{"id":"https://openalex.org/W7162392826","doi":"https://doi.org/10.1109/ispass69572.2026.00050","title":"Evaluating Cross-Architecture Performance Modeling of Distributed ML Workloads Using StableHLO","display_name":"Evaluating Cross-Architecture Performance Modeling of Distributed ML Workloads Using StableHLO","publication_year":2026,"publication_date":"2026-04-26","ids":{"openalex":"https://openalex.org/W7162392826","doi":"https://doi.org/10.1109/ispass69572.2026.00050"},"language":null,"primary_location":{"id":"doi:10.1109/ispass69572.2026.00050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass69572.2026.00050","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":"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/A5003103657","display_name":"Jonas Svedas","orcid":null},"institutions":[{"id":"https://openalex.org/I196972281","display_name":"Imec the Netherlands","ror":"https://ror.org/01ezq2j76","country_code":"NL","type":"facility","lineage":["https://openalex.org/I196972281"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jonas Svedas","raw_affiliation_strings":["20 Station Road, Cambridge CB1 2JD,imec,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"20 Station Road, Cambridge CB1 2JD,imec,UK","institution_ids":["https://openalex.org/I196972281"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059602336","display_name":"Nathan Laubeuf","orcid":"https://orcid.org/0000-0002-1592-755X"},"institutions":[{"id":"https://openalex.org/I196972281","display_name":"Imec the Netherlands","ror":"https://ror.org/01ezq2j76","country_code":"NL","type":"facility","lineage":["https://openalex.org/I196972281"]},{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE","NL"],"is_corresponding":false,"raw_author_name":"Nathan Laubeuf","raw_affiliation_strings":["Kapeldreef 75, 3001,imec,Leuven,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kapeldreef 75, 3001,imec,Leuven,Belgium","institution_ids":["https://openalex.org/I196972281","https://openalex.org/I4210114974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133637182","display_name":"Ryan Harvey","orcid":null},"institutions":[{"id":"https://openalex.org/I196972281","display_name":"Imec the Netherlands","ror":"https://ror.org/01ezq2j76","country_code":"NL","type":"facility","lineage":["https://openalex.org/I196972281"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ryan Harvey","raw_affiliation_strings":["20 Station Road, Cambridge CB1 2JD,imec,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"20 Station Road, Cambridge CB1 2JD,imec,UK","institution_ids":["https://openalex.org/I196972281"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137044175","display_name":"Arjun Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I196972281","display_name":"Imec the Netherlands","ror":"https://ror.org/01ezq2j76","country_code":"NL","type":"facility","lineage":["https://openalex.org/I196972281"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Arjun Singh","raw_affiliation_strings":["20 Station Road, Cambridge CB1 2JD,imec,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"20 Station Road, Cambridge CB1 2JD,imec,UK","institution_ids":["https://openalex.org/I196972281"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137082193","display_name":"Changhai Man","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changhai Man","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117071312","display_name":"Abubakr Nada","orcid":null},"institutions":[{"id":"https://openalex.org/I196972281","display_name":"Imec the Netherlands","ror":"https://ror.org/01ezq2j76","country_code":"NL","type":"facility","lineage":["https://openalex.org/I196972281"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Abubakr Nada","raw_affiliation_strings":["20 Station Road, Cambridge CB1 2JD,imec,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"20 Station Road, Cambridge CB1 2JD,imec,UK","institution_ids":["https://openalex.org/I196972281"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137027416","display_name":"Tushar Krishna","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tushar Krishna","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135582428","display_name":"James Myers","orcid":null},"institutions":[{"id":"https://openalex.org/I196972281","display_name":"Imec the Netherlands","ror":"https://ror.org/01ezq2j76","country_code":"NL","type":"facility","lineage":["https://openalex.org/I196972281"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"James Myers","raw_affiliation_strings":["20 Station Road, Cambridge CB1 2JD,imec,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"20 Station Road, Cambridge CB1 2JD,imec,UK","institution_ids":["https://openalex.org/I196972281"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137044923","display_name":"Debjyoti Bhattacharjee","orcid":null},"institutions":[{"id":"https://openalex.org/I196972281","display_name":"Imec the Netherlands","ror":"https://ror.org/01ezq2j76","country_code":"NL","type":"facility","lineage":["https://openalex.org/I196972281"]},{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE","NL"],"is_corresponding":false,"raw_author_name":"Debjyoti Bhattacharjee","raw_affiliation_strings":["Kapeldreef 75, 3001,imec,Leuven,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kapeldreef 75, 