kD-Tree Traversal Implementations for Ray Tracing on Massive Multiprocessors: A Comparative Study
Current GPU computational power enables the execution of complex and parallel algorithms, such as Ray Tracing techniques supported by kD-trees for 3D scene rendering in real time. This work describes in detail the study and implementation of five different kD-Tree traversal algorithms using the para...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 48 |
|---|---|
| container_issue | |
| container_start_page | 41 |
| container_title | |
| container_volume | |
| creator | dos Santos, A.L. Teixeira, J. de Farias, T.S.M.C. Teichrieb, V. Kelner, J. |
| description | Current GPU computational power enables the execution of complex and parallel algorithms, such as Ray Tracing techniques supported by kD-trees for 3D scene rendering in real time. This work describes in detail the study and implementation of five different kD-Tree traversal algorithms using the parallel framework NVIDIA Compute Unified Device Architecture (CUDA), in order to point their pros and cons regarding adaptation capability to the chosen architecture. In addition, a new algorithm is proposed by the authors based on this analysis, aiming performance improvement. A performance analysis of the implemented techniques demonstrates that two of these algorithms, once adequately adapted to CUDA architecture, are capable of reaching speedup gains up to 15times when compared to former CPU implementations and up to 4times in comparison to existing and optimized parallel ones. As a consequence, interactive frame rates are possible for scenes with 1376 times 768 pixels of resolution and 1 million primitives. |
| doi_str_mv | 10.1109/SBAC-PAD.2009.25 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5336215</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5336215</ieee_id><sourcerecordid>5336215</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-52fd9a3ae06d0749ad759a83eb2c36c107e3c4ceaa28606a34523c42ce5f094f3</originalsourceid><addsrcrecordid>eNotj8tOwzAURC0eEm1hj8TGP-BybcdOzS6kPCq1AtGwri7JDQrkJTut1L8nCFYjzZwZaRi7ljCXEtzt9j5JxWuynCsAN1fmhE2UjbTQAPKUTSG2zuiFie0Zm0hjQFij9QWbhvAFoK1ydsLweykyT8QzjwfyAWu-avqaGmoHHKquDbzsPH_D4y-RV-0n71q-wRCqA_HNvh6q3nc5hdD5cMcTnnZNj36sjvF22BfHS3ZeYh3o6l9n7P3xIUufxfrlaZUma1HJ2AzCqLJwqJHAFhBHDovYOFxo-lC5trmEmHQe5YSoFhYs6sio0VA5mRJcVOoZu_nbrYho1_uqQX_cjY-tkkb_AECUVuo</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>kD-Tree Traversal Implementations for Ray Tracing on Massive Multiprocessors: A Comparative Study</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>dos Santos, A.L. ; Teixeira, J. ; de Farias, T.S.M.C. ; Teichrieb, V. ; Kelner, J.</creator><creatorcontrib>dos Santos, A.L. ; Teixeira, J. ; de Farias, T.S.M.C. ; Teichrieb, V. ; Kelner, J.</creatorcontrib><description>Current GPU computational power enables the execution of complex and parallel algorithms, such as Ray Tracing techniques supported by kD-trees for 3D scene rendering in real time. This work describes in detail the study and implementation of five different kD-Tree traversal algorithms using the parallel framework NVIDIA Compute Unified Device Architecture (CUDA), in order to point their pros and cons regarding adaptation capability to the chosen architecture. In addition, a new algorithm is proposed by the authors based on this analysis, aiming performance improvement. A performance analysis of the implemented techniques demonstrates that two of these algorithms, once adequately adapted to CUDA architecture, are capable of reaching speedup gains up to 15times when compared to former CPU implementations and up to 4times in comparison to existing and optimized parallel ones. As a consequence, interactive frame rates are possible for scenes with 1376 times 768 pixels of resolution and 1 million primitives.