{"id":"https://openalex.org/W4416004143","doi":"https://doi.org/10.1145/3731599.3767704","title":"A Peak Performance Model for All-to-all on Hierarchical Systems and Its Applications","display_name":"A Peak Performance Model for All-to-all on Hierarchical Systems and Its Applications","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004143","doi":"https://doi.org/10.1145/3731599.3767704"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767704","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767704","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731599.3767704","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5096909213","display_name":"Rohini Uma-Vaideswaran","orcid":"https://orcid.org/0000-0003-0583-6109"},"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":"Rohini Uma-Vaideswaran","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":"https://orcid.org/0000-0003-0583-6109","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030832425","display_name":"Joshua Romero","orcid":"https://orcid.org/0000-0003-1358-5565"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Romero","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0003-1358-5565","affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119671325","display_name":"Daniel L. Dotson","orcid":"https://orcid.org/0009-0007-6209-809X"},"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":"Daniel L. Dotson","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":"https://orcid.org/0009-0007-6209-809X","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055298466","display_name":"David Appelhans","orcid":"https://orcid.org/0000-0003-1433-9198"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"David Appelhans","raw_affiliation_strings":["NVIDIA Corporation, Westminster, USA"],"raw_orcid":"https://orcid.org/0000-0003-1433-9198","affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Westminster, USA","institution_ids":["https://openalex.org/I4210127875","https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005975375","display_name":"P. K. Yeung","orcid":"https://orcid.org/0000-0002-6278-6032"},"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":"P. K. Yeung","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":"https://orcid.org/0000-0002-6278-6032","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"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":"1442","last_page":"1451"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6851000189781189,"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":0.6851000189781189,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.10339999943971634,"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/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.03280000016093254,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4878000020980835},{"id":"https://openalex.org/keywords/interconnection","display_name":"Interconnection","score":0.45649999380111694},{"id":"https://openalex.org/keywords/transpose","display_name":"Transpose","score":0.44760000705718994},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4336000084877014},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.42480000853538513},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.41110000014305115},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4081000089645386},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.39739999175071716},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.35040000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741599977016449},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5824999809265137},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4878000020980835},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.44760000705718994},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C203274722","wikidata":"https://www.wikidata.org/wiki/Q7001161","display_name":"Network performance","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.301800012588501},{"id":"https://openalex.org/C158156997","wikidata":"https://www.wikidata.org/wiki/Q1416645","display_name":"Models of communication","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C4292930","wikidata":"https://www.wikidata.org/wiki/Q17009341","display_name":"Distributed element model","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.27489998936653137},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C113740112","wikidata":"https://www.wikidata.org/wiki/Q5904738","display_name":"Slab","level":2,"score":0.2662999927997589}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767704","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767704","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731599.3767704","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767704","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8189731814","display_name":"Construction for the Leadership Class Computing Facility","funder_award_id":"2323116","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":22,"referenced_works":["https://openalex.org/W1512808804","https://openalex.org/W1558115001","https://openalex.org/W1568736435","https://openalex.org/W2042120213","https://openalex.org/W2102061396","https://openalex.org/W2127589680","https://openalex.org/W2133994512","https://openalex.org/W2152719989","https://openalex.org/W2164303766","https://openalex.org/W2789166828","https://openalex.org/W2908578142","https://openalex.org/W2984602355","https://openalex.org/W3083442288","https://openalex.org/W4244682390","https://openalex.org/W4251390107","https://openalex.org/W4255744356","https://openalex.org/W4285100250","https://openalex.org/W4388662129","https://openalex.org/W4402284386","https://openalex.org/W4402702025","https://openalex.org/W4407573637","https://openalex.org/W4410554534"],"related_works":[],"abstract_inverted_index":{"An":[0],"accurate":[1],"measure":[2],"of":[3,10,27,33,36,39,45,54,82,100,116],"communication":[4,83,118],"performance":[5,15,26,91,134],"is":[6,72],"a":[7,21,37,42,80,93],"key":[8],"component":[9],"optimizing":[11],"large":[12],"scale":[13],"high":[14],"computing":[16],"applications.":[17],"This":[18],"paper":[19],"presents":[20],"model":[22,56,71,106],"for":[23,96,129],"the":[24,31,55,105,108,114,123,126],"peak":[25],"all-to-all":[28,87,130],"communication,":[29],"in":[30,64,92,122],"context":[32],"systems":[34],"composed":[35],"hierarchy":[38],"interconnect":[40],"bandwidths;":[41],"common":[43],"trait":[44],"multi-GPU":[46],"per":[47],"node":[48],"systems.":[49],"We":[50],"demonstrate":[51],"an":[52],"application":[53],"to":[57],"distributed":[58,65,89],"transposes,":[59],"such":[60],"as":[61],"those":[62],"encountered":[63],"three-dimensional":[66],"Fast":[67],"Fourier":[68],"Transforms.":[69],"The":[70],"validated":[73],"on":[74],"three":[75],"different":[76],"network":[77,124],"architectures,":[78],"using":[79],"variety":[81],"libraries,":[84],"by":[85],"measuring":[86],"and":[88,107,133],"transpose":[90],"pseudo-spectral":[94],"code":[95],"direct":[97],"numerical":[98],"simulations":[99],"3D":[101],"fluid":[102],"turbulence.":[103],"Both":[104],"validation":[109],"results":[110],"provide":[111],"insights":[112],"into":[113],"impact":[115],"fast":[117],"links":[119],"located":[120],"lower":[121],"hierarchy,":[125],"expected":[127],"scaling":[128],"bound":[131],"problems,":[132],"considerations":[135],"when":[136],"selecting":[137],"slab":[138],"(1D)":[139],"or":[140],"pencil":[141],"(2D)":[142],"domain":[143],"decompositions.":[144]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-07T00:00:00"}