{"id":"https://openalex.org/W7133296031","doi":"https://doi.org/10.1109/tpds.2026.3670145","title":"<i>fPIM:</i> A Holistic Design to Optimize PIM Data Flow for High Execution Efficiency","display_name":"<i>fPIM:</i> A Holistic Design to Optimize PIM Data Flow for High Execution Efficiency","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133296031","doi":"https://doi.org/10.1109/tpds.2026.3670145"},"language":null,"primary_location":{"id":"doi:10.1109/tpds.2026.3670145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2026.3670145","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","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/A5051120907","display_name":"Nan Wang","orcid":"https://orcid.org/0000-0003-1478-7134"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Wang","raw_affiliation_strings":["Department of Computer and Information Sciences, Temple University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1478-7134","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, Temple University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101313121","display_name":"Wenjie Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenjie Liu","raw_affiliation_strings":["Department of Computer and Information Sciences, Temple University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7675-8983","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, Temple University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003397450","display_name":"Qing Liu","orcid":"https://orcid.org/0000-0002-6252-5887"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Liu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087956045","display_name":"Xubin He","orcid":"https://orcid.org/0000-0002-5071-2861"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xubin He","raw_affiliation_strings":["Department of Computer and Information Sciences, Temple University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5071-2861","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, Temple University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I84392919"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25161847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"5","first_page":"1096","last_page":"1106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.06689999997615814,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.06689999997615814,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.03440000116825104,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.03060000017285347,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/workload","display_name":"Workload","score":0.6100999712944031},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5715000033378601},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5313000082969666},{"id":"https://openalex.org/keywords/design-flow","display_name":"Design flow","score":0.42160001397132874},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4065999984741211},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.40369999408721924},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.3391000032424927},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3127000033855438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8842999935150146},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6100999712944031},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5715000033378601},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5313000082969666},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5073000192642212},{"id":"https://openalex.org/C37135326","wikidata":"https://www.wikidata.org/wiki/Q931942","display_name":"Design flow","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4065999984741211},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37130001187324524},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3427000045776367},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29190000891685486},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C88468194","wikidata":"https://www.wikidata.org/wiki/Q1172416","display_name":"Data-flow analysis","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2026.3670145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2026.3670145","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4833532107","display_name":null,"funder_award_id":"CCF-2134202","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5527462769","display_name":null,"funder_award_id":"OAC-2311758","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7660703169","display_name":null,"funder_award_id":"CCF-2134203","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1979978831","https://openalex.org/W1983545421","https://openalex.org/W2019959197","https://openalex.org/W2056222607","https://openalex.org/W2079787774","https://openalex.org/W2086112773","https://openalex.org/W2136268150","https://