{"id":"https://openalex.org/W2163963850","doi":"https://doi.org/10.1145/1735688.1735705","title":"Best-effort semantic document search on GPUs","display_name":"Best-effort semantic document search on GPUs","publication_year":2010,"publication_date":"2010-03-14","ids":{"openalex":"https://openalex.org/W2163963850","doi":"https://doi.org/10.1145/1735688.1735705","mag":"2163963850"},"language":"en","primary_location":{"id":"doi:10.1145/1735688.1735705","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1735688.1735705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units","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/A5062233562","display_name":"Suren Byna","orcid":"https://orcid.org/0000-0003-3048-3448"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Surendra Byna","raw_affiliation_strings":["NEC Laboratories America, Princeton, NJ"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, NJ","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018781096","display_name":"Jiayuan Meng","orcid":"https://orcid.org/0000-0002-1135-6518"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayuan Meng","raw_affiliation_strings":["University of Virginia, Charlottesville, VA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065766721","display_name":"Anand Raghunathan","orcid":"https://orcid.org/0000-0002-4624-564X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Raghunathan","raw_affiliation_strings":["Purdue University, West Lafayette, IN"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042424184","display_name":"Srimat Chakradhar","orcid":"https://orcid.org/0000-0003-3530-3901"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srimat Chakradhar","raw_affiliation_strings":["NEC Laboratories America, Princeton, NJ"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, NJ","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034416611","display_name":"Srihari Cadambi","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srihari Cadambi","raw_affiliation_strings":["NEC Laboratories America, Princeton, NJ"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, NJ","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5062233562"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":5.1095,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.95360787,"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":"86","last_page":"93"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8797407150268555},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7330319881439209},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6579557657241821},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6507568955421448},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5590572953224182},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.5408194065093994},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4711018204689026},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.4644833207130432},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.463228702545166},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.4499109089374542},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.28496643900871277},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.20744481682777405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1618073582649231},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15324944257736206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8797407150268555},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7330319881439209},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6579557657241821},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6507568955421448},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5590572953224182},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.5408194065093994},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4711018204689026},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.4644833207130432},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.463228702545166},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.4499109089374542},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28496643900871277},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.20744481682777405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1618073582649231},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15324944257736206},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1735688.1735705","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1735688.1735705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.720.2940","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.720.2940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://sdm.lbl.gov/%7Esbyna/research/papers/2010-GPU-BestEffortGPU.