{"id":"https://openalex.org/W7204174288","doi":"https://doi.org/10.48550/arxiv.2608.23404","title":"VIPER: Architecture-Aware Performance Modeling for Processing-in-Memory Design-Space Exploration","display_name":"VIPER: Architecture-Aware Performance Modeling for Processing-in-Memory Design-Space Exploration","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204174288","doi":"https://doi.org/10.48550/arxiv.2608.23404"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.23404","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23404","pdf_url":"https://arxiv.org/pdf/2608.23404","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.23404","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148106128","display_name":"Haoran Geng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geng, Haoran","raw_affiliation_strings":["University of Notre Dame , Notre Dame , IN , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame , Notre Dame , IN , USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138934620","display_name":"Tomas Sousa Pereira","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pereira, Tomas Sousa","raw_affiliation_strings":["University of Notre Dame , Notre Dame , IN , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame , Notre Dame , IN , USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071271406","display_name":"Xiaoyang Lu","orcid":"https://orcid.org/0009-0005-9481-7234","observed_orcids":["https://orcid.org/0009-0005-9481-7234"]},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu, Xiaoyang","raw_affiliation_strings":["Illinois Institute of Technology , Chicago , IL , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology , Chicago , IL , USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057665558","display_name":"Xian\u2010He Sun","orcid":"https://orcid.org/0000-0002-1093-0792","observed_orcids":["https://orcid.org/0000-0002-1093-0792"]},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sun, Xian-He","raw_affiliation_strings":["Illinois Institute of Technology , Chicago , IL , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology , Chicago , IL , USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135327021","display_name":"Michael Niemier","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niemier, Michael","raw_affiliation_strings":["University of Notre Dame , Notre Dame , IN , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame , Notre Dame , IN , USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148046331","display_name":"X. Sharon Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, X. Sharon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9717000126838684,"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":0.9717000126838684,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.008899999782443047,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.005400000140070915,"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/in-memory-computing","display_name":"in-memory computing","score":0.9959999918937683},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"design space exploration","score":0.9679999947547913},{"id":"https://openalex.org/keywords/performance-modeling","display_name":"performance modeling","score":0.906000018119812},{"id":"https://openalex.org/keywords/task-offloading","display_name":"task offloading","score":0.859000027179718},{"id":"https://openalex.org/keywords/upmem","display_name":"UPMEM","score":0.7649999856948853},{"id":"https://openalex.org/keywords/resistive-random-access-memory","display_name":"resistive random access memory","score":0.5199999809265137},{"id":"https://openalex.org/keywords/data-movement-overhead","display_name":"data movement overhead","score":0.42500001192092896}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8830999732017517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8097000122070312},{"id":"https://openalex.org/C2780389661","wikidata":"https://www.wikidata.org/wiki/Q1528875","display_name":"VIPeR","level":3,"score":0.6690000295639038},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5439000129699707},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48969998955726624},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.42739999294281006},{"id":"https://openalex.org/C2910624479","wikidata":"https://www.wikidata.org/wiki/Q163656","display_name":"Viper