{"id":"https://openalex.org/W2009173369","doi":"https://doi.org/10.1145/2018323.2018330","title":"Improving SIMD efficiency for parallel Monte Carlo light transport on the GPU","display_name":"Improving SIMD efficiency for parallel Monte Carlo light transport on the GPU","publication_year":2011,"publication_date":"2011-08-05","ids":{"openalex":"https://openalex.org/W2009173369","doi":"https://doi.org/10.1145/2018323.2018330","mag":"2009173369"},"language":"en","primary_location":{"id":"doi:10.1145/2018323.2018330","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2018323.2018330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGGRAPH Symposium on High Performance Graphics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067623312","display_name":"Dietger van Antwerpen","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Dietger van Antwerpen","raw_affiliation_strings":["Delft University of Technology, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5067623312"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":14.0582,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.98694807,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.8136942386627197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7959460020065308},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7644668817520142},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6150146722793579},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.5809032917022705},{"id":"https://openalex.org/keywords/random-walk","display_name":"Random walk","score":0.5164918899536133},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.47788703441619873},{"id":"https://openalex.org/keywords/embarrassingly-parallel","display_name":"Embarrassingly parallel","score":0.47765910625457764},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.45605015754699707},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4283919632434845},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3785564601421356},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.2576388716697693},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11213847994804382},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.09685218334197998},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.08349719643592834}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8136942386627197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7959460020065308},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7644668817520142},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6150146722793579},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5809032917022705},{"id":"https://openalex.org/C121194460","wikidata":"https://www.wikidata.org/wiki/Q856741","display_name":"Random walk","level":2,"score":0.5164918899536133},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.47788703441619873},{"id":"https://openalex.org/C126909462","wikidata":"https://www.wikidata.org/wiki/Q5369501","display_name":"Embarrassingly parallel","level":3,"score":0.47765910625457764},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.45605015754699707},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4283919632434845},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3785564601421356},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.2576388716697693},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11213847994804382},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.09685218334197998},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.08349719643592834},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2018323.2018330","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2018323.2018330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGGRAPH Symposium on High Performance Graphics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W190660021","https://openalex.org/W1552813311","https://openalex.org/W1982661771","https://openalex.org/W2001100395","https://openalex.org/W2008693968","https://openalex.org/W2067313328","https://openalex.org/W2090346540","https://openalex.org/W2098077797","https://openalex.org/W2117236520","https://openalex.org/W2119547137","https://openalex.org/W2122978030","https://openalex.org/W2130026741","https://openalex.org/W2135807756","https://openalex.org/W2152365613","https://openalex.org/W2154891655","https://openalex.org/W2161446118","https://openalex.org/W2188658603","https://openalex.org/W2255785842","https://openalex.org/W2614374371","https://openalex.org/W4232290346","https://openalex.org/W4251846088"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"Monte":[0],"Carlo":[1],"Light":[2,16],"Transport":[3,17],"algorithms":[4,32],"such":[5],"as":[6],"Path":[7,11],"Tracing":[8,12],"(PT),":[9],"Bi-Directional":[10],"(BDPT)":[13],"and":[14,62,82,105,121],"Metropolis":[15],"(MLT)":[18],"make":[19],"use":[20],"of":[21,39,76,91,138],"random":[22,40,71],"walks":[23,41],"to":[24,58,65,86,98],"sample":[25,63,93,110],"light":[26],"transport":[27],"paths.":[28],"When":[29],"parallelizing":[30],"these":[31],"on":[33],"the":[34,36,100],"GPU":[35,103,129],"stochastic":[37,77],"termination":[38],"results":[42],"in":[43,74,94,96,123],"an":[44,136],"uneven":[45],"workload":[46,101],"between":[47,102],"samples,":[48],"which":[49],"reduces":[50],"SIMD":[51,67,107],"efficiency.":[52],"In":[53],"this":[54],"paper":[55],"we":[56,84],"propose":[57,85],"combine":[59],"stream":[60],"compaction":[61],"regeneration":[64],"keep":[66],"efficiency":[68,108],"high":[69],"during":[70,109],"walk":[72],"construction,":[73],"spite":[75],"termination.":[78],"Furthermore,":[79],"for":[80,118],"BDPT":[81],"MLT,":[83],"evaluate":[87],"all":[88],"bidirectional":[89],"connections":[90],"a":[92],"parallel":[95,115],"order":[97,137],"balance":[99],"threads":[104],"improve":[106],"evaluation.":[111],"We":[112,125],"present":[113],"efficient":[114],"GPU-only":[116],"implementations":[117,130,134],"PT,":[119],"BDPT,":[120],"MLT":[122],"CUDA.":[124],"show":[126],"that":[127],"our":[128],"outperform":[131],"similar":[132],"CPU":[133],"by":[135],"magnitude.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}