{"id":"https://openalex.org/W2172042531","doi":"https://doi.org/10.1109/acssc.2008.5074382","title":"High performance matrix multiply using fused datapath operators","display_name":"High performance matrix multiply using fused datapath operators","publication_year":2008,"publication_date":"2008-10-01","ids":{"openalex":"https://openalex.org/W2172042531","doi":"https://doi.org/10.1109/acssc.2008.5074382","mag":"2172042531"},"language":"en","primary_location":{"id":"doi:10.1109/acssc.2008.5074382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2008.5074382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 42nd Asilomar Conference on Signals, Systems and Computers","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/A5082265695","display_name":"Martin Langhammer","orcid":"https://orcid.org/0000-0001-8206-2077"},"institutions":[{"id":"https://openalex.org/I4210094575","display_name":"Altera (United Kingdom)","ror":"https://ror.org/00m96gg93","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210094575"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Martin Langhammer","raw_affiliation_strings":["Holmers Farm Way, Altera Corporation, High Wycombe, Buckinghamshire, UK"],"affiliations":[{"raw_affiliation_string":"Holmers Farm Way, Altera Corporation, High Wycombe, Buckinghamshire, UK","institution_ids":["https://openalex.org/I4210094575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5082265695"],"corresponding_institution_ids":["https://openalex.org/I4210094575"],"apc_list":null,"apc_paid":null,"fwci":0.3466,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71875974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"153","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/datapath","display_name":"Datapath","score":0.9052187204360962},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.8183615207672119},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7659999132156372},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6884399652481079},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.67389976978302},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6227949857711792},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5777834057807922},{"id":"https://openalex.org/keywords/stratix","display_name":"Stratix","score":0.5730268359184265},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.5612819790840149},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5271717309951782},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5255452394485474},{"id":"https://openalex.org/keywords/single-precision-floating-point-format","display_name":"Single-precision floating-point format","score":0.4884449541568756},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3530471622943878},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26717451214790344}],"concepts":[{"id":"https://openalex.org/C2781198647","wikidata":"https://www.wikidata.org/wiki/Q1633673","display_name":"Datapath","level":2,"score":0.9052187204360962},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.8183615207672119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659999132156372},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6884399652481079},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.67389976978302},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6227949857711792},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5777834057807922},{"id":"https://openalex.org/C2776277307","wikidata":"https://www.wikidata.org/wiki/Q22074755","display_name":"Stratix","level":3,"score":0.5730268359184265},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.5612819790840149},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5271717309951782},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5255452394485474},{"id":"https://openalex.org/C133095886","wikidata":"https://www.wikidata.org/wiki/Q1307173","display_name":"Single-precision floating-point format","level":3,"score":0.4884449541568756},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3530471622943878},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26717451214790344},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acssc.2008.5074382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2008.5074382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 42nd Asilomar Conference on Signals, Systems and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4699999988079071,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W114677020","https://openalex.org/W1991973578","https://openalex.org/W2106942255","https://openalex.org/W2111345110"],"related_works":["https://openalex.org/W3116924726","https://openalex.org/W2106942255","https://openalex.org/W2571972762","https://openalex.org/W3177218348","https://openalex.org/W2156524298","https://openalex.org/W2065321717","https://openalex.org/W3097256929","https://openalex.org/W17610788","https://openalex.org/W2752065998","https://openalex.org/W2013660188"],"abstract_inverted_index":{"The":[0],"numerous":[1],"resources":[2],"on":[3,62],"current":[4],"FPGA":[5,133],"devices":[6],"make":[7],"them":[8],"attractive":[9],"for":[10,26,119,142,151],"the":[11,38,106,125,132,143],"implementation":[12,60],"of":[13,28,41,88,108,131],"high":[14,54],"performance":[15],"computing":[16],"and":[17,48,137],"scientific":[18],"algorithm":[19],"acceleration.":[20],"Floating":[21],"point":[22,72,129],"arithmetic":[23],"is":[24,111],"required":[25],"many":[27],"these":[29,152],"applications,":[30],"which":[31],"can":[32,82],"be":[33,83,135],"more":[34],"easily":[35],"supported":[36],"by":[37],"newer":[39],"generation":[40],"embedded":[42,145],"blocks":[43],"such":[44],"as":[45],"larger":[46],"memories":[47],"multipliers.":[49],"This":[50],"paper":[51],"describes":[52],"a":[53,63,140],"performance,":[55],"scalable,":[56],"dense":[57],"matrix":[58],"multiply":[59],"based":[61],"vector":[64],"operator":[65],"function":[66],"generated":[67],"with":[68],"an":[69],"experimental":[70],"floating":[71,128],"datapath":[73,117],"compiler.":[74],"Either":[75],"single":[76,96],"precision":[77,80,92,97],"or":[78,93],"double":[79,91],"datapaths":[81],"compiled,":[84],"providing":[85],"in":[86,98],"excess":[87],"50":[89],"GFLOPs":[90,95],"100":[94],"Altera":[99],"Stratix":[100],"reg":[101],"III":[102],"devices.":[103,153],"In":[104],"particular,":[105],"contribution":[107],"this":[109],"work":[110],"to":[112,134,138,147],"demonstrate":[113],"that":[114],"using":[115],"fused":[116],"synthesis":[118],"linear":[120],"algebra":[121],"applications":[122],"will":[123],"allow":[124],"entire":[126],"theoretical":[127],"capability":[130],"used,":[136],"introduce":[139],"benchmark":[141],"correct":[144],"multiplier":[146],"soft":[148],"logic":[149],"ratio":[150]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}