{"id":"https://openalex.org/W4408900503","doi":"https://doi.org/10.1145/3676641.3716279","title":"Treelet Accelerated Ray Tracing on GPUs","display_name":"Treelet Accelerated Ray Tracing on GPUs","publication_year":2025,"publication_date":"2025-03-27","ids":{"openalex":"https://openalex.org/W4408900503","doi":"https://doi.org/10.1145/3676641.3716279"},"language":"en","primary_location":{"id":"doi:10.1145/3676641.3716279","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676641.3716279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","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/A5017521734","display_name":"Yuan Hsi Chou","orcid":"https://orcid.org/0009-0006-9554-0545"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuan Hsi Chou","raw_affiliation_strings":["University of British Columbia, Vancouver, Canada"],"raw_orcid":"https://orcid.org/0009-0006-9554-0545","affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026788167","display_name":"Tor M. Aamodt","orcid":"https://orcid.org/0000-0003-1161-692X"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tor M. Aamodt","raw_affiliation_strings":["University of British Columbia, Vancouver, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1161-692X","affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10111178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1334","last_page":"1347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9969000220298767,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ray-tracing","display_name":"Ray tracing (physics)","score":0.7257438898086548},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6310238242149353},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.46707940101623535},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3778681755065918},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3634990453720093},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10253632068634033},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10100218653678894},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.09129494428634644}],"concepts":[{"id":"https://openalex.org/C121483023","wikidata":"https://www.wikidata.org/wiki/Q7298343","display_name":"Ray tracing (physics)","level":2,"score":0.7257438898086548},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6310238242149353},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.46707940101623535},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3778681755065918},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3634990453720093},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10253632068634033},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10100218653678894},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.09129494428634644}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3676641.3716279","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676641.3716279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1839039067","https://openalex.org/W2025442915","https://openalex.org/W2102592717","https://openalex.org/W2135807756","https://openalex.org/W2155568054","https://openalex.org/W2160428323","https://openalex.org/W2238992335","https://openalex.org/W2518569579","https://openalex.org/W2737903756","https://openalex.org/W2738383649","https://openalex.org/W2765771514","https://openalex.org/W2800378834","https://openalex.org/W3023860106","https://openalex.org/W3102510044","https://openalex.org/W3205099630","https://openalex.org/W4241602464","https://openalex.org/W4255847023","https://openalex.org/W4302340922","https://openalex.org/W4308083826","https://openalex.org/W4388207348","https://openalex.org/W4389500423","https://openalex.org/W4400681668","https://openalex.org/W4404954483","https://openalex.org/W4404955717","https://openalex.org/W6753118495","https://openalex.org/W6862729836"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2054109135","https://openalex.org/W2888673113","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2043557177","https://openalex.org/W2349351862"],"abstract_inverted_index":{"Despite":[0],"advances":[1],"in":[2,8,104,171,209],"hardware":[3],"acceleration,":[4],"ray":[5,122,203],"tracing":[6,204,214],"use":[7],"real-time":[9],"rendering":[10],"is":[11,80,176],"limited":[12],"and":[13,43,82,127],"often":[14],"lowers":[15],"frame":[16],"rates,":[17],"leading":[18],"users":[19],"such":[20],"as":[21],"video":[22],"game":[23],"players":[24],"to":[25,68,71,85,106,132,156,178,198],"disable":[26],"the":[27,36,99,139,172],"feature":[28],"entirely.":[29],"Prior":[30],"work":[31],"has":[32],"shown":[33],"that":[34,47,75,116,150,162],"dividing":[35],"BVH":[37],"tree":[38],"into":[39],"smaller":[40],"subtrees":[41],"(treelets)":[42],"traversing":[44],"all":[45,207],"rays":[46,103],"visit":[48],"a":[49,60,76,145,199],"treelet":[50,78,147,184,190],"before":[51],"switching":[52],"treelets":[53,70],"can":[54],"significantly":[55],"reduce":[56],"memory":[57],"traffic":[58],"on":[59,193],"specialized":[61],"accelerator,":[62],"but":[63],"there":[64],"are":[65],"many":[66],"challenges":[67],"applying":[69],"GPUs.":[72],"We":[73,159],"find":[74,161],"naive":[77],"implementation":[79],"ineffective":[81],"propose":[83,144],"optimizations":[84],"improve":[86],"performance.":[87],"Virtualized":[88],"Treelet":[89],"Queues":[90],"consist":[91],"of":[92,101,138,169],"two":[93],"main":[94],"components.":[95],"Ray":[96],"virtualization":[97],"increases":[98],"number":[100],"concurrent":[102,141],"flight":[105],"create":[107],"more":[108,129],"cache":[109],"reuse":[110],"opportunities":[111],"by":[112],"terminating":[113],"raygen":[114,130],"shaders":[115,131],"have":[117],"already":[118],"issued":[119],"their":[120],"trace":[121],"instruction,":[123],"reclaiming":[124],"CUDA":[125],"cores":[126],"allowing":[128],"be":[133],"executed.":[134],"To":[135],"take":[136],"advantage":[137],"increased":[140],"rays,":[142],"we":[143],"dynamic":[146],"queue":[148],"architecture":[149],"dynamically":[151],"switches":[152],"between":[153],"traversal":[154,181],"modes":[155],"increase":[157],"efficiency.":[158],"also":[160],"performing":[163],"warp":[164],"repacking":[165],"boosts":[166],"SIMT":[167],"efficiency":[168],"warps":[170],"RT":[173],"unit":[174],"which":[175],"crucial":[177],"achieving":[179],"good":[180],"performance":[182],"with":[183,202,212,220],"queues.":[185],"Our":[186],"simulations":[187],"show":[188],"virtualized":[189],"queues":[191],"achieve":[192],"average":[194],"95%":[195],"speedup":[196],"compared":[197],"baseline":[200],"GPU":[201],"acceleration":[205],"across":[206],"scenes":[208],"LumiBench":[210],"rendered":[211],"path":[213],"at":[215],"one":[216],"sample":[217],"per":[218,224],"pixel":[219],"three":[221],"max":[222],"bounces":[223],"ray.":[225]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