openalex.org/W2162639668","https://openalex.org/W2234355962","https://openalex.org/W2234679013","https://openalex.org/W2332254524","https://openalex.org/W2409849629","https://openalex.org/W2474451066","https://openalex.org/W2514566830","https://openalex.org/W2556370608","https://openalex.org/W2789554134","https://openalex.org/W2888243885","https://openalex.org/W2903868561","https://openalex.org/W2907238177","https://openalex.org/W2930718998","https://openalex.org/W2979719709","https://openalex.org/W3022949655","https://openalex.org/W3043023836","https://openalex.org/W3124802618","https://openalex.org/W3129781741","https://openalex.org/W3146763006","https://openalex.org/W3157531038","https://openalex.org/W3158275024","https://openalex.org/W3165360410","https://openalex.org/W4221001402","https://openalex.org/W4233147525","https://openalex.org/W4239554475","https://openalex.org/W4245923077","https://openalex.org/W4281644153","https://openalex.org/W4281685651","https://openalex.org/W4285121610","https://openalex.org/W4292169167","https://openalex.org/W4301607055","https://openalex.org/W4308083751","https://openalex.org/W4308083849","https://openalex.org/W4322727956","https://openalex.org/W4372263745","https://openalex.org/W4378895288","https://openalex.org/W4392015341","https://openalex.org/W4400205501","https://openalex.org/W4401211602","https://openalex.org/W4409248564","https://openalex.org/W4409248659","https://openalex.org/W4409248689","https://openalex.org/W4409883018","https://openalex.org/W4410359272","https://openalex.org/W4410553137","https://openalex.org/W4414197164","https://openalex.org/W4414197520","https://openalex.org/W4414198693","https://openalex.org/W4414198840","https://openalex.org/W4415250768","https://openalex.org/W7082639760"],"related_works":[],"abstract_inverted_index":{"As":[0],"applications":[1],"demand":[2],"more":[3],"bandwidth,":[4],"the":[5,6,14,32,73,81,87,90,95,108,117,121,127,153,161],"\u201cmemory":[7],"wall\u201d":[8],"problem":[9],"becomes":[10],"increasingly":[11],"severe.":[12],"Therefore,":[13],"processing-in-memory":[15],"(PIM)":[16],"architecture":[17],"has":[18],"attracted":[19],"significant":[20],"research":[21],"interest":[22,63],"due":[23],"to":[24,27,115,138,167,199],"its":[25],"ability":[26],"execute":[28],"instructions":[29,48,61],"offloaded":[30,65],"by":[31,165],"processor.":[33],"Existing":[34],"works":[35],"on":[36],"PIM":[37,70,84,100,104,109,202],"architectures":[38,71],"are":[39,54,64],"classified":[40],"into":[41],"two":[42],"categories:":[43],"regional":[44],"offloading,":[45,58],"where":[46,59],"all":[47],"within":[49,111,120],"a":[50,99],"programmer-specified":[51],"code":[52],"region":[53],"offloaded,":[55],"and":[56,85,133,152,176,193,206],"selective":[57],"only":[60],"of":[62,83,89,184],"via":[66],"hardware":[67],"support.":[68],"However,":[69],"pose":[72],"amplified":[74],"in-PIM":[75],"traffic":[76],"overhead":[77],"challenge":[78],"that":[79,156],"endangers":[80],"performance":[82,88],"degrades":[86],"entire":[91],"system.":[92],"To":[93,143],"address":[94],"challenge,":[96],"we":[97,148],"propose":[98],"architecture,":[101],"called":[102],"fast":[103],"(fPIM),":[105],"which":[106],"integrates":[107],"cache":[110],"each":[112],"Channel":[113],"Controller":[114],"optimize":[116],"data":[118],"flow":[119],"PIM.":[122],"This":[123],"design":[124],"cooperates":[125],"with":[126],"<italic":[128,134,145,157],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[129,135,146,158,169,173,178,186,190,195],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Processing":[130],"Unit":[131],"Load-balancer</i>":[132],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Behavior-based":[136],"Offloader</i>":[137],"achieve":[139],"high":[140],"execution":[141],"efficiency.":[142],"evaluate":[144],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">fPIM</i>,":[147],"perform":[149],"extensive":[150],"experiments,":[151],"results":[154],"show":[155],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">fPIM</i>":[159],"reduces":[160],"workload":[162],"finish":[163],"time":[164],"up":[166],"<inline-formula":[168,172,177,185,189,194],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[170,174,179,187,191,196],"notation=\"LaTeX\">$88.6\\%$</tex-math></inline-formula>,":[171],"notation=\"LaTeX\">$87.5\\%$</tex-math></inline-formula>,":[175],"notation=\"LaTeX\">$79.6\\%$</tex-math></inline-formula>":[180],"(with":[181],"an":[182],"average":[183],"notation=\"LaTeX\">$68.7\\%$</tex-math></inline-formula>,":[188],"notation=\"LaTeX\">$66.2\\%$</tex-math></inline-formula>,":[192],"notation=\"LaTeX\">$59.8\\%$</tex-math></inline-formula>),":[197],"compared":[198],"three":[200],"state-of-the-art":[201],"designs,":[203],"PEI,":[204],"Fafnir,":[205],"SpaceA,":[207],"respectively.":[208]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-04T00:00:00"}