Real-time parallel hashing on the GPU

We demonstrate an efficient data-parallel algorithm for building large hash tables of millions of elements in real-time. We consider two parallel algorithms for the construction: a classical sparse perfect hashing approach, and cuckoo hashing, which packs elements densely by allowing an element to b...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:ACM transactions on graphics 2009-12, Vol.28 (5), p.1-9
Hauptverfasser: Alcantara, Dan A, Sharf, Andrei, Abbasinejad, Fatemeh, Sengupta, Shubhabrata, Mitzenmacher, Michael, Owens, John D, Amenta, Nina
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 9
container_issue 5
container_start_page 1
container_title ACM transactions on graphics
container_volume 28
creator Alcantara, Dan A
Sharf, Andrei
Abbasinejad, Fatemeh
Sengupta, Shubhabrata
Mitzenmacher, Michael
Owens, John D
Amenta, Nina
description We demonstrate an efficient data-parallel algorithm for building large hash tables of millions of elements in real-time. We consider two parallel algorithms for the construction: a classical sparse perfect hashing approach, and cuckoo hashing, which packs elements densely by allowing an element to be stored in one of multiple possible locations. Our construction is a hybrid approach that uses both algorithms. We measure the construction time, access time, and memory usage of our implementations and demonstrate real-time performance on large datasets: for 5 million key-value pairs, we construct a hash table in 35.7 ms using 1.42 times as much memory as the input data itself, and we can access all the elements in that hash table in 15.3 ms. For comparison, sorting the same data requires 36.6 ms, but accessing all the elements via binary search requires 79.5 ms. Furthermore, we show how our hashing methods can be applied to two graphics applications: 3D surface intersection for moving data and geometric hashing for image matching.
doi_str_mv 10.1145/1618452.1618500
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_743736470</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1283694949</sourcerecordid><originalsourceid>FETCH-LOGICAL-c347t-71c481dd1e6a49edaac5584599530b30be154cdd71fdbecb453c62ac930031893</originalsourceid><addsrcrecordid>eNp9kE1Lw0AQhhdRMFbPXnMRvaSdyX4lRylahYIi9rxsNhMT2SQ1mx7896Y0Z5mB9_LwMvMwdouwRBRyhQozIdPlMSXAGYtQSp1orrJzFoHmkAAHvGRXIXwDgBJCRezug6xPxqaleG8H6z35uLahbrqvuO_isaZ48767ZheV9YFu5lyw3fPT5_ol2b5tXteP28RxocdEoxMZliWSsiKn0lon5XRUnksOxbSEUriy1FiVBblCSO5Ual3OAThmOV-w-1Pvfuh_DhRG0zbBkfe2o_4QjBZ8-kdomMiHf0lMM65yMc2Erk6oG_oQBqrMfmhaO_waBHNUZ2Z1ZlbH_wCttV3k</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1283694949</pqid></control><display><type>article</type><title>Real-time parallel hashing on the GPU</title><source>ACM Digital Library Complete</source><creator>Alcantara, Dan A ; Sharf, Andrei ; Abbasinejad, Fatemeh ; Sengupta, Shubhabrata ; Mitzenmacher, Michael ; Owens, John D ; Amenta, Nina</creator><creatorcontrib>Alcantara, Dan A ; Sharf, Andrei ; Abbasinejad, Fatemeh ; Sengupta, Shubhabrata ; Mitzenmacher, Michael ; Owens, John D ; Amenta, Nina</creatorcontrib><description>We demonstrate an efficient data-parallel algorithm for building large hash tables of millions of elements in real-time. We consider two parallel algorithms for the construction: a classical sparse perfect hashing approach, and cuckoo hashing, which packs elements densely by allowing an element to be stored in one of multiple possible locations. Our construction is a hybrid approach that uses both algorithms. We measure the construction time, access time, and memory usage of our implementations and demonstrate real-time performance on large datasets: for 5 million key-value pairs, we construct a hash table in 35.7 ms using 1.42 times as much memory as the input data itself, and we can access all the elements in that hash table in 15.3 ms. For comparison, sorting the same data requires 36.6 ms, but accessing all the elements via binary search requires 79.5 ms. Furthermore, we show how our hashing methods can be applied to two graphics applications: 3D surface intersection for moving data and geometric hashing for image matching.</description><identifier>ISSN: 0730-0301</identifier><identifier>EISSN: 1557-7368</identifier><identifier>DOI: 10.1145/1618452.1618500</identifier><language>eng</language><subject>Access time ; Algorithms ; Construction ; Hash based algorithms ; Real time ; Tables ; Three dimensional</subject><ispartof>ACM transactions on graphics, 2009-12, Vol.28 (5), p.1-9</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c347t-71c481dd1e6a49edaac5584599530b30be154cdd71fdbecb453c62ac930031893</citedby><cites>FETCH-LOGICAL-c347t-71c481dd1e6a49edaac5584599530b30be154cdd71fdbecb453c62ac930031893</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Alcantara, Dan A</creatorcontrib><creatorcontrib>Sharf, Andrei</creatorcontrib><creatorcontrib>Abbasinejad, Fatemeh</creatorcontrib><creatorcontrib>Sengupta, Shubhabrata</creatorcontrib><creatorcontrib>Mitzenmacher, Michael</creatorcontrib><creatorcontrib>Owens, John D</creatorcontrib><creatorcontrib>Amenta, Nina</creatorcontrib><title>Real-time parallel hashing on the GPU</title><title>ACM transactions on graphics</title><description>We demonstrate an efficient data-parallel algorithm for building large hash tables of millions of elements in real-time. We consider two parallel algorithms for the construction: a classical sparse perfect hashing approach, and cuckoo hashing, which packs elements densely by allowing an element to be stored in one of multiple possible locations. Our construction is a hybrid approach that uses both algorithms. We measure the construction time, access time, and memory usage of our implementations and demonstrate real-time performance on large datasets: for 5 million key-value pairs, we construct a hash table in 35.7 ms using 1.42 times as much memory as the input data itself, and we can access all the elements in that hash table in 15.3 ms. For comparison, sorting the same data requires 36.6 ms, but accessing all the elements via binary search requires 79.5 ms. Furthermore, we show how our hashing methods can be applied to two graphics applications: 3D surface intersection for moving data and geometric hashing for image matching.