{"id":"https://openalex.org/W4393145114","doi":"https://doi.org/10.1109/mm.2024.3373763","title":"AI and Memory Wall","display_name":"AI and Memory Wall","publication_year":2024,"publication_date":"2024-03-25","ids":{"openalex":"https://openalex.org/W4393145114","doi":"https://doi.org/10.1109/mm.2024.3373763"},"language":"en","primary_location":{"id":"doi:10.1109/mm.2024.3373763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2024.3373763","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"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 Micro","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/A5114047203","display_name":"Amir Gholami","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amir Gholami","raw_affiliation_strings":["UC Berkeley, , Berkeley, CA, 94720, USA","University of California, Berkeley, United States","ICSI, United States"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, , Berkeley, CA, 94720, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"ICSI, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102915910","display_name":"Zhewei Yao","orcid":"https://orcid.org/0000-0001-7678-4321"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhewei Yao","raw_affiliation_strings":["Snowflake, Bellevue, , WA, 98004, USA","University of California, Berkeley, United States"],"affiliations":[{"raw_affiliation_string":"Snowflake, Bellevue, , WA, 98004, USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"University of California, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002255210","display_name":"Sehoon Kim","orcid":"https://orcid.org/0000-0002-9339-5480"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sehoon Kim","raw_affiliation_strings":["UC Berkeley, , Berkeley, CA, 94720, USA","University of California, Berkeley, United States"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, , Berkeley, CA, 94720, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007438902","display_name":"Coleman Hooper","orcid":"https://orcid.org/0000-0002-5890-610X"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Coleman Hooper","raw_affiliation_strings":["UC Berkeley, , Berkeley, CA, 94720, USA","University of California, Berkeley, United States"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, , Berkeley, CA, 94720, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033006662","display_name":"Michael W. Mahoney","orcid":"https://orcid.org/0000-0001-7920-4652"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael W. Mahoney","raw_affiliation_strings":["UC Berkeley, , Berkeley, CA, 94720, USA","ICSI, United States","LBNL, United States","University of California, Berkeley, United States"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, , Berkeley, CA, 94720, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"ICSI, United States","institution_ids":[]},{"raw_affiliation_string":"LBNL, United States","institution_ids":[]},{"raw_affiliation_string":"University of California, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047285420","display_name":"Kurt Keutzer","orcid":"https://orcid.org/0000-0003-3868-8501"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kurt Keutzer","raw_affiliation_strings":["UC Berkeley, , Berkeley, CA, 94720, USA","University of California, Berkeley, United States"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, , Berkeley, CA, 94720, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114047203"],"corresponding_institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":45.7949,"has_fulltext":false,"cited_by_count":223,"citation_normalized_percentile":{"value":0.99963039,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"44","issue":"3","first_page":"33","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.2542000114917755,"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"}},"topics":[{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.2542000114917755,"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":0.8005083799362183},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3642542362213135},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.361522376537323}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8005083799362183},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3642542362213135},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.361522376537323}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mm.2024.3373763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2024.3373763","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"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 Micro","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":18,"referenced_works":["https://openalex.org/W1999563089","https://openalex.org/W2002555321","https://openalex.org/W2896457183","https://openalex.org/W3031420959","https://openalex.org/W3037639655","https://openalex.org/W3129831491","https://openalex.org/W3137147200","https://openalex.org/W4225591000","https://openalex.org/W4287363917","https://openalex.org/W4292169167","https://openalex.org/W4292779060","https://openalex.org/W4322718253","https://openalex.org/W6755207826","https://openalex.org/W6768723914","https://openalex.org/W6778883912","https://openalex.org/W6790503700","https://openalex.org/W6810220367","https://openalex.org/W6850162387"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"The":[0],"availability":[1],"of":[2,55],"unprecedented":[3,16],"unsupervised":[4],"training":[5],"data,":[6],"along":[7],"with":[8],"neural":[9],"scaling":[10,49],"laws,":[11],"has":[12,47,75],"resulted":[13],"in":[14,18,84,88,116],"an":[15],"surge":[17],"model":[19,117],"size":[20],"and":[21,57,66,94,98,120],"compute":[22],"requirements":[23],"for":[24,108,113],"serving/training":[25],"LLMs.":[26],"However,":[27],"the":[28,39,53,81,105],"main":[29],"performance":[30],"bottleneck":[31,83,107],"is":[32],"increasingly":[33],"shifting":[34],"to":[35,123],"memory":[36,101,126],"bandwidth.":[37],"Over":[38],"past":[40],"20":[41],"years,":[42,71],"peak":[43],"server":[44],"hardware":[45],"FLOPS":[46],"been":[48],"at":[50,64],"3.0\u00d7/2yrs,":[51],"outpacing":[52],"growth":[54],"DRAM":[56],"interconnect":[58],"bandwidth,":[59],"which":[60],"have":[61],"only":[62],"scaled":[63],"1.6":[65],"1.4":[67],"times":[68],"every":[69],"2":[70],"respectively.":[72],"This":[73],"disparity":[74],"made":[76],"memory,":[77],"rather":[78],"than":[79],"compute,":[80],"primary":[82],"AI":[85],"applications,":[86],"particularly":[87],"serving.":[89],"Here,":[90],"we":[91],"analyze":[92],"encoder":[93],"decoder":[95,109],"Transformer":[96],"models":[97],"show":[99],"how":[100],"bandwidth":[102],"can":[103],"become":[104],"dominant":[106],"models.":[110],"We":[111],"argue":[112],"a":[114],"redesign":[115],"architecture,":[118],"training,":[119],"deployment":[121],"strategies":[122],"overcome":[124],"this":[125],"limitation.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":26},{"year":2025,"cited_by_count":159},{"year":2024,"cited_by_count":38}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2024-03-26T00:00:00"}