3001,imec,Leuven,Belgium","institution_ids":["https://openalex.org/I196972281","https://openalex.org/I4210114974"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"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":0.84195779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"448","last_page":"460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.4196000099182129,"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"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.4196000099182129,"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/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/T10101","display_name":"Cloud Computing and Resource Management","score":0.14159999787807465,"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/set","display_name":"Set (abstract data type)","score":0.2694999873638153},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.25049999356269836},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.24799999594688416},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.24369999766349792},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.24320000410079956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6256999969482422},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33500000834465027},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.25049999356269836},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.24799999594688416},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24369999766349792},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.24320000410079956},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.22849999368190765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispass69572.2026.00050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass69572.2026.00050","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":[{"id":"https://metadata.un.org/sdg/9","score":0.4805428683757782,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2057218453","https://openalex.org/W2112103101","https://openalex.org/W2155187164","https://openalex.org/W2606722458","https://openalex.org/W2954698171","https://openalex.org/W3036878841","https://openalex.org/W3102510044","https://openalex.org/W3117255825","https://openalex.org/W3132942233","https://openalex.org/W3157919170","https://openalex.org/W4290725151","https://openalex.org/W4381886086","https://openalex.org/W4381894573","https://openalex.org/W4385585365","https://openalex.org/W4388031315","https://openalex.org/W4390051523","https://openalex.org/W4392265934","https://openalex.org/W4394998532","https://openalex.org/W4401211642","https://openalex.org/W4401567198","https://openalex.org/W4404954309","https://openalex.org/W4406266040","https://openalex.org/W4407196897","https://openalex.org/W4412987267","https://openalex.org/W4415293436","https://openalex.org/W4416199145","https://openalex.org/W7133227460"],"related_works":[],"abstract_inverted_index":{"Predicting":[0],"the":[1,165,201],"performance":[2,67,88,138,187],"of":[3,69],"large-scale":[4],"distributed":[5,32,70,123,185],"machine":[6],"learning":[7],"(ML)":[8],"workloads":[9,99,132],"across":[10,102,116,140,189],"multiple":[11,87],"accelerator":[12,190],"architectures":[13,141,191],"remains":[14],"a":[15,59,76,82,180],"central":[16],"challenge":[17],"in":[18,170],"ML":[19,71,186,202],"system":[20,203],"design.":[21],"Existing":[22],"GPU":[23,172],"and":[24,46,65,93,104,127,142,148,164,192,198],"TPU":[25],"focused":[26],"simulators":[27,34],"are":[28,100],"typically":[29],"architecture-specific,":[30],"while":[31,144],"training":[33,131],"rely":[35],"on":[36],"workload-specific":[37],"analytical":[38],"models":[39],"or":[40],"costly":[41],"post-execution":[42],"traces,":[43],"limiting":[44],"portability":[45],"cross-platform":[47],"comparison.":[48],"This":[49],"work":[50],"evaluates":[51],"whether":[52],"MLIR\u2019s":[53],"StableHLO":[54,135,178],"dialect":[55],"can":[56],"serve":[57],"as":[58],"unified":[60],"workload":[61,84],"representation":[62,85],"for":[63,160,183],"cross-architecture":[64],"crossfidelity":[66],"modeling":[68,117,188],"workloads.":[72],"The":[73],"study":[74],"establishes":[75],"StableHLO-based":[77],"simulation":[78],"methodology":[79,166],"that":[80,134,177],"maps":[81],"single":[83],"onto":[86],"models,":[89],"spanning":[90],"analytical,":[91],"profiling-based,":[92],"simulator-driven":[94],"predictors.":[95],"Using":[96],"this":[97],"methodology,":[98],"evaluated":[101,152],"GPUs":[103],"TPUs":[105],"without":[106],"requiring":[107],"access":[108],"to":[109],"scaled-out":[110],"physical":[111],"systems,":[112],"enabling":[113],"systematic":[114],"comparison":[115],"fidelities.":[118],"An":[119],"empirical":[120],"evaluation":[121,196],"covering":[122],"GEMM":[124],"kernels,":[125],"ResNet,":[126],"large":[128],"language":[129],"model":[130],"demonstrates":[133],"preserves":[136],"relative":[137],"trends":[139],"fidelities,":[143],"exposing":[145],"accuracy":[146],"trade-offs":[147],"simulator":[149],"limitations.":[150],"Across":[151],"scenarios,":[153],"prediction":[154],"errors":[155],"remain":[156],"within":[157],"practical":[158],"bounds":[159],"early-stage":[161],"design":[162,204],"exploration,":[163],"reveals":[167],"fidelity-dependent":[168],"limitations":[169],"existing":[171],"simulators.":[173],"These":[174],"results":[175],"indicate":[176],"provides":[179],"viable":[181],"foundation":[182],"unified,":[184],"simulators,":[193],"supporting":[194],"reusable":[195],"workflows":[197],"crossvalidation":[199],"throughout":[200],"process.":[205]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-27T00:00:00"}