{"id":"https://openalex.org/W4409328268","doi":"https://doi.org/10.1145/3622781.3674186","title":"GUST: Graph Edge-Coloring Utilization for Accelerating Sparse Matrix Vector Multiplication","display_name":"GUST: Graph Edge-Coloring Utilization for Accelerating Sparse Matrix Vector Multiplication","publication_year":2024,"publication_date":"2024-04-27","ids":{"openalex":"https://openalex.org/W4409328268","doi":"https://doi.org/10.1145/3622781.3674186"},"language":"en","primary_location":{"id":"doi:10.1145/3622781.3674186","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3622781.3674186","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3622781.3674186","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3622781.3674186","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112040017","display_name":"A. Gerami","orcid":"https://orcid.org/0009-0005-7542-5374"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Armin Gerami","raw_affiliation_strings":["Computer Science, University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059742939","display_name":"Bahar Asgari","orcid":"https://orcid.org/0000-0003-2305-9892"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bahar Asgari","raw_affiliation_strings":["Computer Science, University of Maryland, College Park, MD, United States of America"],"affiliations":[{"raw_affiliation_string":"Computer Science, University of Maryland, College Park, MD, United States of America","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112040017"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":2.5568,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90739096,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9973000288009644,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9973000288009644,"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9890999794006348,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9835000038146973,"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/computer-science","display_name":"Computer science","score":0.5416070222854614},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5368180274963379},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5127278566360474},{"id":"https://openalex.org/keywords/graph-coloring","display_name":"Graph coloring","score":0.5105944275856018},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.47840532660484314},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4559219479560852},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.36992859840393066},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3257293403148651},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.24657127261161804},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22059467434883118},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.19161972403526306},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.17714262008666992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1212618350982666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5416070222854614},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5368180274963379},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5127278566360474},{"id":"https://openalex.org/C76946457","wikidata":"https://www.wikidata.org/wiki/Q504843","display_name":"Graph coloring","level":3,"score":0.5105944275856018},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.47840532660484314},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4559219479560852},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36992859840393066},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3257293403148651},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.24657127261161804},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22059467434883118},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.19161972403526306},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.17714262008666992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1212618350982666},{"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3622781.3674186","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3622781.3674186","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3622781.3674186","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3622781.3674186","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3622781.3674186","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3622781.3674186","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409328268.pdf","grobid_xml":"https://content.openalex.org/works/W4409328268.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2035080386","https://openalex.org/W2168543008","https://openalex.org/W2325556328","https://openalex.org/W2766681651","https://openalex.org/W2917455221","https://openalex.org/W2950075828","https://openalex.org/W2953212265","https://openalex.org/W2971441423","https://openalex.org/W2979747168","https://openalex.org/W2998631742","https://openalex.org/W3016735325","https://openalex.org/W3016832937","https://openalex.org/W3040024858","https://openalex.org/W3093571597","https://openalex.org/W3107302690","https://openalex.org/W3126890733","https://openalex.org/W3152508978","https://openalex.org/W3157531038","https://openalex.org/W3158275024","https://openalex.org/W3198975860","https://openalex.org/W4200197440","https://openalex.org/W4200467342","https://openalex.org/W4206557440","https://openalex.org/W4211147898","https://openalex.org/W4214651231","https://openalex.org/W4249876349","https://openalex.org/W4252742548","https://openalex.org/W4281685651","https://openalex.org/W4293024216","https://openalex.org/W4312650633","https://openalex.org/W4316252394","https://openalex.org/W4318685745","https://openalex.org/W4321637350","https://openalex.org/W4380874786","https://openalex.org/W4386361584","https://openalex.org/W6966426965"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2093666864"],"abstract_inverted_index":{"Sparse":[0],"matrix-vector":[1],"multiplication":[2,56],"(SpMV)":[3],"plays":[4],"a":[5,67,78,123,128,211,240],"vital":[6],"role":[7],"in":[8,61,87,92],"various":[9,137],"scientific":[10,15],"and":[11,90,102,109,166,171,186,188,194,257],"engineering":[12],"fields,":[13],"from":[14,54,114],"computing":[16],"to":[17,34,40,105,121],"machine":[18],"learning.":[19],"Traditional":[20],"general-purpose":[21],"processors":[22],"often":[23],"fall":[24],"short":[25],"of":[26,37,69,84,148,155,169,184,192,206,222,254],"their":[27],"peak":[28],"performance":[29,112],"with":[30,136,150,174,208,238,245],"sparse":[31],"data,":[32],"leading":[33,104],"the":[35,81,93,146,199,219],"development":[36],"domain-specific":[38],"architectures":[39,141],"enhance":[41],"SpMV.":[42],"Yet,":[43],"these":[44],"specialized":[45],"approaches,":[46],"whether":[47],"tailored":[48],"explicitly":[49],"for":[50],"SpMV":[51,163,243],"or":[52],"adapted":[53],"matrix-matrix":[55],"accelerators,":[57],"still":[58],"face":[59],"challenges":[60],"fully":[62],"utilizing":[63],"hardware":[64,107,153],"resources":[65],"as":[66,210,225],"result":[68],"sparsity.":[70,115],"To":[71,197],"tackle":[72],"this":[73],"problem,":[74],"we":[75,125,202],"introduce":[76],"GUST,":[77,149],"hardware/software":[79],"co-design,":[80],"key":[82],"insight":[83],"which":[85],"lies":[86],"separating":[88],"multipliers":[89],"adders":[91],"hardware,":[94],"thereby":[95],"enabling":[96],"resource":[97,204],"sharing":[98],"across":[99],"multiple":[100],"rows":[101],"columns,":[103],"efficient":[106],"utilization":[108,154],"ameliorating":[110],"negative":[111],"impacts":[113],"Resource":[116],"sharing,":[117],"however,":[118],"can":[119],"lead":[120],"collisions,":[122],"problem":[124],"address":[126],"through":[127,213],"specially":[129],"devised":[130],"edge-coloring":[131],"scheduling":[132],"algorithm.":[133],"Our":[134],"comparisons":[135],"prior":[138],"domain":[139],"specific":[140],"using":[142],"real-world":[143],"datasets":[144],"shows":[145],"effectiveness":[147],"an":[151,181],"average":[152,182],"33.67%.":[156],"We":[157,234],"further":[158],"evaluate":[159],"GUST":[160,173,207,217,230,237,246],"by":[161],"comparing":[162],"execution":[164,249],"time":[165,250],"energy":[167,189,259],"consumption":[168,205,260],"length-256":[170,175,226],"-87":[172],"1-dimensional":[176],"systolic":[177],"array":[178],"(1D),":[179],"achieving":[180,247],"speedup":[183],"411\u00d7":[185],"108\u00d7,":[187],"efficiency":[190],"improvement":[191],"137\u00d7":[193],"148\u00d7,":[195],"respectively.":[196],"asses":[198],"implementation":[200],"aspect,":[201],"compare":[203,236],"1D":[209],"baseline":[212],"FPGA":[214],"synthesis.":[215],"Length-256":[216],"uses":[218,231],"same":[220],"number":[221],"arithmetic":[223],"units":[224],"1D,":[227],"while":[228],"length-87":[229],"considerably":[232],"less.":[233],"also":[235],"Serpens,":[239],"state-of-the-art":[241],"FPGA-based":[242],"accelerator,":[244],"lower":[248,258],"on":[251,261],"seven":[252],"out":[253],"nine":[255],"matrices":[256],"four.":[262]},"counts_by_year":[{"year":2025,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}