{"id":"https://openalex.org/W7159822409","doi":"https://doi.org/10.1145/3801487.3806067","title":"AME-PIM: Can Memory be Your Next Tensor Accelerator?","display_name":"AME-PIM: Can Memory be Your Next Tensor Accelerator?","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7159822409","doi":"https://doi.org/10.1145/3801487.3806067"},"language":"en","primary_location":{"id":"doi:10.1145/3801487.3806067","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3806067","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3801487.3806067","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120422058","display_name":"Emanuele Venieri","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emanuele Venieri","raw_affiliation_strings":["University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0009-0007-7182-505X","affiliations":[{"raw_affiliation_string":"University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093696897","display_name":"Simone Manoni","orcid":"https://orcid.org/0000-0003-1797-1893"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone Manoni","raw_affiliation_strings":["University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0000-0003-1797-1893","affiliations":[{"raw_affiliation_string":"University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110982726","display_name":"Alberto Florian","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Florian","raw_affiliation_strings":["University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0009-0003-4890-3268","affiliations":[{"raw_affiliation_string":"University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134998100","display_name":"Jaehyun Park","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehyun Park","raw_affiliation_strings":["Samsung Electronics, Hwaseong, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-5623-6985","affiliations":[{"raw_affiliation_string":"Samsung Electronics, Hwaseong, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135037653","display_name":"Kyomin Sohn","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyomin Sohn","raw_affiliation_strings":["Samsung Electronics, Hwaseong, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-8094-9843","affiliations":[{"raw_affiliation_string":"Samsung Electronics, Hwaseong, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134937582","display_name":"Andrea Bartolini","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Bartolini","raw_affiliation_strings":["University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1148-2450","affiliations":[{"raw_affiliation_string":"University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.56582966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"232","last_page":"240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8913000226020813,"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":0.8913000226020813,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.020099999383091927,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.014800000004470348,"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/dataflow","display_name":"Dataflow","score":0.7063999772071838},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5159000158309937},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5005000233650208},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4993000030517578},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.48019999265670776},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.4659999907016754},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41760000586509705},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.39570000767707825},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3903999924659729},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.3718000054359436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8066999912261963},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.7063999772071838},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6026999950408936},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5005000233650208},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4993000030517578},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.48019999265670776},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.41839998960494995},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.39570000767707825},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3903999924659729},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.35370001196861267},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.34869998693466187},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34850001335144043},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3375000059604645},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3181999921798706},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30979999899864197},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C89377073","wikidata":"https://www.wikidata.org/wiki/Q1171224","display_name":"Indirection","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C24858836","wikidata":"https://www.wikidata.org/wiki/Q844718","display_name":"Theory of computation","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.2671999931335449},{"id":"https://openalex.org/C39528615","wikidata":"https://www.wikidata.org/wiki/Q1229610","display_name":"Distributed shared memory","level":5,"score":0.26669999957084656},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2630999982357025},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C165443888","wikidata":"https://www.wikidata.org/wiki/Q1482183","display_name":"Transformation matrix","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3801487.3806067","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3806067","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2604.27808","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.27808","pdf_url":"https://arxiv.org/pdf/2604.27808","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:cris.unibo.it:11585/1069857","is_oa":true,"landing_page_url":"https://dl.acm.org/doi/10.1145/3801487.3806067","pdf_url":"https://cris.unibo.it/bitstream/11585/1069857/1/3801487.3806067.pdf","source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3801487.3806067","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3806067","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7501878158","display_name":null,"funder_award_id":"101143421","funder_id":"https://openalex.org/F4320319825","funder_display_name":"T.C. K\u00fc\u00e7\u00fck ve Orta \u00d6l\u00e7ekli \u0130\u015fletmeleri Geli\u015ftirme ve Destekleme \u0130daresi Ba\u015fkanl\u0131\u011f\u0131"}],"funders":[{"id":"https://openalex.org/F4320319825","display_name":"T.C. K\u00fc\u00e7\u00fck ve Orta \u00d6l\u00e7ekli \u0130\u015fletmeleri Geli\u015ftirme ve Destekleme \u0130daresi Ba\u015fkanl\u0131\u011f\u0131","ror":null},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"High":[0],"Bandwidth":[1],"Memory":[2],"with":[3],"Processing-in-Memory":[4],"(HBM-PIM)":[5],"offers":[6],"an":[7],"opportunity":[8],"to":[9,72,138],"reduce":[10],"data":[11,76],"movement":[12],"by":[13],"executing":[14],"computation":[15],"directly":[16],"inside":[17],"memory,":[18],"but":[19],"current":[20],"commercial":[21],"platforms":[22],"expose":[23],"limited":[24],"instruction":[25],"sets":[26],"and":[27,69,75,113,121],"require":[28],"specialized":[29],"software":[30],"stacks.":[31],"In":[32],"this":[33],"work,":[34],"we":[35,85],"investigate":[36],"whether":[37],"HBM-PIM":[38,73],"can":[39],"serve":[40],"as":[41,55],"a":[42,56,61,87,144],"backend":[43],"for":[44],"ISA-level":[45],"matrix":[46,70,133],"acceleration,":[47],"using":[48],"the":[49,98],"RISC-V":[50],"Attached":[51],"Matrix":[52],"Extension":[53],"(AME)":[54],"semantic":[57],"reference.":[58],"We":[59],"propose":[60],"PEP-based":[62],"execution":[63,108],"model":[64],"that":[65,91,131],"maps":[66],"AME":[67,132],"element-wise":[68,110],"instructions":[71,77],"micro-kernels":[74],"in":[78,115],"memory":[79,96],"operations.":[80],"Differently":[81],"from":[82],"SoA":[83],"HBM-PIM,":[84],"introduce":[86],"reduction-free":[88],"outer-product":[89],"dataflow":[90],"enables":[92],"accumulation":[93],"entirely":[94],"within":[95],"despite":[97],"lack":[99],"of":[100,109],"native":[101],"reduction":[102],"support.":[103],"Our":[104],"approach":[105],"supports":[106],"end-to-end":[107],"operations,":[111],"GEMV,":[112],"GEMM":[114],"PIM":[116],"mode,":[117],"minimizing":[118],"host":[119],"involvement":[120],"off-chip":[122],"transfers.":[123],"An":[124],"experimental":[125],"evaluation":[126],"on":[127,143],"Samsung":[128],"Aquabolt-XL":[129],"shows":[130],"tile":[134],"multiplication":[135],"achieves":[136],"up":[137],"14.9":[139],"GFLOP/s":[140],"(59.4":[141],"FLOP/cycle)":[142],"single":[145],"HBM":[146],"pseudo-channel.":[147]},"counts_by_year":[],"updated_date":"2026-07-05T07:55:05.734416","created_date":"2026-05-03T00:00:00"}
