{"id":"https://openalex.org/W7162449978","doi":"https://doi.org/10.1109/ispass69572.2026.00016","title":"HARMONI: Hierarchical ARchitecture MOdeling for LLMs with Near/In Memory Computing","display_name":"HARMONI: Hierarchical ARchitecture MOdeling for LLMs with Near/In Memory Computing","publication_year":2026,"publication_date":"2026-04-26","ids":{"openalex":"https://openalex.org/W7162449978","doi":"https://doi.org/10.1109/ispass69572.2026.00016"},"language":null,"primary_location":{"id":"doi:10.1109/ispass69572.2026.00016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass69572.2026.00016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046178447","display_name":"Khyati Kiyawat","orcid":"https://orcid.org/0000-0001-6535-8220"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khyati Kiyawat","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018295880","display_name":"Yasas Seneviratne","orcid":"https://orcid.org/0009-0000-9052-4374"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yasas Seneviratne","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050900455","display_name":"Ziyao Fan","orcid":"https://orcid.org/0009-0005-1379-6698"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenxing Fan","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092392091","display_name":"Morteza Baradaran","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Morteza Baradaran","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074818897","display_name":"Kevin Skadron","orcid":"https://orcid.org/0000-0002-8091-9302"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Skadron","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49841986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.19200000166893005,"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":0.19200000166893005,"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/T11424","display_name":"Security and Verification in Computing","score":0.12729999423027039,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.10100000351667404,"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/architecture","display_name":"Architecture","score":0.4339999854564667},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.32919999957084656},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.2538999915122986},{"id":"https://openalex.org/keywords/systems-architecture","display_name":"Systems architecture","score":0.24410000443458557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6592000126838684},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.2538999915122986},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2515999972820282},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.24410000443458557},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.23739999532699585},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.23680000007152557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispass69572.2026.00016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass69572.2026.00016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2015840019","https://openalex.org/W2118231264","https://openalex.org/W2157225945","https://openalex.org/W3006586535","https://openalex.org/W3096425133","https://openalex.org/W3206328251","https://openalex.org/W4251599208","https://openalex.org/W4280496502","https://openalex.org/W4293731257","https://openalex.org/W4297097348","https://openalex.org/W4385245566","https://openalex.org/W4387321091","https://openalex.org/W4388757726","https://openalex.org/W4392427708","https://openalex.org/W4394998968","https://openalex.org/W4395073431","https://openalex.org/W4395106409","https://openalex.org/W4399402229","https://openalex.org/W4400985603","https://openalex.org/W4401211704","https://openalex.org/W4403635905","https://openalex.org/W4404848672","https://openalex.org/W4404955001","https://openalex.org/W4406266076","https://openalex.org/W4407425079","https://openalex.org/W4408925909","https://openalex.org/W4409248687","https://openalex.org/W4409248815","https://openalex.org/W4409326216","https://openalex.org/W4411019820","https://openalex.org/W4412987267","https://openalex.org/W4412987431","https://openalex.org/W4413360549","https://openalex.org/W4414197041","https://openalex.org/W7133224090"],"related_works":[],"abstract_inverted_index":{"LLM":[0,64],"inference":[1,36,70,98,144],"has":[2],"emerged":[3],"as":[4],"a":[5,50,73,125],"strongly":[6],"memory-bound":[7],"workload":[8],"suitable":[9],"for":[10,59,128],"Processing-in-Memory":[11],"(PIM)":[12],"and":[13,30,40,76,88,108,111,133,146],"Processing-near-Memory":[14],"(PNM)":[15],"architectures.":[16],"Yet,":[17],"most":[18],"existing":[19],"PIM-LLM":[20],"evaluation":[21],"frameworks":[22],"are":[23],"in-house,":[24],"closed-source,":[25],"or":[26,38],"difficult":[27],"to":[28,33],"extend,":[29],"often":[31],"fail":[32],"model":[34],"end-to-end":[35],"behavior":[37],"tensor-allocation":[39],"communication":[41],"effects":[42],"that":[43],"critically":[44],"shape":[45],"performance.":[46],"We":[47],"introduce":[48],"HARMONI,":[49],"fast,":[51],"modular,":[52],"memory-centric":[53,147],"performance":[54],"modeling":[55],"framework":[56],"designed":[57],"specifically":[58],"hierarchical":[60],"PIM/PNM":[61,131],"architectures":[62],"running":[63],"workloads.":[65],"HARMONI":[66,104,124],"captures":[67],"the":[68],"complete":[69],"execution":[71],"through":[72],"task-graph":[74],"representation":[75],"supports":[77],"user-defined":[78],"tensor":[79],"allocation":[80],"with":[81],"address-interleaving":[82],"schemes.":[83],"It":[84],"models":[85],"computation,":[86],"communication,":[87],"queuing":[89],"delays":[90],"across":[91],"logic":[92,102],"nodes,":[93],"enabling":[94,140],"realistic":[95],"mapping":[96],"of":[97,143],"kernels":[99],"onto":[100],"heterogeneous":[101],"nodes.":[103],"outputs":[105],"detailed,":[106],"kernel-wise":[107],"resource-wise":[109],"time":[110],"energy":[112],"breakdowns,":[113],"providing":[114],"actionable":[115],"visibility":[116],"into":[117],"architectural":[118],"bottlenecks.":[119],"Together,":[120],"these":[121],"capabilities":[122],"make":[123],"practical":[126],"tool":[127],"rapidly":[129],"evaluating":[130],"designs":[132],"DRAM":[134],"standards":[135],"(e.g.,":[136],"DDR4,":[137],"DDR5,":[138],"GDDR6),":[139],"systematic":[141],"co-evaluation":[142],"workloads":[145],"architecture":[148],"designs.":[149]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-27T00:00:00"}