{"id":"https://openalex.org/W4415594537","doi":"https://doi.org/10.1109/tc.2025.3624920","title":"HighP: In-Memory Acceleration of SpGEMM With High Bank-Level Parallelism","display_name":"HighP: In-Memory Acceleration of SpGEMM With High Bank-Level Parallelism","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4415594537","doi":"https://doi.org/10.1109/tc.2025.3624920"},"language":null,"primary_location":{"id":"doi:10.1109/tc.2025.3624920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2025.3624920","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-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":null,"display_name":"Dan Chen","orcid":"https://orcid.org/0000-0003-4158-5239"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dan Chen","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-4158-5239","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064127766","display_name":"Huize Li","orcid":"https://orcid.org/0000-0002-8710-4472"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huize Li","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-8710-4472","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081598354","display_name":"Huiying Lan","orcid":"https://orcid.org/0000-0003-3120-5773"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210162847","display_name":"Lumen (United Kingdom)","ror":"https://ror.org/05fexxx29","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210162847"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huiying Lan","raw_affiliation_strings":["Lumai, OX3 8SB Oxford, U.K","Lumai, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lumai, OX3 8SB Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Lumai, Oxford, United Kingdom","institution_ids":["https://openalex.org/I4210162847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046379562","display_name":"Zhaoying Li","orcid":"https://orcid.org/0000-0001-7513-9494"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhaoying Li","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7513-9494","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pengcheng Yao","orcid":"https://orcid.org/0000-0003-4701-2239"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Yao","raw_affiliation_strings":["School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-4701-2239","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049237676","display_name":"Tulika Mitra","orcid":"https://orcid.org/0000-0003-4136-4188"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tulika Mitra","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-4136-4188","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9389,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81467924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"75","issue":"1","first_page":"139","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987000226974487,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987000226974487,"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":0.9965999722480774,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9824000000953674,"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/bottleneck","display_name":"Bottleneck","score":0.5751000046730042},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5557000041007996},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.44020000100135803},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43799999356269836},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43529999256134033},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4049000144004822},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4016000032424927},{"id":"https://openalex.org/keywords/memory-architecture","display_name":"Memory architecture","score":0.4009999930858612},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.37860000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8529999852180481},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6664999723434448},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5751000046730042},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5557000041007996},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4049000144004822},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4016000032424927},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.35510000586509705},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.32179999351501465},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C123593499","wikidata":"https://www.wikidata.org/wiki/Q6008583","display_name":"In-Memory Processing","level":5,"score":0.28519999980926514},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2653000056743622},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C177950962","wikidata":"https://www.wikidata.org/wiki/Q10997658","display_name":"Non-volatile memory","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2025.3624920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2025.3624920","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G913999031","display_name":null,"funder_award_id":"MOE-MOET32024-0003","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1515144947","https://openalex.org/W2024818089","https://openalex.org/W2034861439","https://openalex.org/W2035080386","https://openalex.org/W2045431893","https://openalex.org/W2114440330","https://openalex.org/W2483136543","https://openalex.org/W2605347906","https://openalex.org/W2612654866","https://openalex.org/W2794952988","https://openalex.org/W2795118915","https://openalex.org/W2897709121","https://openalex.org/W2904295992","https://openalex.org/W2923014074","https://openalex.org/W2962903741","https://openalex.org/W3016832937","https://openalex.org/W3042598257","https://openalex.org/W3100710793","https://openalex.org/W3103168911","https://openalex.org/W3146763006","https://openalex.org/W3155004489","https://openalex.org/W3155922894","https://openalex.org/W3158275024","https://openalex.org/W3205727737","https://openalex.org/W3206453033","https://openalex.org/W4239722617","https://openalex.org/W4242679152","https://openalex.org/W4243519499","https://openalex.org/W4285504044","https://openalex.org/W4318540786","https://openalex.org/W4327503237","https://openalex.org/W4380875717","https://openalex.org/W4386709686","https://openalex.org/W4388101094","https://openalex.org/W4401408710","https://openalex.org/W4408846943"],"related_works":[],"abstract_inverted_index":{"Generalized":[0],"sparse":[1],"matrix-matrix":[2],"multiplication":[3],"(SpGEMM)":[4],"is":[5,11,25,45,73,90],"a":[6,26,68,121,134,149],"critical":[7],"computational":[8,177],"primitive":[9],"that":[10,91],"highly":[12],"memory-bound":[13],"due":[14,62],"to":[15,29,52,63,171,180,188,193,201],"its":[16],"inherent":[17],"irregular":[18],"data-dependent":[19],"access":[20],"pattern.":[21],"Near-bank":[22],"processing-in-memory":[23],"(PIM)":[24],"promising":[27],"technique":[28],"overcome":[30],"the":[31,40,43,55,194,206],"memory":[32,57,71,167],"bottleneck":[33],"of":[34,100],"SpGEMM":[35,61,126,196],"by":[36],"performing":[37,60],"computations":[38],"near":[39],"bank":[41],"where":[42,97],"data":[44,182],"stored.":[46],"However,":[47],"earlier":[48],"PIM":[49,123,151,208],"studies":[50],"fail":[51],"fully":[53],"utilize":[54],"high":[56,128,176],"bandwidth":[58,72],"when":[59],"low":[64],"bank-level":[65,129],"parallelism.":[66,130],"As":[67],"result,":[69],"80%":[70],"wasted":[74],"as":[75],"observed":[76],"in":[77,87,95,114],"our":[78],"in-depth":[79],"experimental":[80],"analysis.":[81],"<p":[82],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[83],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Our":[84],"key":[85],"insight":[86],"this":[88],"paper":[89],"non-conflicting":[92,140],"matrix":[93],"columns":[94,102,141],"SpGEMM,":[96],"each":[98],"row":[99],"these":[101],"has":[103],"no":[104],"more":[105],"than":[106],"one":[107],"non-zero":[108],"element,":[109],"can":[110],"be":[111],"processed":[112],"simultaneously":[113],"different":[115],"banks.":[116],"We":[117,131,146],"hence":[118],"propose":[119,133],"HighP,":[120],"near-bank":[122],"accelerator":[124,197],"for":[125,159],"with":[127,153,175],"first":[132],"set-based":[135],"search":[136],"mechanism,":[137],"which":[138],"finds":[139],"through":[142],"set":[143,173],"operations":[144,174],"automatically.":[145],"then":[147],"develop":[148],"DIMM-based":[150],"architecture":[152],"detailed":[154],"hardware":[155],"and":[156,164,179,198],"workflow":[157],"designs":[158],"SpGEMM.":[160],"Set":[161],"operation":[162],"logic":[163],"unified":[165],"scratchpad":[166],"management":[168],"are":[169],"designed":[170],"perform":[172],"parallelism":[178],"enhance":[181],"reuse,":[183],"respectively.":[184],"HighP":[185],"provides":[186],"up":[187,200],"17.88\u00d7":[189],"performance":[190,203],"improvement":[191,204],"compared":[192],"state-of-th-eart":[195],"achieves":[199],"8.19\u00d7":[202],"over":[205],"state-of-the-art":[207],"solution.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-12T23:16:27.785689","created_date":"2025-10-28T00:00:00"}
