{"id":"https://openalex.org/W4402044182","doi":"https://doi.org/10.1145/3625549.3658656","title":"Efficient all-to-all Collective Communication Schedules for Direct-connect Topologies","display_name":"Efficient all-to-all Collective Communication Schedules for Direct-connect Topologies","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4402044182","doi":"https://doi.org/10.1145/3625549.3658656"},"language":"en","primary_location":{"id":"doi:10.1145/3625549.3658656","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625549.3658656","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 33rd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3625549.3658656","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057455780","display_name":"Prithwish Basu","orcid":"https://orcid.org/0000-0001-8295-1878"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prithwish Basu","raw_affiliation_strings":["RTX BBN Technologies, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8295-1878","affiliations":[{"raw_affiliation_string":"RTX BBN Technologies, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101304603","display_name":"Liangyu Zhao","orcid":"https://orcid.org/0009-0007-5794-0326"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liangyu Zhao","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0009-0007-5794-0326","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067704877","display_name":"Jason Fantl","orcid":"https://orcid.org/0000-0001-7369-5585"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jason Fantl","raw_affiliation_strings":["RTX BBN Technologies, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7369-5585","affiliations":[{"raw_affiliation_string":"RTX BBN Technologies, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055768967","display_name":"Siddharth Pal","orcid":"https://orcid.org/0000-0001-6509-6267"},"institutions":[{"id":"https://openalex.org/I4210121768","display_name":"Radikal Therapeutics","ror":"https://ror.org/02t4f0726","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121768"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Pal","raw_affiliation_strings":["RTX BBN Technologies, Cambridge, MA, United States"],"raw_orcid":"https://orcid.org/0000-0001-6509-6267","affiliations":[{"raw_affiliation_string":"RTX BBN Technologies, Cambridge, MA, United States","institution_ids":["https://openalex.org/I4210121768"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101497042","display_name":"Arvind Krishnamurthy","orcid":"https://orcid.org/0000-0002-9505-9528"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arvind Krishnamurthy","raw_affiliation_strings":["University of Washington, Seattle, WA, United States"],"raw_orcid":"https://orcid.org/0000-0002-9505-9528","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, United States","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019286093","display_name":"Joud Khoury","orcid":"https://orcid.org/0000-0002-9030-5208"},"institutions":[{"id":"https://openalex.org/I4210121768","display_name":"Radikal Therapeutics","ror":"https://ror.org/02t4f0726","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121768"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joud Khoury","raw_affiliation_strings":["RTX BBN Technologies, Cambridge, MA, United States"],"raw_orcid":"https://orcid.org/0000-0002-9030-5208","affiliations":[{"raw_affiliation_string":"RTX BBN Technologies, Cambridge, MA, United States","institution_ids":["https://openalex.org/I4210121768"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8733,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86646525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"28","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9998999834060669,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998999834060669,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9939000010490417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.8247143626213074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6547918915748596},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.5155072212219238},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4647122621536255}],"concepts":[{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.8247143626213074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6547918915748596},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.5155072212219238},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4647122621536255}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3625549.3658656","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625549.3658656","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 33rd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3625549.3658656","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625549.3658656","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 33rd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W779866412","https://openalex.org/W1501077214","https://openalex.org/W1591532709","https://openalex.org/W1979796968","https://openalex.org/W2020899710","https://openalex.org/W2035652501","https://openalex.org/W2038423000","https://openalex.org/W2063999066","https://openalex.org/W2104487100","https://openalex.org/W2104545548","https://openalex.org/W2117595194","https://openalex.org/W2140980608","https://openalex.org/W2142480021","https://openalex.org/W2143404251","https://openalex.org/W2154323564","https://openalex.org/W2155187164","https://openalex.org/W2404013814","https://openalex.org/W2559629050","https://openalex.org/W2953378622","https://openalex.org/W2962921664","https://openalex.org/W3072623287","https://openalex.org/W3129488589","https://openalex.org/W3153986782","https://openalex.org/W3187367917","https://openalex.org/W3188706325","https://openalex.org/W3197720002","https://openalex.org/W4210835401","https://openalex.org/W4290990894","https://openalex.org/W4380874786"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W2086397253"],"abstract_inverted_index":{"The":[0],"all-to-all":[1,58,77,101],"collective":[2,59],"communications":[3,60],"primitive":[4],"is":[5,22,32],"widely":[6],"used":[7],"in":[8,72],"machine":[9],"learning":[10],"(ML)":[11],"and":[12,18,28,69,75,82,89],"high":[13],"performance":[14,21,56],"computing":[15],"(HPC)":[16],"workloads,":[17],"optimizing":[19],"its":[20],"of":[23,57],"interest":[24],"to":[25,53,86],"both":[26],"ML":[27],"HPC":[29],"communities.":[30],"All-to-all":[31],"a":[33,50,95],"particularly":[34],"challenging":[35],"workload":[36],"that":[37,98],"can":[38],"severely":[39],"strain":[40],"the":[41,55,84],"underlying":[42],"interconnect":[43,90],"bandwidth":[44],"at":[45],"scale.":[46],"This":[47],"paper":[48],"takes":[49],"holistic":[51],"approach":[52],"optimize":[54],"on":[61],"supercomputer-scale":[62],"direct-connect":[63],"interconnects.":[64],"We":[65,92],"address":[66],"several":[67],"algorithmic":[68],"practical":[70],"challenges":[71],"developing":[73],"efficient":[74],"bandwidth-optimal":[76],"schedules":[78,85],"for":[79],"any":[80],"topology":[81,97],"lowering":[83],"various":[87],"runtimes":[88],"technologies.":[91],"also":[93],"propose":[94],"novel":[96],"delivers":[99],"near-optimal":[100],"performance.":[102]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}