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1810646324","https://openalex.org/W1998938125","https://openalex.org/W2002046716","https://openalex.org/W2015935981","https://openalex.org/W2071039340","https://openalex.org/W2091434413","https://openalex.org/W2109722477","https://openalex.org/W2109884165","https://openalex.org/W2111783218","https://openalex.org/W2117154099","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2129921015","https://openalex.org/W2162241008","https://openalex.org/W2600222141","https://openalex.org/W4206566500","https://openalex.org/W6735341058"],"related_works":["https://openalex.org/W2621501241","https://openalex.org/W2208757713","https://openalex.org/W3177128669","https://openalex.org/W2991848348","https://openalex.org/W2966127030","https://openalex.org/W2232473477","https://openalex.org/W1509422975","https://openalex.org/W47034296","https://openalex.org/W1496703677","https://openalex.org/W2160476201"],"abstract_inverted_index":{"Semantic":[0,108],"indexing":[1,24,40,77,102],"is":[2,47,125,261,393,420],"a":[3,35,42,52,69,134,138,148,259,272,284,335,354,359,365,375,381,398],"popular":[4],"technique":[5],"used":[6],"to":[7,68,86,95,183,202,228,236,277,297,364,374,397],"access":[8,145],"and":[9,25,78,127,164,225,254,310,312,412],"organize":[10],"large":[11],"amounts":[12],"of":[13,22,38,75,83,119,133,167,188,206,234,242,251,293,330,337],"unstructured":[14],"text":[15],"data.":[16],"We":[17,32,61,245,324],"describe":[18],"an":[19,56],"optimized":[20],"implementation":[21,37,54,156,329,352,368,379,392,400,419],"semantic":[23,39,76,101,331],"document":[26,332],"search":[27,333],"on":[28,41,55,258,271,301,334,353,369,380,401],"manycore":[29],"GPU":[30,46,155,169,260,315,351,391,418],"platforms.":[31],"observed":[33,151],"that":[34,91,152,198,248,406],"parallel":[36,294,367,377,399],"128-core":[43,355],"Tesla":[44,356],"C870":[45,357],"only":[48],"2.4X":[49],"faster":[50],"than":[51,65],"sequential":[53,212],"Intel":[57,384],"Xeon":[58,385],"2.4GHz":[59],"processor.":[60],"ascribe":[62],"the":[63,72,79,87,117,131,153,159,168,172,185,189,211,231,238,243,249,278,291,302,370,389,402],"less":[64],"spectacular":[66],"speedup":[67],"mismatch":[70],"in":[71,121,142],"workload":[73,232],"characteristics":[74,115,193,233],"unique":[80,177,192,239],"architectural":[81,240,280],"features":[82,241,281],"GPUs.":[84],"Compared":[85,373,396],"regular":[88],"numerical":[89,204],"computations":[90],"have":[92],"been":[93],"ported":[94],"GPUs":[96],"with":[97,137,210],"great":[98],"success,":[99],"our":[100,326,346,350,416],"algorithm":[103,110,174],"(the":[104],"recently":[105],"proposed":[106],"Supervised":[107],"Indexing":[109],"called":[111],"SSI)":[112],"has":[113],"interesting":[114],"--":[116],"amount":[118,292],"parallelism":[120],"each":[122,128,207],"training":[123,208],"instance":[124],"data-dependent,":[126],"iteration":[129,209],"involves":[130],"product":[132],"dense":[135],"matrix":[136],"sparse":[139],"vector,":[140],"resulting":[141],"random":[143],"memory":[144,165],"patterns.":[146],"As":[147],"result,":[149],"we":[150,180,216,319],"baseline":[154,366,376],"significantly":[157],"under-utilizes":[158],"hardware":[160],"resources":[161],"(processing":[162],"elements":[163],"bandwidth)":[166],"platform.":[170],"However,":[171],"SSI":[173,235],"also":[175,246,407],"demonstrates":[176],"characteristics,":[178],"which":[179],"collectively":[181],"refer":[182],"as":[184,222,362],"\"forgiving":[186],"nature\"":[187],"algorithm.":[190],"These":[191],"allow":[194],"for":[195],"novel":[196,347],"optimizations":[197],"do":[199],"not":[200],"strive":[201],"preserve":[203],"equivalence":[205],"implementation.":[213],"In":[214],"particular,":[215],"consider":[217],"best-effort":[218],"computing":[219],"techniques,":[220,415],"such":[221],"dependency":[223,252,410],"relaxation":[224,253,411],"computation":[226,255,414],"dropping,":[227],"suitably":[229],"alter":[230],"leverage":[237],"GPU.":[244,285,303,372],"show":[247],"realization":[250],"dropping":[256,413],"concepts":[257,270],"quite":[262],"different":[263],"from":[264,342],"how":[265],"one":[266],"would":[267],"implement":[268],"these":[269],"multicore":[273,386],"CPU,":[274],"largely":[275],"due":[276],"distinct":[279],"supported":[282],"by":[283,313],"Our":[286],"new":[287,327],"techniques":[288],"dramatically":[289],"enhance":[290],"workload,":[295],"leading":[296],"much":[298],"higher":[299],"performance":[300,322],"By":[304,344],"optimizing":[305],"data":[306,409],"transfers":[307],"between":[308],"CPU":[309,387,405],"GPU,":[311],"reducing":[314],"kernel":[316],"invocation":[317],"overheads,":[318],"achieve":[320],"further":[321],"gains.":[323],"evaluated":[325],"GPU-accelerated":[328],"database":[336],"over":[338],"1.8":[339],"million":[340],"documents":[341],"Wikipedia.":[343],"applying":[345],"performance-enhancing":[348],"strategies,":[349],"achieved":[358],"5.5X":[360],"acceleration":[361],"compared":[363],"same":[371,403],"TBB":[378],"dual-socket":[382],"quad-core":[383],"(8-cores),":[388],"enhanced":[390,417],"11X":[394],"faster.":[395,422],"multi-core":[404],"uses":[408],"5X":[421]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}