{"id":"https://openalex.org/W1994515555","doi":"https://doi.org/10.1109/iccd.2014.6974716","title":"An energy efficient column-major backend for FPGA SpMV accelerators","display_name":"An energy efficient column-major backend for FPGA SpMV accelerators","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W1994515555","doi":"https://doi.org/10.1109/iccd.2014.6974716","mag":"1994515555"},"language":"en","primary_location":{"id":"doi:10.1109/iccd.2014.6974716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd.2014.6974716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 32nd International Conference on Computer Design (ICCD)","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/A5001185686","display_name":"Yaman Umuroglu","orcid":null},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]},{"id":"https://openalex.org/I4210105718","display_name":"Trondheim Kommune","ror":"https://ror.org/01gjtys23","country_code":"NO","type":"government","lineage":["https://openalex.org/I4210105718"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Yaman Umuroglu","raw_affiliation_strings":["Norges teknisk-naturvitenskapelige universitet, Trondheim, NO","Norwegian University of Science and Technology, Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norges teknisk-naturvitenskapelige universitet, Trondheim, NO","institution_ids":["https://openalex.org/I4210105718"]},{"raw_affiliation_string":"Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067108530","display_name":"Magnus Jahre","orcid":"https://orcid.org/0000-0001-9147-5228"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Magnus Jahre","raw_affiliation_strings":["Department of Computer and Information Science, Norwegian University of Science and Technology, Trondheim, Norway","Norwegian University of Science and Technology, Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5755,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.82414116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"432","last_page":"439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9975000023841858,"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":0.8212252259254456},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.7222311496734619},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6516175270080566},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5421240925788879},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4807415008544922},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.4109596610069275},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.359688937664032},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3531416654586792},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.28177160024642944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212252259254456},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.7222311496734619},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6516175270080566},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5421240925788879},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4807415008544922},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.4109596610069275},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.359688937664032},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3531416654586792},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.28177160024642944},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccd.2014.6974716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd.2014.6974716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 32nd International Conference on Computer Design (ICCD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1975116854","https://openalex.org/W2003313945","https://openalex.org/W2014469493","https://openalex.org/W2022881857","https://openalex.org/W2035080386","https://openalex.org/W2035234517","https://openalex.org/W2080146741","https://openalex.org/W2099625934","https://openalex.org/W2103877122","https://openalex.org/W2105332698","https://openalex.org/W2106111377","https://openalex.org/W2108540054","https://openalex.org/W2115172404","https://openalex.org/W2124408528","https://openalex.org/W2128853364","https://openalex.org/W2129513794","https://openalex.org/W2162639668","https://openalex.org/W2166000469","https://openalex.org/W4233908922","https://openalex.org/W6677264922"],"related_works":["https://openalex.org/W3120961607","https://openalex.org/W2098207691","https://openalex.org/W1967938402","https://openalex.org/W2386041993","https://openalex.org/W1608572506","https://openalex.org/W2984139344","https://openalex.org/W2077105843","https://openalex.org/W2770465587","https://openalex.org/W2086716781","https://openalex.org/W2022510519"],"abstract_inverted_index":{"FPGAs":[0],"are":[1],"promising":[2],"candidates":[3],"for":[4],"energy":[5],"efficient":[6],"acceleration":[7],"of":[8,52,111,163],"sparse":[9],"matrix-vector":[10],"multiplication":[11],"(SpMV),":[12],"a":[13,84,103,132],"kernel":[14],"with":[15,122],"important":[16,40],"applications":[17],"in":[18],"scientific":[19],"computing":[20],"and":[21,29,55,70,73,92,119,145],"engineering.":[22],"SpMV":[23,45,68,166],"is":[24,106],"characterized":[25],"by":[26,125,168],"matrix-dependent":[27,57],"performance":[28,41],"high":[30,96],"external":[31],"memory":[32,53,71,114],"bandwidth":[33,37,58,97,116,124,161],"demands,":[34],"which":[35,78],"makes":[36],"utilization":[38,162],"an":[39],"indicator.":[42],"Existing":[43],"FPGA":[44,165],"accelerators":[46,167],"focus":[47,74],"on":[48,75,117],"datapath":[49],"optimizations":[50],"instead":[51],"behavior,":[54,72],"exhibit":[56],"utilization.":[59,98],"In":[60],"this":[61],"work,":[62],"we":[63],"propose":[64],"to":[65,94,108,131,139,147,170],"decouple":[66],"the":[67,76,80,159],"computation":[69],"backend":[77,86,105],"handles":[79],"latter.":[81],"We":[82],"describe":[83],"scalable":[85],"architecture":[87],"that":[88,102,155],"exploits":[89],"column-major":[90],"traversal":[91],"interleaving":[93],"achieve":[95],"Our":[99],"experiments":[100],"show":[101],"single":[104],"able":[107],"sustain":[109],"96%":[110],"its":[112],"assigned":[113],"port":[115],"average,":[118],"scales":[120],"well":[121],"increased":[123],"instantiating":[126],"multiple":[127],"parallel":[128],"units.":[129],"Compared":[130],"baseline":[133],"scheme,":[134],"our":[135,156],"scheme":[136,157],"offers":[137],"up":[138,146],"1.5\u00d7":[140],"higher":[141,149],"DRAM":[142],"power":[143],"efficiency":[144],"20%":[148],"aggregate":[150],"bandwidth.":[151],"The":[152],"results":[153],"indicate":[154],"improves":[158],"average":[160],"existing":[164],"15":[169],"77%.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}