{"id":"https://openalex.org/W4416004260","doi":"https://doi.org/10.1145/3731599.3767393","title":"Scaling All-to-All Operations Across Emerging Many-Core Supercomputers","display_name":"Scaling All-to-All Operations Across Emerging Many-Core Supercomputers","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004260","doi":"https://doi.org/10.1145/3731599.3767393"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767393","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767393","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/10.1145/3731599.3767393","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120109946","display_name":"Shannon Gayle Kinkead","orcid":"https://orcid.org/0009-0005-6583-7789"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shannon Gayle Kinkead","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, USA and University of New Mexico, Albuquerque, USA"],"raw_orcid":"https://orcid.org/0009-0005-6583-7789","affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, USA and University of New Mexico, Albuquerque, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046833654","display_name":"J.C. Wesley","orcid":"https://orcid.org/0009-0009-4036-0442"},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jackson Wesley","raw_affiliation_strings":["University of New Mexico, Albuquerque, USA"],"raw_orcid":"https://orcid.org/0009-0009-4036-0442","affiliations":[{"raw_affiliation_string":"University of New Mexico, Albuquerque, USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016007722","display_name":"Whit Schonbein","orcid":"https://orcid.org/0000-0003-4955-2984"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Whit Schonbein","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, USA"],"raw_orcid":"https://orcid.org/0000-0003-4955-2984","affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086898985","display_name":"David DeBonis","orcid":"https://orcid.org/0000-0002-6519-2811"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David DeBonis","raw_affiliation_strings":["Los Alamos National Laboratory (LANL), Los Alamos, USA"],"raw_orcid":"https://orcid.org/0000-0002-6519-2811","affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory (LANL), Los Alamos, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025874342","display_name":"Matthew G. F. Dosanjh","orcid":"https://orcid.org/0000-0001-5141-9176"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Dosanjh","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, USA"],"raw_orcid":"https://orcid.org/0000-0001-5141-9176","affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075734006","display_name":"Amanda Bienz","orcid":"https://orcid.org/0000-0002-8891-934X"},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amanda Bienz","raw_affiliation_strings":["University of New Mexico, Albuquerque, USA"],"raw_orcid":"https://orcid.org/0000-0002-8891-934X","affiliations":[{"raw_affiliation_string":"University of New Mexico, Albuquerque, USA","institution_ids":["https://openalex.org/I169521973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34618442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"479","last_page":"488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8709999918937683,"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":0.8709999918937683,"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":0.04729999974370003,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.013399999588727951,"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/implementation","display_name":"Implementation","score":0.663100004196167},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6047000288963318},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5871999859809875},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5171999931335449},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.35580000281333923},{"id":"https://openalex.org/keywords/parallel-processing","display_name":"Parallel processing","score":0.33959999680519104},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.288100004196167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.815500020980835},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6643999814987183},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.663100004196167},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6047000288963318},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5871999859809875},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5171999931335449},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4471000134944916},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3228999972343445},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C2775904623","wikidata":"https://www.wikidata.org/wiki/Q108529","display_name":"Tera-","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.26919999718666077},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767393","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767393","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:10.1145/3731599.3767393","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767393","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1968257152","https://openalex.org/W1988113008","https://openalex.org/W2000531806","https://openalex.org/W2011443595","https://openalex.org/W2099030945","https://openalex.org/W2127533540","https://openalex.org/W2133557963","https://openalex.org/W2138036770","https://openalex.org/W2505535144","https://openalex.org/W2535045667","https://openalex.org/W2902551881","https://openalex.org/W2932898043","https://openalex.org/W2964677345","https://openalex.org/W2998841280","https://openalex.org/W3190316384","https://openalex.org/W4285105236","https://openalex.org/W4289827868","https://openalex.org/W4295780299","https://openalex.org/W4388031372","https://openalex.org/W4388581355","https://openalex.org/W4396790354"],"related_works":[],"abstract_inverted_index":{"Performant":[0],"all-to-all":[1,23,50],"collective":[2],"operations":[3],"in":[4],"MPI":[5,79],"are":[6,18],"critical":[7],"to":[8,74],"fast":[9],"Fourier":[10],"transforms,":[11],"transposition,":[12],"and":[13,42,66],"machine":[14],"learning":[15],"applications.":[16],"There":[17],"many":[19,34],"existing":[20,64],"implementations":[21],"for":[22,52],"exchanges":[24],"on":[25,33],"emerging":[26,53],"systems,":[27],"with":[28,69],"the":[29,57],"achieved":[30],"performance":[31,61],"dependent":[32],"factors,":[35],"including":[36],"message":[37],"size,":[38],"process":[39],"count,":[40],"architecture,":[41],"parallel":[43],"system":[44,67,78],"partition.":[45],"This":[46],"paper":[47,58],"presents":[48,59],"novel":[49,70],"algorithms":[51,65,71],"many-core":[54],"systems.":[55,87],"Further,":[56],"a":[60],"analysis":[62],"against":[63],"MPI,":[68],"achieving":[72],"up":[73],"3x":[75],"speedup":[76],"over":[77],"at":[80],"32":[81],"nodes":[82],"of":[83],"state-of-the-art":[84],"Sapphire":[85],"Rapids":[86]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-07T00:00:00"}