{"id":"https://openalex.org/W4411055228","doi":"https://doi.org/10.1109/tetc.2025.3574508","title":"What, When, Where to Compute-in-Memory for Efficient Matrix Multiplication During Machine Learning Inference","display_name":"What, When, Where to Compute-in-Memory for Efficient Matrix Multiplication During Machine Learning Inference","publication_year":2025,"publication_date":"2025-06-05","ids":{"openalex":"https://openalex.org/W4411055228","doi":"https://doi.org/10.1109/tetc.2025.3574508"},"language":"en","primary_location":{"id":"doi:10.1109/tetc.2025.3574508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2025.3574508","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"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 Emerging Topics in Computing","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":"https://openalex.org/A5031858360","display_name":"T. P. Sharma","orcid":"https://orcid.org/0000-0001-8307-5785"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanvi Sharma","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-8307-5785","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042118220","display_name":"Mustafa Ali","orcid":"https://orcid.org/0000-0002-4452-6464"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mustafa Ali","raw_affiliation_strings":["Azure Hardware Systems & Infrastructure, Microsoft, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4452-6464","affiliations":[{"raw_affiliation_string":"Azure Hardware Systems & Infrastructure, Microsoft, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036923158","display_name":"Indranil Chakraborty","orcid":"https://orcid.org/0000-0003-4829-3706"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Indranil Chakraborty","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0003-4829-3706","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031161187","display_name":"Kaushik Roy","orcid":"https://orcid.org/0000-0002-0735-9695"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaushik Roy","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-0735-9695","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5295,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62617002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":"3","first_page":"1215","last_page":"1229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9968000054359436,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9968000054359436,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9965999722480774,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7803486585617065},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6323440074920654},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6060656905174255},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4736056327819824},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4018441438674927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3967244327068329},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36017143726348877},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.3570955693721771},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11537683010101318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803486585617065},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6323440074920654},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6060656905174255},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4736056327819824},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4018441438674927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3967244327068329},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36017143726348877},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3570955693721771},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11537683010101318},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetc.2025.3574508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2025.3574508","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"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 Emerging Topics in Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1999085092","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2415655736","https://openalex.org/W2588191434","https://openalex.org/W2896457183","https://openalex.org/W2913104037","https://openalex.org/W2914532769","https://openalex.org/W2940862705","https://openalex.org/W2947737663","https://openalex.org/W2950138172","https://openalex.org/W2969812992","https://openalex.org/W2976137532","https://openalex.org/W2981751377","https://openalex.org/W3011446983","https://openalex.org/W3013739639","https://openalex.org/W3015432327","https://openalex.org/W3017521908","https://openalex.org/W3044248149","https://openalex.org/W3106120796","https://openalex.org/W3111721177","https://openalex.org/W3134526034","https://openalex.org/W3159353913","https://openalex.org/W3161604716","https://openalex.org/W3161867321","https://openalex.org/W4220958508","https://openalex.org/W4221038786","https://openalex.org/W4236868170","https://openalex.org/W4280578694","https://openalex.org/W4281644153","https://openalex.org/W4292119927","https://openalex.org/W4292169167","https://openalex.org/W4302296459","https://openalex.org/W4308083849","https://openalex.org/W4312949026","https://openalex.org/W4322718253","https://openalex.org/W4360605483","https://openalex.org/W4360605969","https://openalex.org/W4360606939","https://openalex.org/W4376134047","https://openalex.org/W4378942239","https://openalex.org/W4386763973"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W2057797376","https://openalex.org/W2090319426","https://openalex.org/W752783541","https://openalex.org/W2036954759","https://openalex.org/W2506252583","https://openalex.org/W1506547947","https://openalex.org/W4406620725","https://openalex.org/W2048249848"],"abstract_inverted_index":{"Matrix":[0],"multiplication":[1,15],"is":[2,57,82],"the":[3,154,160,193,208],"dominant":[4],"computation":[5],"during":[6],"Machine":[7],"Learning":[8],"(ML)":[9],"inference.":[10],"To":[11,109],"efficiently":[12],"perform":[13],"such":[14,36,111],"operations,":[16],"Compute-in-memory":[17],"(CiM)":[18],"paradigms":[19],"have":[20],"emerged":[21],"as":[22,37],"a":[23,45,68,145,164],"highly":[24],"energy":[25,174],"efficient":[26,212],"solution.":[27],"However,":[28],"integrating":[29],"compute":[30,73],"in":[31,207],"memory":[32,71,94,172],"poses":[33],"key":[34],"questions,":[35],"1)What":[38],"type":[39],"of":[40,47,70,156,163,199],"CiM":[41,48,81,107,115,147,157,170,200],"to":[42,60,78,90,135,185,201],"use:":[43],"Given":[44],"multitude":[46],"design":[49],"characteristics,":[50],"determining":[51],"their":[52],"suitability":[53],"from":[54],"architecture":[55],"perspective":[56],"needed.":[58],"2)When":[59],"use":[61,122],"CiM:":[62,92],"ML":[63,119],"inference":[64],"includes":[65],"workloads":[66],"with":[67,127,188],"variety":[69],"and":[72,99,140,149,167],"requirements,":[74],"making":[75],"it":[76,206],"difficult":[77],"identify":[79],"when":[80],"more":[83],"beneficial":[84],"than":[85],"standard":[86],"processing":[87],"cores.":[88],"3)Where":[89],"integrate":[91,205],"Each":[93],"level":[95],"has":[96],"different":[97,102],"bandwidth":[98],"capacity,":[100],"creating":[101],"data":[103,142],"reuse":[104,139],"opportunities":[105],"for":[106,117,144,211],"integration.":[108],"answer":[110],"questions":[112],"regarding":[113],"on-chip":[114],"integration":[116,155],"accelerating":[118],"workloads,":[120],"we":[121],"an":[123],"analytical":[124],"architecture-evaluation":[125],"methodology":[126],"tailored":[128],"mapping":[129,132],"algorithm.":[130],"The":[131],"algorithm":[133],"aims":[134],"achieve":[136],"highest":[137],"weight":[138],"reduced":[141],"movements":[143],"given":[146],"prototype":[148],"workload.":[150],"Our":[151],"analysis":[152],"considers":[153],"prototypes":[158],"into":[159],"cache":[161,209],"levels":[162],"tensor-core-like":[165],"architecture,":[166],"shows":[168],"that":[169],"integrated":[171],"improves":[173],"efficiency":[175],"by":[176,181],"up":[177,182],"to$3.4":[178],"\\times$and":[179],"throughput":[180],"to$15.6":[183],"\\times$compared":[184],"established":[186],"baseline":[187],"INT-8":[189],"precision.":[190],"We":[191],"believe":[192],"proposed":[194],"work":[195],"provides":[196],"insights":[197],"intowhattype":[198],"use,":[202],"andwhenandwhereto":[203],"optimally":[204],"hierarchy":[210],"matrix":[213],"multiplication.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}