{"id":"https://openalex.org/W4414210048","doi":"https://doi.org/10.1145/3731545.3731590","title":"Parameterized Algorithms for Non-uniform All-to-all","display_name":"Parameterized Algorithms for Non-uniform All-to-all","publication_year":2025,"publication_date":"2025-07-20","ids":{"openalex":"https://openalex.org/W4414210048","doi":"https://doi.org/10.1145/3731545.3731590"},"language":"en","primary_location":{"id":"doi:10.1145/3731545.3731590","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731545.3731590","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3731545.3731590?download=true","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 34th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3731545.3731590?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086407525","display_name":"Ke Fan","orcid":"https://orcid.org/0000-0002-9563-6129"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Fan","raw_affiliation_strings":["University of Illinois, Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0000-0002-9563-6129","affiliations":[{"raw_affiliation_string":"University of Illinois, Chicago, Chicago, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039069961","display_name":"Jens Domke","orcid":"https://orcid.org/0000-0002-5343-414X"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jens Domke","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5343-414X","affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015750267","display_name":"Seydou Ba","orcid":"https://orcid.org/0000-0001-8837-3116"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Seydou Ba","raw_affiliation_strings":["RIKEN Center for Computational Science (R-CCS), Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8837-3116","affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science (R-CCS), Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101815397","display_name":"Sidharth Kumar","orcid":"https://orcid.org/0009-0007-0418-9962"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sidharth Kumar","raw_affiliation_strings":["University of Illinois, Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0009-0007-0418-9962","affiliations":[{"raw_affiliation_string":"University of Illinois, Chicago, Chicago, USA","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2561,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95971917,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10829","display_name":"Interconnection Networks and Systems","score":0.9921000003814697,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/logarithm","display_name":"Logarithm","score":0.8069999814033508},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.784500002861023},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.661300003528595},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.4690999984741211},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.45329999923706055},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4113999903202057},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4068000018596649},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.36309999227523804}],"concepts":[{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.8069999814033508},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.784500002861023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7213000059127808},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.661300003528595},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.51419997215271},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.4690999984741211},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3864000141620636},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34450000524520874},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C2986651925","wikidata":"https://www.wikidata.org/wiki/Q1514868","display_name":"Graph algorithms","level":3,"score":0.3102000057697296},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731545.3731590","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731545.3731590","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3731545.3731590?download=true","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 34th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731545.3731590","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731545.3731590","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3731545.3731590?download=true","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 34th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3698157498","display_name":"Collaborative Research: PPoSS: Large: A Full-stack Approach to Declarative Analytics at Scale","funder_award_id":"2316157","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"},{"id":"https://openalex.org/F4320335125","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414210048.pdf","grobid_xml":"https://content.openalex.org/works/W4414210048.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1531516256","https://openalex.org/W1540417193","https://openalex.org/W1825216778","https://openalex.org/W2035080386","https://openalex.org/W2076167255","https://openalex.org/W2099507400","https://openalex.org/W2131613942","https://openalex.org/W2133557963","https://openalex.org/W2532546572","https://openalex.org/W2718955078","https://openalex.org/W2885707392","https://openalex.org/W2893158683","https://openalex.org/W3035481050","https://openalex.org/W3129471938","https://openalex.org/W4283397908","https://openalex.org/W4289827868","https://openalex.org/W4295780299","https://openalex.org/W4388581355","https://openalex.org/W4396790354"],"related_works":[],"abstract_inverted_index":{"MPI_Alltoallv":[0,56],"generalizes":[1],"the":[2,9,66,76,85,143,163],"uniform":[3],"all-to-all":[4],"communication":[5],"(MPI_Alltoall)":[6],"by":[7,166],"enabling":[8],"exchange":[10],"of":[11,13,50,62,68,78,168],"data-blocks":[12],"varied":[14],"sizes":[15],"among":[16],"processes.":[17],"This":[18],"function":[19],"plays":[20],"a":[21,48,119,130,159],"crucial":[22],"role":[23],"in":[24],"facilitating":[25],"many":[26],"computational":[27],"tasks,":[28],"such":[29,40,83],"as":[30,41,84],"FFT":[31],"calculations":[32],"and":[33,43,52,92,111,127,132,148,170,174],"graph":[34],"mining":[35],"operations.":[36],"Popular":[37],"MPI":[38],"libraries,":[39],"MPICH":[42],"OpenMPI,":[44],"implement":[45],"MPI_Alltoall":[46],"using":[47],"combination":[49],"linear":[51,63],"logarithmic":[53,69,121],"algorithms.":[54],"However,":[55],"typically":[57],"relies":[58],"only":[59],"on":[60,172],"variations":[61],"algorithms,":[64],"missing":[65],"benefits":[67],"approaches.":[70],"Furthermore,":[71],"current":[72],"algorithms":[73,140],"also":[74],"overlook":[75],"intricacies":[77],"modern":[79],"HPC":[80],"system":[81],"architectures,":[82],"significant":[86],"performance":[87,160],"gap":[88],"between":[89,145],"intra-node":[90],"(local)":[91],"inter-node":[93],"(global)":[94],"communication.":[95],"To":[96],"address":[97,142],"these":[98],"problems,":[99],"this":[100],"paper":[101],"presents":[102],"two":[103],"novel":[104],"algorithms:":[105],"Parameterized":[106,112],"Logarithmic":[107],"non-uniform":[108,125,137],"All-to-all":[109,115],"(ParLogNa)":[110],"Linear":[113],"nonuniform":[114],"(ParLinNa).":[116],"ParLogNa":[117],"is":[118,129],"tunable":[120,133],"time":[122],"algorithm":[123,135],"for":[124,136],"all-to-all,":[126],"ParLinNa":[128],"hierarchical":[131],"near-linear-time":[134],"all-to-all.":[138],"These":[139],"efficiently":[141],"trade-off":[144],"bandwidth":[146],"maximization":[147],"latency":[149],"minimization":[150],"that":[151],"existing":[152],"implementations":[153,165],"struggle":[154],"to":[155],"optimize.":[156],"We":[157],"show":[158],"improvement":[161],"over":[162],"state-of-the-art":[164],"factors":[167],"42x":[169],"138x":[171],"Polaris":[173],"Fugaku,":[175],"respectively.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}