</description><identifier>ISSN: 1550-6533</identifier><identifier>ISBN: 0769538576</identifier><identifier>ISBN: 9780769538570</identifier><identifier>EISSN: 2643-3001</identifier><identifier>DOI: 10.1109/SBAC-PAD.2009.25</identifier><language>eng</language><publisher>IEEE</publisher><subject>Communication standards ; CUDA ; Decoding ; Digital video broadcasting ; Error correction codes ; Integrated circuit interconnections ; Iterative algorithms ; kD-Tree ; Network-on-a-chip ; Parity check codes ; Ray tracing ; Traversal ; WiMAX</subject><ispartof>2009 21st International Symposium on Computer Architecture and High Performance Computing, 2009, p.41-48</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5336215$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5336215$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>dos Santos, A.L.</creatorcontrib><creatorcontrib>Teixeira, J.</creatorcontrib><creatorcontrib>de Farias, T.S.M.C.</creatorcontrib><creatorcontrib>Teichrieb, V.</creatorcontrib><creatorcontrib>Kelner, J.</creatorcontrib><title>kD-Tree Traversal Implementations for Ray Tracing on Massive Multiprocessors: A Comparative Study</title><title>2009 21st International Symposium on Computer Architecture and High Performance Computing</title><addtitle>SBACPAD</addtitle><description>Current GPU computational power enables the execution of complex and parallel algorithms, such as Ray Tracing techniques supported by kD-trees for 3D scene rendering in real time. This work describes in detail the study and implementation of five different kD-Tree traversal algorithms using the parallel framework NVIDIA Compute Unified Device Architecture (CUDA), in order to point their pros and cons regarding adaptation capability to the chosen architecture. In addition, a new algorithm is proposed by the authors based on this analysis, aiming performance improvement. A performance analysis of the implemented techniques demonstrates that two of these algorithms, once adequately adapted to CUDA architecture, are capable of reaching speedup gains up to 15times when compared to former CPU implementations and up to 4times in comparison to existing and optimized parallel ones. As a consequence, interactive frame rates are possible for scenes with 1376 times 768 pixels of resolution and 1 million primitives.</description><subject>Communication standards</subject><subject>CUDA</subject><subject>Decoding</subject><subject>Digital video broadcasting</subject><subject>Error correction codes</subject><subject>Integrated circuit interconnections</subject><subject>Iterative algorithms</subject><subject>kD-Tree</subject><subject>Network-on-a-chip</subject><subject>Parity check codes</subject><subject>Ray tracing</subject><subject>Traversal</subject><subject>WiMAX</subject><issn>1550-6533</issn><issn>2643-3001</issn><isbn>0769538576</isbn><isbn>9780769538570</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2009</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotj8tOwzAURC0eEm1hj8TGP-BybcdOzS6kPCq1AtGwri7JDQrkJTut1L8nCFYjzZwZaRi7ljCXEtzt9j5JxWuynCsAN1fmhE2UjbTQAPKUTSG2zuiFie0Zm0hjQFij9QWbhvAFoK1ydsLweykyT8QzjwfyAWu-avqaGmoHHKquDbzsPH_D4y-RV-0n71q-wRCqA_HNvh6q3nc5hdD5cMcTnnZNj36sjvF22BfHS3ZeYh3o6l9n7P3xIUufxfrlaZUma1HJ2AzCqLJwqJHAFhBHDovYOFxo-lC5trmEmHQe5YSoFhYs6sio0VA5mRJcVOoZu_nbrYho1_uqQX_cjY-tkkb_AECUVuo</recordid><startdate>200910</startdate><enddate>200910</enddate><creator>dos Santos, A.L.</creator><creator>Teixeira, J.</creator><creator>de Farias, T.S.M.C.</creator><creator>Teichrieb, V.</creator><creator>Kelner, J.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200910</creationdate><title>kD-Tree Traversal Implementations for Ray Tracing on Massive Multiprocessors: A Comparative Study</title><author>dos Santos, A.L. ; Teixeira, J. ; de Farias, T.S.M.C. ; Teichrieb, V. ; Kelner, J.