{"id":"https://openalex.org/W4316252394","doi":"https://doi.org/10.1145/3545008.3545053","title":"Mentha: Enabling Sparse-Packing Computation on Systolic Arrays","display_name":"Mentha: Enabling Sparse-Packing Computation on Systolic Arrays","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4316252394","doi":"https://doi.org/10.1145/3545008.3545053"},"language":"en","primary_location":{"id":"doi:10.1145/3545008.3545053","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3545008.3545053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 51st International Conference on Parallel Processing","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/A5072361503","display_name":"Minjin Tang","orcid":"https://orcid.org/0009-0000-2254-4912"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minjin Tang","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101937502","display_name":"Mei Wen","orcid":"https://orcid.org/0000-0002-5875-3297"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Wen","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057268141","display_name":"Yasong Cao","orcid":"https://orcid.org/0009-0003-7683-989X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yasong Cao","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037428152","display_name":"Junzhong Shen","orcid":"https://orcid.org/0000-0001-6233-6800"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhong Shen","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianchao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianchao Yang","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014208203","display_name":"Jiawei Fei","orcid":"https://orcid.org/0000-0001-9325-0516"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Fei","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720832","display_name":"Yang Guo","orcid":"https://orcid.org/0000-0001-9050-0866"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Guo","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100320010","display_name":"Sheng Liu","orcid":"https://orcid.org/0000-0003-2731-9591"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Liu","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.9137,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.75895623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.998199999332428,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9966999888420105,"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/systolic-array","display_name":"Systolic array","score":0.7920188903808594},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6748497486114502},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6424002647399902},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.6349331140518188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5656008124351501},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5458312034606934},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5265771746635437},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.48789235949516296},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.483639121055603},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.45548030734062195},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4446742832660675},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40994033217430115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28186658024787903},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.13506776094436646},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.12338602542877197},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.09151804447174072},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.084562748670578}],"concepts":[{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.7920188903808594},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6748497486114502},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6424002647399902},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.6349331140518188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5656008124351501},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5458312034606934},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5265771746635437},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.48789235949516296},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.483639121055603},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.45548030734062195},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4446742832660675},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40994033217430115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28186658024787903},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.13506776094436646},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.12338602542877197},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.09151804447174072},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.084562748670578},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3545008.3545053","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3545008.3545053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2035080386","https://openalex.org/W2285660444","https://openalex.org/W2560674852","https://openalex.org/W2585720638","https://openalex.org/W2606722458","https://openalex.org/W2625457103","https://openalex.org/W2747329762","https://openalex.org/W2773750423","https://openalex.org/W2900228909","https://openalex.org/W2904902077","https://openalex.org/W2914631005","https://openalex.org/W2915106038","https://openalex.org/W2979310060","https://openalex.org/W2979439447","https://openalex.org/W2980186997","https://openalex.org/W3016832937","https://openalex.org/W3040024858","https://openalex.org/W3092156174","https://openalex.org/W3100023286","https://openalex.org/W3102587717","https://openalex.org/W3105802176","https://openalex.org/W3185702163"],"related_works":["https://openalex.org/W2022229285","https://openalex.org/W46448156","https://openalex.org/W2283084692","https://openalex.org/W2130878144","https://openalex.org/W3172158163","https://openalex.org/W2150609674","https://openalex.org/W2138404091","https://openalex.org/W3034729708","https://openalex.org/W2078475991","https://openalex.org/W2380696053"],"abstract_inverted_index":{"Generalized":[0],"Sparse":[1],"Matrix-Matrix":[2],"Multiplication":[3],"(SpGEMM)":[4],"is":[5,131,198],"a":[6,18,75,88,156,209],"critical":[7],"kernel":[8],"in":[9,69,119,152,160,163,176,182,215],"domains":[10],"like":[11],"graph":[12],"analytic":[13],"and":[14,103,125,165,180],"scientific":[15],"computation.":[16],"As":[17],"kind":[19],"of":[20,95,112,128,178,184,212],"classical":[21,37],"special-purpose":[22],"architecture,":[23],"systolic":[24,38,79,96,153,172],"arrays":[25,39,80,154,173],"were":[26],"first":[27],"used":[28],"for":[29,92],"complex":[30],"computing":[31],"problems,":[32],"e.g.,":[33],"matrix":[34,84,121,130],"multiplication.":[35],"However,":[36],"are":[40,122],"not":[41,63],"efficient":[42],"enough":[43],"when":[44,186],"handling":[45],"sparse":[46,83,114,190],"matrices":[47,191],"due":[48],"to":[49,65,81],"the":[50,53,66,108,113,116,120,126,129,141,216],"fact":[51],"that":[52,61,77,167],"PEs":[54,151],"containing":[55],"zero-valued":[56,117],"entries":[57],"perform":[58],"unnecessary":[59],"operations":[60],"do":[62],"contribute":[64],"result.":[67],"Accordingly,":[68],"this":[70],"paper,":[71],"we":[72,149],"propose":[73],"Mentha,":[74],"framework":[76],"enables":[78],"accelerate":[82],"computation":[85],"by":[86,140,174],"employing":[87],"sparse-packing":[89],"algorithm":[90],"suitable":[91],"various":[93],"dataflow":[94],"array.":[97],"Firstly,":[98],"Mentha":[99],"supports":[100],"both":[101],"online":[102],"offline":[104],"methods.":[105],"By":[106],"packing":[107],"rows":[109],"or":[110],"columns":[111],"matrix,":[115],"items":[118],"significantly":[123],"reduced":[124],"density":[127],"improved.":[132],"In":[133],"addition,":[134],"acceleration":[135],"benefits":[136],"can":[137],"be":[138],"obtained":[139],"adaptation":[142],"scheme":[143],"even":[144],"with":[145,188],"limited":[146],"resources.":[147],"Moreover,":[148],"reconfigure":[150],"at":[155,199],"low":[157],"cost":[158],"(1.28x":[159],"area,":[161],"1.21x":[162],"power)":[164],"find":[166],"our":[168],"method":[169],"outperforms":[170],"TPU-like":[171],"1.2~3.3x":[175],"terms":[177,183],"SpMM":[179],"1.3~4.4x":[181],"SpGEMM":[185],"dealing":[187],"moderately":[189],"(sparsity":[192],"<":[193],"0.9),":[194],"while":[195],"its":[196],"performance":[197],"least":[200],"9.7x":[201],"better":[202],"than":[203],"cuSPARSE.":[204],"Furthermore,":[205],"experimental":[206],"results":[207],"show":[208],"FLOPs":[210],"reduction":[211],"roughly":[213],"3.4x":[214],"neural":[217],"network.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}