{"id":"https://openalex.org/W2505906308","doi":"https://doi.org/10.1109/coolchips.2016.7503681","title":"A power-efficient FPGA accelerator: Systolic array with cache-coherent interface for pair-HMM algorithm","display_name":"A power-efficient FPGA accelerator: Systolic array with cache-coherent interface for pair-HMM algorithm","publication_year":2016,"publication_date":"2016-04-01","ids":{"openalex":"https://openalex.org/W2505906308","doi":"https://doi.org/10.1109/coolchips.2016.7503681","mag":"2505906308"},"language":"en","primary_location":{"id":"doi:10.1109/coolchips.2016.7503681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coolchips.2016.7503681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Symposium in Low-Power and High-Speed Chips (COOL CHIPS XIX)","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/A5042484827","display_name":"Megumi Ito","orcid":"https://orcid.org/0009-0002-3627-5308"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Megumi Ito","raw_affiliation_strings":["IBM Research \u2013 Tokyo, Chuo-ku, Japan"],"affiliations":[{"raw_affiliation_string":"IBM Research \u2013 Tokyo, Chuo-ku, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108772251","display_name":"Moriyoshi Ohara","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Moriyoshi Ohara","raw_affiliation_strings":["IBM Research \u2013 Tokyo, Chuo-ku, Japan"],"affiliations":[{"raw_affiliation_string":"IBM Research \u2013 Tokyo, Chuo-ku, Japan","institution_ids":["https://openalex.org/I4210145865"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042484827"],"corresponding_institution_ids":["https://openalex.org/I4210145865"],"apc_list":null,"apc_paid":null,"fwci":4.33869955,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.95634509,"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":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.9994000196456909,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9984999895095825,"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":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8076533079147339},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7967408895492554},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.5763862133026123},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4937497079372406},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.46918654441833496},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4656791090965271},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.45358115434646606},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.43304911255836487},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4150053560733795},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3334220349788666},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.1554267704486847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076533079147339},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7967408895492554},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.5763862133026123},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4937497079372406},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.46918654441833496},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4656791090965271},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.45358115434646606},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.43304911255836487},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4150053560733795},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3334220349788666},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.1554267704486847},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coolchips.2016.7503681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coolchips.2016.7503681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Symposium in Low-Power and High-Speed Chips (COOL CHIPS XIX)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W67414564","https://openalex.org/W1997113918","https://openalex.org/W2017369466","https://openalex.org/W2120345843","https://openalex.org/W2144316495","https://openalex.org/W4233749681"],"related_works":["https://openalex.org/W4240320454","https://openalex.org/W2070314832","https://openalex.org/W2395557210","https://openalex.org/W2111241003","https://openalex.org/W2010232134","https://openalex.org/W4200391368","https://openalex.org/W2210979487","https://openalex.org/W2347854075","https://openalex.org/W2518118925","https://openalex.org/W3159273459"],"abstract_inverted_index":{"A":[0],"systolic":[1],"array":[2],"is":[3],"known":[4],"as":[5],"a":[6,12,55,102],"parallel":[7],"hardware":[8,40],"architecture":[9],"applicable":[10],"to":[11,22,53],"wide":[13],"range":[14],"of":[15],"applications.":[16],"Naive":[17],"implementations,":[18],"however,":[19],"can":[20],"lead":[21],"inefficient":[23],"resource":[24,41],"usage":[25],"and":[26,45],"low":[27],"power":[28,99],"performance.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"discuss":[34],"two":[35],"techniques":[36],"for":[37,78],"improving":[38],"the":[39,62,75,80,88,93,107],"usage:":[42],"flexible":[43],"multi-threading":[44],"dummy":[46],"data":[47],"padding.":[48],"The":[49,71],"design":[50,77],"was":[51],"implemented":[52,89],"accelerate":[54],"pair-HMM":[56,94],"algorithm":[57,95],"on":[58],"an":[59],"FPGA":[60,81,90],"with":[61],"IBM":[63],"POWER8":[64,103],"CAPI":[65,72],"(Coherent":[66],"Accelerator":[67],"Processor":[68],"Interface)":[69],"feature.":[70],"feature":[73],"simplifies":[74],"software":[76],"driving":[79],"accelerator.":[82],"Our":[83],"experimental":[84],"result":[85],"indicates":[86],"that":[87],"accelerator":[91],"executing":[92,106],"achieves":[96],"33x":[97],"higher":[98],"performance":[100],"than":[101],"processor":[104],"chip":[105],"same":[108],"algorithm.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}