.2021
Subjects:
Engines
Graph sampling
graphics processing unit
Graphics processing units
Heuristic algorithms
Memory management
Parallel algorithms
Parallel architectures
random walk
Task analysis
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Graph sampling and random walk operations, capturing the structural properties of graphs, are playing an important role today as we cannot directly adopt computing-intensive algorithms on large-scale graphs. Existing system frameworks for these tasks are not only spatially and temporally inefficient, but many also lead to biased results. This paper presents Skywalker, a high-throughput, quality-preserving random walk and sampling framework based on GPUs. Skywalker makes three key contributions: first, it takes the first step to realize efficient biased sampling with the alias method on a GPU. Second, it introduces well-crafted load-balancing techniques to effectively utilize the massive parallelism of GPUs. Third, it accelerates alias table construction and reduce the GPU memory requirement with efficient memory management scheme. We show that Skywalker greatly outperforms the state-of-the-art CPU-based and GPU-based baselines, in a wide spectrum of workload scenarios.
AbstractList Graph sampling and random walk operations, capturing the structural properties of graphs, are playing an important role today as we cannot directly adopt computing-intensive algorithms on large-scale graphs. Existing system frameworks for these tasks are not only spatially and temporally inefficient, but many also lead to biased results. This paper presents Skywalker, a high-throughput, quality-preserving random walk and sampling framework based on GPUs. Skywalker makes three key contributions: first, it takes the first step to realize efficient biased sampling with the alias method on a GPU. Second, it introduces well-crafted load-balancing techniques to effectively utilize the massive parallelism of GPUs. Third, it accelerates alias table construction and reduce the GPU memory requirement with efficient memory management scheme. We show that Skywalker greatly outperforms the state-of-the-art CPU-based and GPU-based baselines, in a wide spectrum of workload scenarios.
Author Zhang, Lu
Li, Chao
Chen, Quan
Leng, Jingwen
Wang, Jing
Wang, Pengyu
Wang, Taolei
Guo, Minyi
Author_xml – sequence: 1
  givenname: Pengyu
  surname: Wang
  fullname: Wang, Pengyu
  email: wpybtw@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China
– sequence: 2
  givenname: Chao
  surname: Li
  fullname: Li, Chao
  email: lichao@cs.sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China
– sequence: 3
  givenname: Jing
  surname: Wang
  fullname: Wang, Jing
  email: jing618@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China
– sequence: 4
  givenname: Taolei
  surname: Wang
  fullname: Wang, Taolei
  email: sjtuwtl@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China
– sequence: 5
  givenname: Lu
  surname: Zhang
  fullname: Zhang, Lu
  email: luzhang@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China
– sequence: 6
  givenname: Jingwen
  surname: Leng
  fullname: Leng, Jingwen
  email: leng-jw@cs.sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China
– sequence: 7
  givenname: Quan
  surname: Chen
  fullname: Chen, Quan
  email: chen-quan@cs.sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China
– sequence: 8
  givenname: Minyi
  surname: Guo
  fullname: Guo, Minyi
  email: guo-my@cs.sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China
BookMark eNotjMtKw0AUQEdQUGu-QBfzA6l3XpkZdzG0UahabIvLcpPM2KF5kQSkf29BN-eszrkll23XOkIeGMwZA_u4TrOt4tqqOQfO5gDA7QWJrDYsSZSUXBt9TaJxDAUorYXmlt2Q983x9IP10Q1PdOF9KINrJ5rWAcf4zU2HroqfcXQVzQfsD3SDTV-H9ptiW9HPM7qGfp1z2rU0X-_GO3LlsR5d9O8Z2S0X2-wlXn3kr1m6ipEbNcUCrJDcCygEWi6FZ4gmUZUpJBNGlolhUjtdQQmlRONl4lGWViKvbFEUpZiR-79vcM7t-yE0OJz2ViUCOIhfGehOfQ
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/PACT52795.2021.00029
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781665442787
1665442786
EndPage 317
ExternalDocumentID 9563020
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 61972247,62072297
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IL
ACM
ALMA_UNASSIGNED_HOLDINGS
APO
CBEJK
LHSKQ
RIE
RIL
ID FETCH-LOGICAL-a285t-309342f30b3a9243f1aa865d8b41384c68147e7d0c0c4a8f46fa4c94a2d9bbbc3
IEDL.DBID RIE
ISICitedReferencesCount 16
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000758464500022&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:24:04 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a285t-309342f30b3a9243f1aa865d8b41384c68147e7d0c0c4a8f46fa4c94a2d9bbbc3
PageCount 14
ParticipantIDs ieee_primary_9563020
PublicationCentury 2000
PublicationDate 2021-Sept.
