{"id":"https://openalex.org/W3132973453","doi":"https://doi.org/10.1109/tcad.2021.3058910","title":"Agglomerative Memory and Thread Scheduling for High-Performance Ray-Tracing on GPUs","display_name":"Agglomerative Memory and Thread Scheduling for High-Performance Ray-Tracing on GPUs","publication_year":2021,"publication_date":"2021-02-13","ids":{"openalex":"https://openalex.org/W3132973453","doi":"https://doi.org/10.1109/tcad.2021.3058910","mag":"3132973453"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2021.3058910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2021.3058910","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-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/A5084623149","display_name":"Yufei Ni","orcid":"https://orcid.org/0000-0002-3868-3025"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Ni","raw_affiliation_strings":["Department of Microelectronics, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3868-3025","affiliations":[{"raw_affiliation_string":"Department of Microelectronics, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059155953","display_name":"Yangdong Deng","orcid":"https://orcid.org/0000-0002-8257-693X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangdong Deng","raw_affiliation_strings":["School of Software, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015545142","display_name":"Zonghui Li","orcid":"https://orcid.org/0000-0002-0772-1738"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zonghui Li","raw_affiliation_strings":["School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4062,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65897621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"41","issue":"2","first_page":"334","last_page":"345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9944999814033508,"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/computer-science","display_name":"Computer science","score":0.8455345630645752},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7495547533035278},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6684572696685791},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5959858894348145},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5375708341598511},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5188233256340027},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.4452746510505676},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22770103812217712},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.22651800513267517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8455345630645752},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7495547533035278},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6684572696685791},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5959858894348145},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5375708341598511},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5188233256340027},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.4452746510505676},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22770103812217712},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.22651800513267517},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2021.3058910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2021.3058910","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3740624217","display_name":null,"funder_award_id":"61527812","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1564611446","https://openalex.org/W1839039067","https://openalex.org/W1976090850","https://openalex.org/W1979527452","https://openalex.org/W1982853272","https://openalex.org/W1997162567","https://openalex.org/W2004471965","https://openalex.org/W2005032370","https://openalex.org/W2012892204","https://openalex.org/W2025442915","https://openalex.org/W2050609278","https://openalex.org/W2063249715","https://openalex.org/W2067313328","https://openalex.org/W2077945322","https://openalex.org/W2102592717","https://openalex.org/W2116453990","https://openalex.org/W2122681699","https://openalex.org/W2142703245","https://openalex.org/W2153226019","https://openalex.org/W2157300467","https://openalex.org/W2160428323","https://openalex.org/W2296218291","https://openalex.org/W2511683765","https://openalex.org/W2753156694","https://openalex.org/W2761675321","https://openalex.org/W2888242478","https://openalex.org/W3000296767","https://openalex.org/W3128982134","https://openalex.org/W4214596219","https://openalex.org/W4243155314","https://openalex.org/W4255962840","https://openalex.org/W6675306916"],"related_works":["https://openalex.org/W1571368810","https://openalex.org/W1594563977","https://openalex.org/W1616582327","https://openalex.org/W1784146144","https://openalex.org/W2068042411","https://openalex.org/W1532146045","https://openalex.org/W1579918296","https://openalex.org/W4242316748","https://openalex.org/W3132973453","https://openalex.org/W4235870392"],"abstract_inverted_index":{"Ray-tracing":[0],"rendering":[1,23,32],"has":[2],"long":[3],"been":[4],"considered":[5],"as":[6],"a":[7,12,51,71,77,83,95,105,131,160,230],"promising":[8],"technology":[9],"to":[10,24,31,37,55,93,116,171],"enable":[11],"higher":[13],"level":[14],"of":[15,20,60,63,74,86,196],"visual":[16],"experience.":[17],"The":[18,68,202],"democratization":[19],"the":[21,57,118,122,137,155,172,193,221],"ray-tracing":[22,46,123,133],"consumer":[25],"platforms,":[26],"however,":[27],"poses":[28],"significant":[29,84],"challenges":[30],"hardware":[33],"and":[34,65,111,179,228],"software":[35],"due":[36],"its":[38],"highly":[39],"irregular":[40,87],"computing":[41,58],"patterns.":[42],"In":[43,102,186],"fact,":[44],"modern":[45],"techniques":[47],"typically":[48],"depend":[49],"on":[50,76,125,208],"tree-based":[52],"acceleration":[53,138],"structure":[54,139],"reduce":[56],"complexity":[59],"intersection":[61],"testing":[62],"rays":[64,75,178],"graphics":[66,78],"primitives.":[67],"traversal":[69],"by":[70,175,234],"massive":[72],"number":[73],"processing":[79],"unit":[80],"(GPU)":[81],"incurs":[82],"amount":[85],"memory":[88,226],"traffic,":[89],"which":[90,136],"turns":[91],"out":[92],"be":[94,151,206],"major":[96],"stumbling":[97],"block":[98],"for":[99,184,236],"real-time":[100],"performance.":[101],"this":[103,143],"work,":[104],"scheduling":[106,165],"mechanism,":[107],"so-called":[108],"Agglomerative":[109],"Memory":[110],"Thread":[112],"Scheduling,":[113],"is":[114,128,145],"proposed":[115,203,222],"unleash":[117],"inherence":[119],"parallelism":[120],"in":[121,135,142,198],"process":[124],"GPUs.":[126],"It":[127],"associated":[129],"with":[130,169,212],"tile-based":[132],"framework":[134,223],"(i.e.,":[140],"KD-tree":[141],"work)":[144],"partitioned":[146],"into":[147,154,182,192],"subtrees":[148,173,188],"that":[149,220],"can":[150,205],"completely":[152],"loaded":[153],"on-chip":[156],"L1":[157,194],"cache":[158,195],"inside":[159],"streaming":[161],"multiprocessor.":[162],"An":[163],"effective":[164],"mechanism":[166],"collects":[167],"threads":[168,181],"regard":[170],"hit":[174],"their":[176],"respective":[177],"regroup":[180],"warps":[183],"dispatching.":[185],"addition,":[187],"are":[189],"dynamically":[190],"preloaded":[191],"multiprocessors":[197],"an":[199],"on-demand":[200],"fashion.":[201],"scheduler":[204],"integrated":[207],"today&#x2019;s":[209],"high-end":[210],"GPUs":[211],"only":[213],"minor":[214],"overhead.":[215],"Microarchitecture":[216],"simulation":[217],"results":[218],"prove":[219],"significantly":[224],"improves":[225],"efficiency":[227],"outperforms":[229],"traditional":[231],"GPU":[232],"microarchitecture":[233],"47.4&#x0025;":[235],"average.":[237]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