Venoms","level":4,"score":0.4250999987125397},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.40709999203681946},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.40220001339912415},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.37860000133514404},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.311599999666214},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.2612999975681305},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.23404","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23404","pdf_url":"https://arxiv.org/pdf/2608.23404","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.2608.23404","doi":"https://doi.org/10.48550/arxiv.2608.23404","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23404","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.23404","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23404","pdf_url":"https://arxiv.org/pdf/2608.23404","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[{"score":0.5378999710083008,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204174288.pdf","grobid_xml":"https://content.openalex.org/works/W7204174288.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7171526864","https://openalex.org/W7161006499","https://openalex.org/W4401568638","https://openalex.org/W3202917172","https://openalex.org/W4406266076","https://openalex.org/W4412987208","https://openalex.org/W3185300257","https://openalex.org/W4285121610","https://openalex.org/W2900639816","https://openalex.org/W2809979730"],"abstract_inverted_index":{"Processing-in-Memory":[0],"(PIM)":[1],"promises":[2],"to":[3,205,223],"reduce":[4],"data":[5],"movement":[6],"overhead":[7],"by":[8,131],"executing":[9],"computation":[10],"in":[11],"or":[12],"near":[13],"memory,":[14],"but":[15],"its":[16],"realized":[17],"application":[18],"speedup":[19,197],"remains":[20],"highly":[21],"design-dependent.":[22],"Non-offloadable":[23],"host":[24,93,100],"execution,":[25],"host-PIM":[26,133],"transfers,":[27],"limited":[28],"PIM":[29,48,61,89],"capacity,":[30],"and":[31,54,83,96,121,128,142,165,178,233],"device":[32,139],"programming":[33,140],"latency":[34],"can":[35],"limit":[36],"end-to-end":[37,60],"speedup,":[38],"making":[39],"fast":[40],"early-stage":[41],"design-space":[42],"exploration":[43],"(DSE)":[44],"essential.":[45],"However,":[46],"existing":[47],"evaluation":[49,86,219,245],"methods":[50],"remain":[51],"limited:":[52],"circuit-":[53],"device-level":[55,244],"tools":[56],"cannot":[57],"capture":[58],"these":[59],"performance":[62,85,148,241],"factors,":[63],"while":[64,217],"cycle-accurate":[65,155,169],"simulation":[66],"is":[67],"too":[68],"slow":[69],"for":[70,88,150],"iterative":[71,151],"DSE.":[72,90],"To":[73],"address":[74],"this":[75],"gap,":[76],"we":[77],"present":[78],"VIPER,":[79],"a":[80,103,161,181,185],"unified,":[81],"lightweight,":[82],"architecture-aware":[84,147,237],"framework":[87],"VIPER":[91,159,172,211],"profiles":[92],"execution":[94,130],"once":[95],"combines":[97],"the":[98,174,190,200,206],"measured":[99,191],"behavior":[101,193],"with":[102,184,194],"PIM-aware":[104],"analytical":[105],"engine":[106],"that":[107,236,243],"sweeps":[108],"PIM-side":[109],"parameters":[110],"across":[111,199],"candidate":[112],"designs.":[113],"It":[114],"supports":[115],"both":[116],"Processing":[117,122],"Near":[118],"Memory":[119,124],"(PNM)":[120],"Using":[123],"(PUM)":[125],"under":[126,224],"task-offloading":[127],"data-triggered":[129],"capturing":[132],"transfer,":[134],"array":[135],"access,":[136],"in-memory":[137],"computation,":[138],"latency,":[141],"capacity-induced":[143],"partitioning,":[144],"providing":[145],"rapid":[146],"estimates":[149],"DSE":[152,238],"without":[153],"repeated":[154],"simulation.":[156],"We":[157],"validate":[158],"against":[160],"commercial":[162],"UPMEM":[163,175],"system":[164],"more":[166],"than":[167,214],"400":[168],"gem5":[170],"configurations.":[171],"predicts":[173],"offloading":[176],"decision":[177],"break-even":[179],"region":[180],"priori,":[182],"and,":[183],"refined":[186],"transfer":[187],"model,":[188],"captures":[189],"peak-and-rolloff":[192],"12\\%":[195],"mean":[196],"error":[198,216],"DPU":[201],"sweep":[202],"(6\\%":[203],"up":[204],"256-DPU":[207],"peak).":[208],"Against":[209],"gem5,":[210],"achieves":[212],"less":[213],"10\\%":[215],"reducing":[218],"time":[220],"from":[221],"hours":[222],"one":[225],"minute.":[226],"Case":[227],"studies":[228],"of":[229],"UPMEM,":[230],"ReRAM/FeFET":[231],"crossbars,":[232],"IMCRYPTO":[234],"show":[235],"reveals":[239],"key":[240],"trade-offs":[242],"misses.":[246]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}