PublicationDateYYYYMMDD 2021-09-01
PublicationDate_xml – month: 09
  year: 2021
  text: 2021-Sept.
PublicationDecade 2020
PublicationTitle 2021 30th International Conference on Parallel Architectures and Compilation Techniques (PACT)
PublicationTitleAbbrev PACT
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssib057737291
Score 2.3180842
Snippet Graph sampling and random walk operations, capturing the structural properties of graphs, are playing an important role today as we cannot directly adopt...
SourceID ieee
SourceType Publisher
StartPage 304
SubjectTerms Engines
Graph sampling
graphics processing unit
Graphics processing units
Heuristic algorithms
Memory management
Parallel algorithms
Parallel architectures
random walk
Task analysis
Title Skywalker: Efficient Alias-Method-Based Graph Sampling and Random Walk on GPUs
URI https://ieeexplore.ieee.org/document/9563020
WOSCitedRecordID wos000758464500022&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG6QePCkBozv9ODRyrbb3bbekABeJBuByI30aQiwa3ho_Pe2C6IHL142zSZNk5mmX6cz830A3FBHKLNEI668G_yBpxA3mCAPJh5euZHCmVJsgvV6fDQSWQXc7nphrLVl8Zm9C8Myl28KvQ5PZQ0RyKyID9D3GGObXq3vvZOwoLci8LY7DkeikTVbg4QwkfgokOBAVBjukb80VEoI6Rz-b_EjUP_pxYPZDmWOQcXmNdDrTz8_5GxqF_ewXZJA-LmwOZvIJXoqNaHRg4cnA7uBjxr2Zagbz1-hzA189p9iDl_8dFjksJsNl3Uw7LQHrUe0VUZAkvBkhUL6khIXRyqWPoCKHZaSp4nhymMSpzrl2HuAmUhHmkruaOok1YJKYoRSSscnoJoXuT0FMJVRqg3H1tiQ00uFSbBTlClllUu5OwO1YIvx24b8Yrw1w_nfvy_AQTD2pgjrElRXi7W9Avv6fTVZLq5Lj30BAZ2Wnw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA6lCnpSacW3OXh07Sab3U281dKH2C6LbbG3kqeU1l3pQ_Hfm2zr4-DFyxIWQmAm5MtkZr4PgCtiMIk1lh4V1g32wBMeVQh7FkwsvFLFmVGF2EScJHQ0YmkJXH_3wmiti-IzfeOGRS5f5XLlnspqzJFZYRugb4WEYLTu1vraPWHsFFcY2vTHIZ_V0npjEOKYhTYOxMhRFbqb5C8VlQJEWnv_W34fVH-68WD6jTMHoKSzCkj60493Ppvq-S1sFjQQdi6szyZ84fUKVWjvzgKUgm3HSA373FWOZ8-QZwo-2k_-Ap_sdJhnsJ0OF1UwbDUHjY630UbwOKbh0nMJTIJN4IuA2xAqMIhzGoWKCotKlMiIIuuDWPnSl4RTQyLDiWSEY8WEEDI4BOUsz_QRgBH3I6ko0kq7rF7EVIiMILEQWpiImmNQcbYYv67pL8YbM5z8_fsS7HQGve64e588nIJdZ_h1SdYZKC_nK30OtuXbcrKYXxTe-wQIoZnm
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2021+30th+International+Conference+on+Parallel+Architectures+and+Compilation+Techniques+%28PACT%29&rft.atitle=Skywalker%3A+Efficient+Alias-Method-Based+Graph+Sampling+and+Random+Walk+on+GPUs&rft.au=Wang%2C+Pengyu&rft.au=Li%2C+Chao&rft.au=Wang%2C+Jing&rft.au=Wang%2C+Taolei&rft.date=2021-09-01&rft.pub=IEEE&rft.spage=304&rft.epage=317&rft_id=info:doi/10.1109%2FPACT52795.2021.00029&rft.externalDocID=9563020