{"id":"https://openalex.org/W2156140864","doi":"https://doi.org/10.1109/asap.2010.5540796","title":"Highly efficient mapping of the Smith-Waterman algorithm on CUDA-compatible GPUs","display_name":"Highly efficient mapping of the Smith-Waterman algorithm on CUDA-compatible GPUs","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2156140864","doi":"https://doi.org/10.1109/asap.2010.5540796","mag":"2156140864"},"language":"en","primary_location":{"id":"doi:10.1109/asap.2010.5540796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2010.5540796","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ASAP 2010 - 21st IEEE International Conference on Application-specific Systems, Architectures and Processors","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/A5023754045","display_name":"Kaoru Dohi","orcid":"https://orcid.org/0000-0002-5078-6326"},"institutions":[{"id":"https://openalex.org/I43777268","display_name":"Nagasaki University","ror":"https://ror.org/058h74p94","country_code":"JP","type":"education","lineage":["https://openalex.org/I43777268"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"K Dohi","raw_affiliation_strings":["Dept. of Computer and Information Sciences Nagasaki University, Nagasaki, Japan"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer and Information Sciences Nagasaki University, Nagasaki, Japan","institution_ids":["https://openalex.org/I43777268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098506596","display_name":"K Benkridt","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"K Benkridt","raw_affiliation_strings":["The University of Edinburgh, Edinburgh, Edinburgh, GB"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, Edinburgh, GB","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":null,"display_name":"C Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"C Ling","raw_affiliation_strings":["School of Engineering, King's Buildings. The University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Engineering, King's Buildings. The University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079641930","display_name":"Takashi Hamada","orcid":"https://orcid.org/0000-0002-8438-750X"},"institutions":[{"id":"https://openalex.org/I43777268","display_name":"Nagasaki University","ror":"https://ror.org/058h74p94","country_code":"JP","type":"education","lineage":["https://openalex.org/I43777268"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T Hamada","raw_affiliation_strings":["Dept. of Computer and Information Sciences Nagasaki University, Nagasaki, Japan"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer and Information Sciences Nagasaki University, Nagasaki, Japan","institution_ids":["https://openalex.org/I43777268"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108530640","display_name":"Y. Shibata","orcid":null},"institutions":[{"id":"https://openalex.org/I43777268","display_name":"Nagasaki University","ror":"https://ror.org/058h74p94","country_code":"JP","type":"education","lineage":["https://openalex.org/I43777268"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Y Shibata","raw_affiliation_strings":["Dept. of Computer and Information Sciences Nagasaki University, Nagasaki, Japan"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer and Information Sciences Nagasaki University, Nagasaki, Japan","institution_ids":["https://openalex.org/I43777268"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5023754045"],"corresponding_institution_ids":["https://openalex.org/I43777268"],"apc_list":null,"apc_paid":null,"fwci":6.0629,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.96230159,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9968000054359436,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9968000054359436,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.989799976348877,"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":0.874211847782135},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8510473966598511},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8146466612815857},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.7659265995025635},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5200007557868958},{"id":"https://openalex.org/keywords/smith\u2013waterman-algorithm","display_name":"Smith\u2013Waterman algorithm","score":0.5043891668319702},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4574347138404846},{"id":"https://openalex.org/keywords/loop-tiling","display_name":"Loop tiling","score":0.4302319884300232},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4174535274505615},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1392839252948761},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.10962626338005066},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.10692676901817322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.874211847782135},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8510473966598511},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8146466612815857},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.7659265995025635},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5200007557868958},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.5043891668319702},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4574347138404846},{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.4302319884300232},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4174535274505615},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1392839252948761},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.10962626338005066},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.10692676901817322},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asap.2010.5540796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2010.5540796","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ASAP 2010 - 21st IEEE International Conference on Application-specific Systems, Architectures and Processors","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1494930385","https://openalex.org/W1507497085","https://openalex.org/W2011652244","https://openalex.org/W2068448872","https://openalex.org/W2087064593","https://openalex.org/W2132967231","https://openalex.org/W2133540884","https://openalex.org/W2143210482","https://openalex.org/W2144316495","https://openalex.org/W2146379626","https://openalex.org/W2166081493","https://openalex.org/W2184753910","https://openalex.org/W4236236547","https://openalex.org/W6686290393"],"related_works":["https://openalex.org/W30800889","https://openalex.org/W1951652387","https://openalex.org/W4251798485","https://openalex.org/W2122418911","https://openalex.org/W1992520403","https://openalex.org/W2039186546","https://openalex.org/W2151744790","https://openalex.org/W2340721088","https://openalex.org/W2278840053","https://openalex.org/W4232588022"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,31,41,130,142,157,161,170],"multi-threaded":[4],"parallel":[5],"design":[6],"and":[7,33,78,127,153,160,166],"implementation":[8,121,136,178,187,201],"of":[9,40,60,87,101,132,137,179,199],"the":[10,38,56,61,85,99,115,138,175,180,205],"Smith-Waterman":[11],"(SW)":[12],"algorithm":[13,140,182],"on":[14,55,156,169],"graphic":[15],"processing":[16],"units":[17],"(GPUs)":[18],"with":[19,65,174],"NVIDIA":[20],"corporation's":[21],"Compute":[22],"Unified":[23],"Device":[24],"Architecture":[25],"(CUDA).":[26],"Central":[27],"to":[28,83,97,184,190,210],"this":[29],"is":[30,107,202],"divide":[32],"conquer":[34],"approach":[35],"which":[36],"divides":[37],"computation":[39],"whole":[42],"pairwise":[43],"sequence":[44],"alignment":[45],"matrix":[46],"into":[47],"multiple":[48],"sub-matrices":[49],"(or":[50],"parallelograms)":[51],"each":[52],"running":[53],"efficiently":[54],"available":[57,203],"hardware":[58],"resources":[59],"GPU":[62,177],"in":[63,70,81,95,109,119,194,204],"hand,":[64],"temporary":[66],"intermediate":[67,105],"data":[68,106],"stored":[69,108],"global":[71,110],"memory.":[72],"Moreover,":[73],"we":[74],"use":[75],"thread":[76,88],"warps":[77],"padding":[79],"techniques":[80],"order":[82,96],"decrease":[84],"cost":[86,100],"synchronization,":[89],"as":[90,92],"well":[91],"loop":[93,118],"unrolling":[94],"reduce":[98],"conditional":[102],"branches.":[103],"While":[104],"memory":[111,126],"for":[112,208],"large":[113],"queries,":[114],"most":[116],"inner":[117],"our":[120,135,186,200],"will":[122],"only":[123],"access":[124],"shared":[125],"registers.":[128],"As":[129],"result":[131],"these":[133],"optimizations,":[134],"SW":[139,181],"achieves":[141,188],"throughput":[143,162],"ranging":[144],"between":[145,163],"9.09":[146],"GCUPS":[147,155,165,168],"(Giga":[148],"Cell":[149],"Update":[150],"per":[151],"Second)":[152],"12.71":[154],"single-GPU":[158],"version,":[159],"29.46":[164],"43.05":[167],"quad-GPU":[171],"platform.":[172],"Compared":[173],"best":[176],"reported":[183],"date,":[185],"up":[189],"46":[191],"%":[192],"improvement":[193],"speed.":[195],"The":[196],"source":[197],"code":[198],"public":[206],"domain":[207],"Bioinformaticians":[209],"benefit":[211],"from":[212],"its":[213],"performance.":[214]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":8}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}