</description><subject>Access time</subject><subject>Algorithms</subject><subject>Construction</subject><subject>Hash based algorithms</subject><subject>Real time</subject><subject>Tables</subject><subject>Three dimensional</subject><issn>0730-0301</issn><issn>1557-7368</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2009</creationdate><recordtype>article</recordtype><recordid>eNp9kE1Lw0AQhhdRMFbPXnMRvaSdyX4lRylahYIi9rxsNhMT2SQ1mx7896Y0Z5mB9_LwMvMwdouwRBRyhQozIdPlMSXAGYtQSp1orrJzFoHmkAAHvGRXIXwDgBJCRezug6xPxqaleG8H6z35uLahbrqvuO_isaZ48767ZheV9YFu5lyw3fPT5_ol2b5tXteP28RxocdEoxMZliWSsiKn0lon5XRUnksOxbSEUriy1FiVBblCSO5Ual3OAThmOV-w-1Pvfuh_DhRG0zbBkfe2o_4QjBZ8-kdomMiHf0lMM65yMc2Erk6oG_oQBqrMfmhaO_waBHNUZ2Z1ZlbH_wCttV3k</recordid><startdate>20091201</startdate><enddate>20091201</enddate><creator>Alcantara, Dan A</creator><creator>Sharf, Andrei</creator><creator>Abbasinejad, Fatemeh</creator><creator>Sengupta, Shubhabrata</creator><creator>Mitzenmacher, Michael</creator><creator>Owens, John D</creator><creator>Amenta, Nina</creator><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20091201</creationdate><title>Real-time parallel hashing on the GPU</title><author>Alcantara, Dan A ; Sharf, Andrei ; Abbasinejad, Fatemeh ; Sengupta, Shubhabrata ; Mitzenmacher, Michael ; Owens, John D ; Amenta, Nina</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c347t-71c481dd1e6a49edaac5584599530b30be154cdd71fdbecb453c62ac930031893</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Access time</topic><topic>Algorithms</topic><topic>Construction</topic><topic>Hash based algorithms</topic><topic>Real time</topic><topic>Tables</topic><topic>Three dimensional</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Alcantara, Dan A</creatorcontrib><creatorcontrib>Sharf, Andrei</creatorcontrib><creatorcontrib>Abbasinejad, Fatemeh</creatorcontrib><creatorcontrib>Sengupta, Shubhabrata</creatorcontrib><creatorcontrib>Mitzenmacher, Michael</creatorcontrib><creatorcontrib>Owens, John D</creatorcontrib><creatorcontrib>Amenta, Nina</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>ACM transactions on graphics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Alcantara, Dan A</au><au>Sharf, Andrei</au><au>Abbasinejad, Fatemeh</au><au>Sengupta, Shubhabrata</au><au>Mitzenmacher, Michael</au><au>Owens, John D</au><au>Amenta, Nina</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Real-time parallel hashing on the GPU</atitle><jtitle>ACM transactions on graphics</jtitle><date>2009-12-01</date><risdate>2009</risdate><volume>28</volume><issue>5</issue><spage>1</spage><epage>9</epage><pages>1-9</pages><issn>0730-0301</issn><eissn>1557-7368</eissn><abstract>We demonstrate an efficient data-parallel algorithm for building large hash tables of millions of elements in real-time. We consider two parallel algorithms for the construction: a classical sparse perfect hashing approach, and cuckoo hashing, which packs elements densely by allowing an element to be stored in one of multiple possible locations. Our construction is a hybrid approach that uses both algorithms. We measure the construction time, access time, and memory usage of our implementations and demonstrate real-time performance on large datasets: for 5 million key-value pairs, we construct a hash table in 35.7 ms using 1.42 times as much memory as the input data itself, and we can access all the elements in that hash table in 15.3 ms. For comparison, sorting the same data requires 36.6 ms, but accessing all the elements via binary search requires 79.5 ms. Furthermore, we show how our hashing methods can be applied to two graphics applications: 3D surface intersection for moving data and geometric hashing for image matching.</abstract><doi>10.1145/1618452.1618500</doi><tpages>9</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0730-0301
ispartof ACM transactions on graphics, 2009-12, Vol.28 (5), p.1-9
issn 0730-0301
1557-7368
language eng
recordid cdi_proquest_miscellaneous_743736470
source ACM Digital Library Complete
subjects Access time
Algorithms
Construction
Hash based algorithms
Real time
Tables
Three dimensional
title Real-time parallel hashing on the GPU
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T13%3A28%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Real-time%20parallel%20hashing%20on%20the%20GPU&rft.jtitle=ACM%20transactions%20on%20graphics&rft.au=Alcantara,%20Dan%20A&rft.date=2009-12-01&rft.volume=28&rft.issue=5&rft.spage=1&rft.epage=9&rft.pages=1-9&rft.issn=0730-0301&rft.eissn=1557-7368&rft_id=info:doi/10.1145/1618452.1618500&rft_dat=%3Cproquest_cross%3E1283694949%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1283694949&rft_id=info:pmid/&rfr_iscdi=true