{"id":"https://openalex.org/W7125418637","doi":"https://doi.org/10.1145/3784828.3785405","title":"An analysis of memory access patterns in RISC-V vector workloads on heterogeneous memory architectures","display_name":"An analysis of memory access patterns in RISC-V vector workloads on heterogeneous memory architectures","publication_year":2026,"publication_date":"2026-01-22","ids":{"openalex":"https://openalex.org/W7125418637","doi":"https://doi.org/10.1145/3784828.3785405"},"language":null,"primary_location":{"id":"doi:10.1145/3784828.3785405","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785405","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 Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3784828.3785405","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123570272","display_name":"Ryo Yokoyama","orcid":null},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Yokoyama","raw_affiliation_strings":["Graduate School of Information Sciences, Tohoku University, Sendai City, Miyagi Prefecture, Japan"],"raw_orcid":"https://orcid.org/0009-0003-2657-765X","affiliations":[{"raw_affiliation_string":"Graduate School of Information Sciences, Tohoku University, Sendai City, Miyagi Prefecture, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005806373","display_name":"Masahito Kumagai","orcid":"https://orcid.org/0000-0002-0903-064X"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahito Kumagai","raw_affiliation_strings":["Graduate School of Information Sciences, Tohoku University, Sendai City, Miyagi Prefecture, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0903-064X","affiliations":[{"raw_affiliation_string":"Graduate School of Information Sciences, Tohoku University, Sendai City, Miyagi Prefecture, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051997684","display_name":"Kazuhiko Komatsu","orcid":"https://orcid.org/0000-0003-4463-8359"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]},{"id":"https://openalex.org/I4210093896","display_name":"Tohoku University Hospital","ror":"https://ror.org/00kcd6x60","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210093896"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiko Komatsu","raw_affiliation_strings":["Research Center for Green X-Tech, Tohoku University, Sendai City, Miyagi Prefecture, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4463-8359","affiliations":[{"raw_affiliation_string":"Research Center for Green X-Tech, Tohoku University, Sendai City, Miyagi Prefecture, Japan","institution_ids":["https://openalex.org/I201537933","https://openalex.org/I4210093896"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123608341","display_name":"Masayuki Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I103605164","display_name":"Tohoku Institute of Technology","ror":"https://ror.org/01phqre83","country_code":"JP","type":"education","lineage":["https://openalex.org/I103605164"]},{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Sato","raw_affiliation_strings":["Institute for Excellence in Higher Education, Tohoku University, Sendai City, Miyagi Prefecture, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4186-5014","affiliations":[{"raw_affiliation_string":"Institute for Excellence in Higher Education, Tohoku University, Sendai City, Miyagi Prefecture, Japan","institution_ids":["https://openalex.org/I103605164","https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123589765","display_name":"Hiroaki Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroaki Kobayashi","raw_affiliation_strings":["Graduate School of Information Sciences, Tohoku University, Sendai City, Miyagi Prefecture, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3350-1413","affiliations":[{"raw_affiliation_string":"Graduate School of Information Sciences, Tohoku University, Sendai City, Miyagi Prefecture, Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"255","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9527000188827515,"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":0.9527000188827515,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.007699999958276749,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.007300000172108412,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.48489999771118164},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4794999957084656},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4535999894142151},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4474000036716461},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4465999901294708},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4318999946117401},{"id":"https://openalex.org/keywords/interleaved-memory","display_name":"Interleaved memory","score":0.42149999737739563},{"id":"https://openalex.org/keywords/flat-memory-model","display_name":"Flat memory model","score":0.4120999872684479},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.38989999890327454},{"id":"https://openalex.org/keywords/vector-processor","display_name":"Vector processor","score":0.3662000000476837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7915999889373779},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6348000168800354},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4794999957084656},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4474000036716461},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.42149999737739563},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.4120999872684479},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.38989999890327454},{"id":"https://openalex.org/C161824985","wikidata":"https://www.wikidata.org/wiki/Q919509","display_name":"Vector