{"id":"https://openalex.org/W7164186084","doi":"https://doi.org/10.1109/fccm68464.2026.00049","title":"A Streaming FPGA Architecture for Sparse Matrix Multiplication with Sparsity-Aware Data Reordering","display_name":"A Streaming FPGA Architecture for Sparse Matrix Multiplication with Sparsity-Aware Data Reordering","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7164186084","doi":"https://doi.org/10.1109/fccm68464.2026.00049"},"language":"en","primary_location":{"id":"doi:10.1109/fccm68464.2026.00049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fccm68464.2026.00049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 34th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/385088/1/385088.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134647050","display_name":"Shuxuan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shuxuan Li","raw_affiliation_strings":["University of Glasgow,School of Computing Science,Glasgow,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,School of Computing Science,Glasgow,United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057776164","display_name":"\u039d\u03b9\u03ba\u03ad\u03bb\u03b1 \u03a0\u03b1\u03c0\u03b1\u03b4\u03bf\u03c0\u03bf\u03cd\u03bb\u03bf\u03c5","orcid":"https://orcid.org/0000-0003-2141-5654"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nikela Papadopoulou","raw_affiliation_strings":["University of Glasgow,School of Computing Science,Glasgow,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,School of Computing Science,Glasgow,United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138380347","display_name":"Wim Vanderbauwhede","orcid":null},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wim Vanderbauwhede","raw_affiliation_strings":["University of Glasgow,School of Computing Science,Glasgow,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,School of Computing Science,Glasgow,United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79554019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.46000000834465027,"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"}},"topics":[{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.46000000834465027,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.14470000565052032,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.10769999772310257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.47360000014305115},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4090999960899353},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.39640000462532043},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.37709999084472656},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3598000109195709},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3273000121116638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737500011920929},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.47360000014305115},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4343999922275543},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4090999960899353},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3968999981880188},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.37709999084472656},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.35089999437332153},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3012000024318695},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.257099986076355}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/fccm68464.2026.00049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fccm68464.2026.00049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 34th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:385088","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/76271.html>,","pdf_url":"https://eprints.gla.ac.uk/385088/1/385088.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:385088","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/76271.html>,","pdf_url":"https://eprints.gla.ac.uk/385088/1/385088.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7164186084.pdf","grobid_xml":"https://content.openalex.org/works/W7164186084.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4378804724"],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"matrix\u2013dense":[1],"matrix":[2],"multiplication":[3],"(SpMM)":[4],"is":[5],"a":[6,71],"fundamental":[7],"kernel":[8],"in":[9],"graph":[10,12],"analytics,":[11],"neural":[13],"networks,":[14],"and":[15,46,57,102],"many":[16],"sparse":[17,77,92],"deep":[18],"learning":[19],"workloads.":[20],"However,":[21],"its":[22],"irregular":[23,40,76],"sparsity":[24],"patterns":[25],"make":[26,58],"efficient":[27],"execution":[28,82],"on":[29],"FPGAs":[30],"challenging.":[31],"Conventional":[32],"CSR-":[33],"or":[34],"COO-based":[35],"traversal":[36],"often":[37],"leads":[38],"to":[39,61],"control":[41],"flow,":[42],"fragmented":[43],"memory":[44],"accesses,":[45],"limited":[47],"reuse":[48],"of":[49],"dense":[50],"features,":[51],"which":[52],"together":[53],"reduce":[54],"pipeline":[55],"efficiency":[56],"it":[59],"difficult":[60],"sustain":[62],"high":[63],"throughput.":[64],"This":[65],"work":[66],"addresses":[67],"these":[68],"limitations":[69],"through":[70],"host\u2013FPGA":[72],"co-design":[73],"that":[74],"converts":[75],"computation":[78],"into":[79],"streamable":[80],"tile-level":[81],"units.":[83],"By":[84],"combining":[85],"sparsity-aware":[86],"data":[87,100],"reordering":[88],"with":[89],"an":[90],"execution-oriented":[91],"representation,":[93],"the":[94],"proposed":[95],"approach":[96],"enables":[97],"more":[98],"regular":[99],"movement":[101],"better":[103],"hardware":[104],"utilization.":[105]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-06-11T00:00:00"}