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-52fd9a3ae06d0749ad759a83eb2c36c107e3c4ceaa28606a34523c42ce5f094f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Communication standards</topic><topic>CUDA</topic><topic>Decoding</topic><topic>Digital video broadcasting</topic><topic>Error correction codes</topic><topic>Integrated circuit interconnections</topic><topic>Iterative algorithms</topic><topic>kD-Tree</topic><topic>Network-on-a-chip</topic><topic>Parity check codes</topic><topic>Ray tracing</topic><topic>Traversal</topic><topic>WiMAX</topic><toplevel>online_resources</toplevel><creatorcontrib>dos Santos, A.L.</creatorcontrib><creatorcontrib>Teixeira, J.</creatorcontrib><creatorcontrib>de Farias, T.S.M.C.</creatorcontrib><creatorcontrib>Teichrieb, V.</creatorcontrib><creatorcontrib>Kelner, J.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>dos Santos, A.L.</au><au>Teixeira, J.</au><au>de Farias, T.S.M.C.</au><au>Teichrieb, V.</au><au>Kelner, J.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>kD-Tree Traversal Implementations for Ray Tracing on Massive Multiprocessors: A Comparative Study</atitle><btitle>2009 21st International Symposium on Computer Architecture and High Performance Computing</btitle><stitle>SBACPAD</stitle><date>2009-10</date><risdate>2009</risdate><spage>41</spage><epage>48</epage><pages>41-48</pages><issn>1550-6533</issn><eissn>2643-3001</eissn><isbn>0769538576</isbn><isbn>9780769538570</isbn><abstract>Current GPU computational power enables the execution of complex and parallel algorithms, such as Ray Tracing techniques supported by kD-trees for 3D scene rendering in real time. This work describes in detail the study and implementation of five different kD-Tree traversal algorithms using the parallel framework NVIDIA Compute Unified Device Architecture (CUDA), in order to point their pros and cons regarding adaptation capability to the chosen architecture. In addition, a new algorithm is proposed by the authors based on this analysis, aiming performance improvement. A performance analysis of the implemented techniques demonstrates that two of these algorithms, once adequately adapted to CUDA architecture, are capable of reaching speedup gains up to 15times when compared to former CPU implementations and up to 4times in comparison to existing and optimized parallel ones. As a consequence, interactive frame rates are possible for scenes with 1376 times 768 pixels of resolution and 1 million primitives.</abstract><pub>IEEE</pub><doi>10.1109/SBAC-PAD.2009.25</doi><tpages>8</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1550-6533 |
| ispartof | 2009 21st International Symposium on Computer Architecture and High Performance Computing, 2009, p.41-48 |
| issn | 1550-6533 2643-3001 |
| language | eng |
| recordid | cdi_ieee_primary_5336215 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Communication standards CUDA Decoding Digital video broadcasting Error correction codes Integrated circuit interconnections Iterative algorithms kD-Tree Network-on-a-chip Parity check codes Ray tracing Traversal WiMAX |
| title | kD-Tree Traversal Implementations for Ray Tracing on Massive Multiprocessors: A Comparative Study |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T11%3A43%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=kD-Tree%20Traversal%20Implementations%20for%20Ray%20Tracing%20on%20Massive%20Multiprocessors:%20A%20Comparative%20Study&rft.btitle=2009%2021st%20International%20Symposium%20on%20Computer%20Architecture%20and%20High%20Performance%20Computing&rft.au=dos%20Santos,%20A.L.&rft.date=2009-10&rft.spage=41&rft.epage=48&rft.pages=41-48&rft.issn=1550-6533&rft.eissn=2643-3001&rft.isbn=0769538576&rft.isbn_list=9780769538570&rft_id=info:doi/10.1109/SBAC-PAD.2009.25&rft_dat=%3Cieee_6IE%3E5336215%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5336215&rfr_iscdi=true |