A Multi-Stage CUDA Kernel for Floyd-Warshall
We present a new implementation of the Floyd-Warshall All-Pairs Shortest Paths algorithm on CUDA. Our algorithm runs approximately 5 times faster than the previously best reported algorithm. In order to achieve this speedup, we applied a new technique to reduce usage of on-chip shared memory and all...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Lund, Ben Smith, Justin W |
| description | We present a new implementation of the Floyd-Warshall All-Pairs Shortest
Paths algorithm on CUDA. Our algorithm runs approximately 5 times faster than
the previously best reported algorithm. In order to achieve this speedup, we
applied a new technique to reduce usage of on-chip shared memory and allow the
CUDA scheduler to more effectively hide instruction latency. |
| doi_str_mv | 10.48550/arxiv.1001.4108 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1001_4108</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1001_4108</sourcerecordid><originalsourceid>FETCH-LOGICAL-a658-5abdab6280d06346be3ba8412e8fd093ed0904a781307dbf13a7a38d2d8e11fc3</originalsourceid><addsrcrecordid>eNotzrFOwzAUhWEvDFVh74T8ADjcGzvOZYwChYogBooYo2tsQyRDkFMQeXtaYDn_dvQJsUIoDFUVnHP-Hr4KBMDCINBCnDXy7jPtBvWw45cg28fLRt6G_B6SjGOW6zTOXj1xnl45pWNxFDlN4eS_S7FdX23bG9XdX2_aplNsK1IVO8_OlgQerDbWBe2YDJaBoocLHfYDhmtCDbV3ETXXrMmXngJifNZLcfp3-6vtP_LwxnnuD-r-oNY_uTQ6tg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A Multi-Stage CUDA Kernel for Floyd-Warshall</title><source>arXiv.org</source><creator>Lund, Ben ; Smith, Justin W</creator><creatorcontrib>Lund, Ben ; Smith, Justin W</creatorcontrib><description>We present a new implementation of the Floyd-Warshall All-Pairs Shortest
Paths algorithm on CUDA. Our algorithm runs approximately 5 times faster than
the previously best reported algorithm. In order to achieve this speedup, we
applied a new technique to reduce usage of on-chip shared memory and allow the
CUDA scheduler to more effectively hide instruction latency.</description><identifier>DOI: 10.48550/arxiv.1001.4108</identifier><language>eng</language><subject>Computer Science - Distributed, Parallel, and Cluster Computing ; Computer Science - Performance</subject><creationdate>2010-01</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1001.4108$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1001.4108$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Lund, Ben</creatorcontrib><creatorcontrib>Smith, Justin W</creatorcontrib><title>A Multi-Stage CUDA Kernel for Floyd-Warshall</title><description>We present a new implementation of the Floyd-Warshall All-Pairs Shortest
Paths algorithm on CUDA. Our algorithm runs approximately 5 times faster than
the previously best reported algorithm. In order to achieve this speedup, we
applied a new technique to reduce usage of on-chip shared memory and allow the
CUDA scheduler to more effectively hide instruction latency.</description><subject>Computer Science - Distributed, Parallel, and Cluster Computing</subject><subject>Computer Science - Performance</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2010</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzrFOwzAUhWEvDFVh74T8ADjcGzvOZYwChYogBooYo2tsQyRDkFMQeXtaYDn_dvQJsUIoDFUVnHP-Hr4KBMDCINBCnDXy7jPtBvWw45cg28fLRt6G_B6SjGOW6zTOXj1xnl45pWNxFDlN4eS_S7FdX23bG9XdX2_aplNsK1IVO8_OlgQerDbWBe2YDJaBoocLHfYDhmtCDbV3ETXXrMmXngJifNZLcfp3-6vtP_LwxnnuD-r-oNY_uTQ6tg</recordid><startdate>20100122</startdate><enddate>20100122</enddate><creator>Lund, Ben</creator><creator>Smith, Justin W</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20100122</creationdate><title>A Multi-Stage CUDA Kernel for Floyd-Warshall</title><author>Lund, Ben ; Smith, Justin W</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a658-5abdab6280d06346be3ba8412e8fd093ed0904a781307dbf13a7a38d2d8e11fc3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Computer Science - Distributed, Parallel, and Cluster Computing</topic><topic>Computer Science - Performance</topic><toplevel>online_resources</toplevel><creatorcontrib>Lund, Ben</creatorcontrib><creatorcontrib>Smith, Justin W</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Lund, Ben</au><au>Smith, Justin W</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Multi-Stage CUDA Kernel for Floyd-Warshall</atitle><date>2010-01-22</date><risdate>2010</risdate><abstract>We present a new implementation of the Floyd-Warshall All-Pairs Shortest
Paths algorithm on CUDA. Our algorithm runs approximately 5 times faster than
the previously best reported algorithm. In order to achieve this speedup, we
applied a new technique to reduce usage of on-chip shared memory and allow the
CUDA scheduler to more effectively hide instruction latency.</abstract><doi>10.48550/arxiv.1001.4108</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1001.4108 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1001_4108 |
| source | arXiv.org |
| subjects | Computer Science - Distributed, Parallel, and Cluster Computing Computer Science - Performance |
| title | A Multi-Stage CUDA Kernel for Floyd-Warshall |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T19%3A41%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Multi-Stage%20CUDA%20Kernel%20for%20Floyd-Warshall&rft.au=Lund,%20Ben&rft.date=2010-01-22&rft_id=info:doi/10.48550/arxiv.1001.4108&rft_dat=%3Carxiv_GOX%3E1001_4108%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |