{"id":"https://openalex.org/W2104262506","doi":"https://doi.org/10.1109/ipdps.2014.36","title":"cuBLASTP: Fine-Grained Parallelization of Protein Sequence Search on a GPU","display_name":"cuBLASTP: Fine-Grained Parallelization of Protein Sequence Search on a GPU","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2104262506","doi":"https://doi.org/10.1109/ipdps.2014.36","mag":"2104262506"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2014.36","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2014.36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","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/A5061841494","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0002-8495-2804"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Dept. of Computer Science","Virginia Tech, Blacksburg, United States"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science","institution_ids":[]},{"raw_affiliation_string":"Virginia Tech, Blacksburg, United States","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446064","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0001-9301-5989"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Dept. of Computer Science","Virginia Tech, Blacksburg, United States"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science","institution_ids":[]},{"raw_affiliation_string":"Virginia Tech, Blacksburg, United States","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103124804","display_name":"Heshan Lin","orcid":"https://orcid.org/0000-0003-0825-6169"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heshan Lin","raw_affiliation_strings":["Dept. of Computer Science","Virginia Tech, Blacksburg, United States"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science","institution_ids":[]},{"raw_affiliation_string":"Virginia Tech, Blacksburg, United States","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058539554","display_name":"Wu-chun Feng","orcid":"https://orcid.org/0000-0002-6015-0727"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu-Chun Feng","raw_affiliation_strings":["Dept. of Electrical & Computer Engineering \u2502Virginia Tech","Virginia Tech, Blacksburg, United States"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical & Computer Engineering \u2502Virginia Tech","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Virginia Tech, Blacksburg, United States","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061841494"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":2.139,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.87593603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"251","last_page":"260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9934999942779541,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9628999829292297,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8641076683998108},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7812256813049316},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7666606903076172},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7264902591705322},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4911057949066162},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.46587297320365906},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.4511503577232361},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.43820077180862427},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.43758174777030945},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4319833517074585},{"id":"https://openalex.org/keywords/smith\u2013waterman-algorithm","display_name":"Smith\u2013Waterman algorithm","score":0.42723825573921204},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.4270942807197571},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4218676686286926},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4202401041984558},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.218916654586792},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.16282853484153748}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8641076683998108},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7812256813049316},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7666606903076172},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7264902591705322},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4911057949066162},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.46587297320365906},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.4511503577232361},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.43820077180862427},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.43758174777030945},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4319833517074585},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.42723825573921204},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.4270942807197571},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4218676686286926},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4202401041984558},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.218916654586792},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.16282853484153748},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2014.36","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2014.36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.990.4915","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.990.4915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://on-demand.gputechconf.com/gtc/2014/poster/pdf/P4214_bioinformatics_BLAST_BLASTP.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12","score":0.5199999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W145805655","https://openalex.org/W1978885894","https://openalex.org/W2057496513","https://openalex.org/W2057783089","https://openalex.org/W2072177669","https://openalex.org/W2087064593","https://openalex.org/W2096041635","https://openalex.org/W2103644816","https://openalex.org/W2122482436","https://openalex.org/W2142678478","https://openalex.org/W2155957132","https://openalex.org/W2156137607","https://openalex.org/W2171474230","https://openalex.org/W4236236547","https://openalex.org/W6606052223"],"related_works":["https://openalex.org/W1968724572","https://openalex.org/W2191246539","https://openalex.org/W2151046618","https://openalex.org/W1972148443","https://openalex.org/W1969233021","https://openalex.org/W2161873733","https://openalex.org/W2146379626","https://openalex.org/W2167646277","https://openalex.org/W2063573318","https://openalex.org/W2375309128"],"abstract_inverted_index":{"BLAST,":[0],"short":[1],"for":[2,72,141,201,220,252,277,288],"Basic":[3],"Local":[4],"Alignment":[5],"Search":[6],"Tool,":[7],"is":[8,47,88],"a":[9,124,171,174,179,231,239,246,274,285],"fundamental":[10],"algorithm":[11,71],"in":[12,30,102,210],"the":[13,22,35,41,54,62,69,97,110,121,130,142,189,193,221,253,278,282,289],"life":[14],"sciences":[15],"that":[16,229],"compares":[17],"biological":[18],"sequences.":[19],"However,":[20],"with":[21,173,207,260],"advent":[23],"of":[24,44,266],"next-generation":[25],"sequencing":[26],"(NGS)":[27],"and":[28,117,198,212,245,284],"increase":[29],"sequence":[31,45,86],"read-lengths,":[32],"whether":[33],"at":[34],"outset":[36],"or":[37],"downstream":[38],"from":[39,160],"NGS,":[40],"exponential":[42],"growth":[43],"databases":[46],"arguably":[48],"outstripping":[49],"our":[50],"ability":[51],"to":[52,67,90,96,108,120,157,163,169,178,185,204,216,238,268,273],"analyze":[53],"data.":[55],"Though":[56],"several":[57],"recent":[58],"studies":[59,79],"have":[60],"utilized":[61],"graphics":[63],"processing":[64],"unit":[65],"(GPU)":[66],"speedup":[68,241,248,276,287],"BLAST":[70],"searching":[73],"protein":[74],"sequences":[75,206],"(i.e.,":[76,114],"BLASTP),":[77],"these":[78],"used":[80],"coarse-grained":[81],"parallel":[82],"approaches,":[83],"where":[84],"one":[85,92],"alignment":[87],"mapped":[89],"only":[91],"thread.":[93],"Moreover,":[94],"due":[95],"irregular":[98],"memory":[99],"access":[100],"patterns":[101],"BLASTP,":[103],"there":[104],"remain":[105],"significant":[106],"challenges":[107],"map":[109,170],"most":[111],"time-consuming":[112],"phases":[113],"hit":[115,172,183],"detection":[116],"ungapped":[118,202],"extension)":[119],"GPU":[122,143,264,283],"using":[123,144],"fine-grained":[125,138],"multithreaded":[126,250],"approach.":[127],"To":[128],"address":[129],"above":[131],"issues,":[132],"we":[133],"propose":[134],"cuBLASTP,":[135],"an":[136],"efficient":[137],"BLASTP":[139,267],"implementation":[140,265],"CUDA.":[145],"Our":[146],"cuBLASTP":[147,235,270],"realization":[148],"encompasses":[149],"many":[150],"research":[151],"contributions,":[152],"including":[153],"(1)":[154],"memory-access":[155,218],"reordering":[156],"reorder":[158],"hits":[159,187],"column-major":[161],"order":[162],"diagonal-major":[164],"order,":[165],"(2)":[166],"position-based":[167],"indexing":[168],"packed":[175],"data":[176,223],"structure":[177],"bin,":[180],"(3)":[181],"aggressive":[182],"filtering":[184],"eliminate":[186],"beyond":[188],"threshold":[190],"distance":[191],"along":[192],"diagonal,":[194],"(4)":[195],"diagonal-based":[196],"parallelism":[197,200],"hit-based":[199],"extension":[203],"extend":[205],"different":[208],"lengths":[209],"databases,":[211],"(5)":[213],"hierarchical":[214],"buffering":[215],"reduce":[217],"overhead":[219],"core":[222],"structures.":[224],"The":[225],"experimental":[226],"results":[227],"show":[228],"on":[230,281],"NVIDIA":[232],"Kepler":[233],"GPU,":[234],"delivers":[236],"up":[237,272],"5.0-fold":[240],"over":[242,249],"sequential":[243],"FSA-BLAST":[244],"3.7-fold":[247],"NCBI-BLAST":[251],"overall":[254,290],"program":[255,291],"execution.":[256,292],"In":[257],"addition,":[258],"compared":[259],"GPU-BLASTP":[261],"(the":[262],"fastest":[263],"date),":[269],"achieves":[271],"2.8-fold":[275],"kernel":[279],"execution":[280],"1.8-fold":[286]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}