processor","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C74426580","wikidata":"https://www.wikidata.org/wiki/Q719484","display_name":"Memory map","level":3,"score":0.3515999913215637},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C3720319","wikidata":"https://www.wikidata.org/wiki/Q5015937","display_name":"Cache-only memory architecture","level":5,"score":0.3334999978542328},{"id":"https://openalex.org/C133371097","wikidata":"https://www.wikidata.org/wiki/Q868014","display_name":"Non-uniform memory access","level":5,"score":0.3328000009059906},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.31690001487731934},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.30390000343322754},{"id":"https://openalex.org/C39528615","wikidata":"https://www.wikidata.org/wiki/Q1229610","display_name":"Distributed shared memory","level":5,"score":0.30140000581741333},{"id":"https://openalex.org/C41036726","wikidata":"https://www.wikidata.org/wiki/Q844824","display_name":"Physical address","level":3,"score":0.30140000581741333},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.29120001196861267},{"id":"https://openalex.org/C171675096","wikidata":"https://www.wikidata.org/wiki/Q1143380","display_name":"Extended memory","level":4,"score":0.28200000524520874},{"id":"https://openalex.org/C177950962","wikidata":"https://www.wikidata.org/wiki/Q10997658","display_name":"Non-volatile memory","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2908950501","wikidata":"https://www.wikidata.org/wiki/Q11072","display_name":"Memory problems","level":4,"score":0.27489998936653137},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C93446704","wikidata":"https://www.wikidata.org/wiki/Q449328","display_name":"Registered memory","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3784828.3785405","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785405","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 Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3784828.3785405","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785405","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 Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.910365879535675}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1975698617","https://openalex.org/W1993089791","https://openalex.org/W2003751022","https://openalex.org/W2095258606","https://openalex.org/W2124031229","https://openalex.org/W2138661001","https://openalex.org/W2165741216","https://openalex.org/W2169865228","https://openalex.org/W2606571143","https://openalex.org/W2612219836","https://openalex.org/W2902045097","https://openalex.org/W2980564817","https://openalex.org/W2996384689","https://openalex.org/W3045569623","https://openalex.org/W3102724434","https://openalex.org/W4360832003","https://openalex.org/W4386764052","https://openalex.org/W4394648225","https://openalex.org/W4395065783","https://openalex.org/W4405756223"],"related_works":[],"abstract_inverted_index":{"Vector":[0],"processors":[1,94],"that":[2,24,53,152,164,203],"benefit":[3],"from":[4],"data-level":[5],"parallelism":[6],"are":[7],"regaining":[8],"prominence":[9],"as":[10],"workloads":[11,20,130],"grow":[12],"more":[13],"data-intensive.":[14],"At":[15],"the":[16,41,76,117,128,153,180,191],"same":[17,181],"time,":[18],"these":[19,55],"require":[21],"memory":[22,50,63,69,106,124,143,147,157],"systems":[23],"offer":[25],"high":[26,31],"performance,":[27],"large":[28,67],"capacity,":[29],"and":[30,71,104,116,131,145,163,200,210],"energy":[32],"efficiency.":[33],"This":[34],"paper":[35,101],"considers":[36],"a":[37,48,60,66,110,168],"RISC-V":[38,42,111],"processor":[39],"with":[40,47,65],"vector":[43,93,105,112,142,182,209,218],"extension":[44],"(RVV)":[45],"paired":[46],"heterogeneous":[49],"architecture":[51],"(HMA)":[52],"meets":[54],"needs.":[56],"The":[57,149],"HMA":[58,215],"combines":[59],"fast":[61],"near":[62],"tier":[64],"far":[68],"tier,":[70],"places":[72],"data":[73,134,206],"to":[74],"exploit":[75],"strengths":[77],"of":[78,156],"each":[79],"tier.":[80],"Although":[81],"HMAs":[82],"have":[83],"been":[84],"studied":[85],"for":[86,91,217],"scalar":[87,103,146,211],"processors,":[88],"their":[89],"behavior":[90,187],"modern":[92],"is":[95],"less":[96],"well":[97],"understood.":[98],"Thus,":[99],"this":[100,121],"analyzes":[102],"references":[107,144,158,177],"issued":[108,178],"by":[109,139,179,208],"processor.":[113],"Using":[114],"gem5":[115],"RiVEC":[118],"benchmark":[119],"suite,":[120],"study":[122],"characterizes":[123],"access":[125,161],"patterns":[126],"in":[127,160,167,213],"RVV":[129],"investigates":[132],"how":[133],"management":[135],"can":[136],"be":[137],"improved":[138],"distinguishing":[140],"between":[141],"references.":[148],"results":[150],"show":[151],"two":[154],"types":[155],"differ":[159],"behavior,":[162],"isolating":[165],"them":[166],"PC-based":[169],"reuse":[170,186],"predictor":[171],"improves":[172],"reuse-prediction":[173],"accuracy.":[174],"In":[175],"addition,":[176],"instruction":[183],"share":[184],"similar":[185],"when":[188],"grouped":[189],"at":[190],"vector-length":[192],"granularity.":[193],"These":[194],"findings":[195],"motivate":[196],"vector/scalar-aware":[197],"placement,":[198],"prefetching,":[199],"replacement":[201],"policies":[202],"separately":[204],"manage":[205],"handled":[207],"instructions":[212],"future":[214],"designs":[216],"processors.":[219]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-01-23T00:00:00"}