{"id":"https://openalex.org/W4281733247","doi":"https://doi.org/10.1145/3489048.3522661","title":"Towards Efficient Sparse Matrix Vector Multiplication on Real Processing-In-Memory Architectures","display_name":"Towards Efficient Sparse Matrix Vector Multiplication on Real Processing-In-Memory Architectures","publication_year":2022,"publication_date":"2022-06-02","ids":{"openalex":"https://openalex.org/W4281733247","doi":"https://doi.org/10.1145/3489048.3522661"},"language":"en","primary_location":{"id":"doi:10.1145/3489048.3522661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3489048.3522661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstract Proceedings of the 2022 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems","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/A5044162748","display_name":"Christina Giannoula","orcid":"https://orcid.org/0000-0003-0162-4547"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Christina Giannoula","raw_affiliation_strings":["ETH Z\u00fcrich &amp; National Technical University of Athens, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich &amp; National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020856640","display_name":"Ivan Fernandez","orcid":"https://orcid.org/0000-0001-6133-5670"},"institutions":[{"id":"https://openalex.org/I82767444","display_name":"Universidad de M\u00e1laga","ror":"https://ror.org/036b2ww28","country_code":"ES","type":"education","lineage":["https://openalex.org/I82767444"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ivan Fernandez","raw_affiliation_strings":["ETH Z\u00fcrich &amp; University of Malaga, Malaga, Spain"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich &amp; University of Malaga, Malaga, Spain","institution_ids":["https://openalex.org/I82767444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044416322","display_name":"Juan G\u00f3mez-Luna","orcid":"https://orcid.org/0000-0002-6514-1571"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Juan G\u00f3mez-Luna","raw_affiliation_strings":["ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023526161","display_name":"Nectarios Koziris","orcid":"https://orcid.org/0000-0002-4890-8427"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nectarios Koziris","raw_affiliation_strings":["National Technical University of Athens, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023870696","display_name":"Georgios Goumas","orcid":"https://orcid.org/0000-0001-7811-4831"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Goumas","raw_affiliation_strings":["National Technical University of Athens, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050695684","display_name":"Onur Mutlu","orcid":"https://orcid.org/0000-0002-0075-2312"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Onur Mutlu","raw_affiliation_strings":["ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5044162748"],"corresponding_institution_ids":["https://openalex.org/I174458059"],"apc_list":null,"apc_paid":null,"fwci":1.8643,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84238147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9994999766349792,"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":0.844063401222229},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.670659065246582},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5296021699905396},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5267983078956604},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4981815814971924},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4324556589126587}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.844063401222229},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.670659065246582},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5296021699905396},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5267983078956604},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4981815814971924},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4324556589126587},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3489048.3522661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3489048.3522661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstract Proceedings of the 2022 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1975116854","https://openalex.org/W2170257519","https://openalex.org/W2332254524","https://openalex.org/W2944819262","https://openalex.org/W2982008795","https://openalex.org/W3101416431","https://openalex.org/W3111721177","https://openalex.org/W3115226260","https://openalex.org/W3147974890","https://openalex.org/W3159011214","https://openalex.org/W3202917172","https://openalex.org/W4312258681"],"related_works":["https://openalex.org/W2039378765","https://openalex.org/W3202552726","https://openalex.org/W2279642117","https://openalex.org/W1982351223","https://openalex.org/W1541167181","https://openalex.org/W2887282140","https://openalex.org/W2077105843","https://openalex.org/W4389888442","https://openalex.org/W2770465587","https://openalex.org/W2149529325"],"abstract_inverted_index":{"Several":[0],"manufacturers":[1],"have":[2],"already":[3],"started":[4],"to":[5,23,69,158,230,265],"commercialize":[6],"near-bank":[7],"Processing-In-Memory":[8],"(PIM)":[9],"architectures,":[10],"after":[11],"decades":[12],"of":[13,53,84,117,129,174,188,202,269],"research":[14,27],"efforts.":[15],"Near-bank":[16],"PIM":[17,47,134,145,167,193,208,214,238,250],"architectures":[18],"place":[19],"simple":[20],"cores":[21],"close":[22],"DRAM":[24],"banks.":[25],"Recent":[26],"demonstrates":[28],"that":[29],"they":[30],"can":[31,49],"yield":[32],"significant":[33,87],"performance":[34],"and":[35,59,88,113,136,165,222,227,254,280],"energy":[36],"improvements":[37],"in":[38,163,205],"parallel":[39],"applications":[40],"by":[41],"alleviating":[42],"data":[43],"access":[44,62],"costs.":[45],"Real":[46],"systems":[48],"provide":[50,183],"high":[51],"levels":[52],"parallelism,":[54],"large":[55],"aggregate":[56],"memory":[57,61,102],"bandwidth":[58],"low":[60],"latency,":[63],"thereby":[64],"being":[65],"a":[66,97,132,171,191],"good":[67],"fit":[68],"accelerate":[70,159,232],"the":[71,85,108,114,118,125,139,160,184,206,210,233,248,255,263,266,270],"Sparse":[72],"Matrix":[73],"Vector":[74],"Multiplication":[75],"(SpMV)":[76],"kernel.":[77],"SpMV":[78,130,141,156,161,189,203,234,249],"has":[79],"been":[80],"characterized":[81],"as":[82],"one":[83],"most":[86],"thoroughly":[89],"studied":[90],"scientific":[91],"computation":[92],"kernels.":[93],"It":[94],"is":[95,278],"primarily":[96],"memory-bound":[98],"kernel":[99,162,235],"with":[100,177],"intensive":[101],"accesses":[103],"due":[104],"its":[105],"algorithmic":[106],"nature,":[107],"compressed":[109],"matrix":[110],"format":[111],"used,":[112],"sparsity":[115,179],"patterns":[116],"input":[119],"matrices":[120,176],"given.":[121],"This":[122],"paper":[123,271],"provides":[124,219],"first":[126,140,185,211],"comprehensive":[127,186],"analysis":[128,187,201],"on":[131,190,236,247],"real-world":[133,213],"architecture,":[135],"presents":[137],"SparseP,":[138],"library":[142],"for":[143,224],"real":[144,192,237],"architectures.":[146],"We":[147],"make":[148],"two":[149],"key":[150],"contributions.":[151],"First,":[152],"we":[153,182,196,261],"design":[154],"efficient":[155],"algorithms":[157],"current":[164],"future":[166],"systems,":[168],"while":[169],"covering":[170],"wide":[172],"variety":[173],"sparse":[175],"diverse":[178],"patterns.":[180],"Second,":[181],"architecture.":[194,215],"Specifically,":[195],"conduct":[197],"our":[198,244],"rigorous":[199],"experimental":[200],"kernels":[204],"UPMEM":[207],"system,":[209],"publicly-available":[212],"Our":[216],"extensive":[217],"evaluation":[218],"new":[220],"insights":[221,253],"recommendations":[223],"software":[225,258,276],"designers":[226],"hardware":[228],"architects":[229],"efficiently":[231],"systems.":[239],"For":[240],"more":[241],"information":[242],"about":[243],"thorough":[245],"characterization":[246],"execution,":[251],"results,":[252],"open-source":[256],"SparseP":[257,275],"package":[259,277],"[21],":[260],"refer":[262],"reader":[264],"full":[267],"version":[268],"[3,":[272],"4].":[273],"The":[274],"publicly":[279],"freely":[281],"available":[282],"at":[283],"https://github.com/CMU-SAFARI/SparseP.":[284]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}
