{"id":"https://openalex.org/W2889758522","doi":"https://doi.org/10.1145/3236367.3236371","title":"Multi-Threading and Lock-Free MPI RMA Based Graph Processing on KNL and POWER Architectures","display_name":"Multi-Threading and Lock-Free MPI RMA Based Graph Processing on KNL and POWER Architectures","publication_year":2018,"publication_date":"2018-09-19","ids":{"openalex":"https://openalex.org/W2889758522","doi":"https://doi.org/10.1145/3236367.3236371","mag":"2889758522"},"language":"en","primary_location":{"id":"doi:10.1145/3236367.3236371","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3236367.3236371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th European MPI Users' Group Meeting","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/A5100775673","display_name":"Mingzhe Li","orcid":"https://orcid.org/0000-0002-0883-3678"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mingzhe Li","raw_affiliation_strings":["The Ohio State University, Columbus, Ohio"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, Ohio","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067748041","display_name":"Xiaoyi Lu","orcid":"https://orcid.org/0000-0001-7581-8905"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyi Lu","raw_affiliation_strings":["The Ohio State University, Columbus, Ohio"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, Ohio","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034293705","display_name":"Hari Subramoni","orcid":"https://orcid.org/0000-0002-1200-2754"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hari Subramoni","raw_affiliation_strings":["The Ohio State University, Columbus, Ohio"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, Ohio","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024879682","display_name":"Dhabaleswar K. Panda","orcid":"https://orcid.org/0000-0002-0356-1781"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhabaleswar K. Panda","raw_affiliation_strings":["The Ohio State University, Columbus, Ohio"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, Ohio","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100775673"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.1045,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44523788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9975000023841858,"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":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.8775224089622498},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6273422837257385},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.5958586931228638},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5952374935150146},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5937753915786743},{"id":"https://openalex.org/keywords/threading","display_name":"Threading (protein sequence)","score":0.4716695249080658},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4515671730041504},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4375303387641907},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3400048017501831}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8775224089622498},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6273422837257385},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.5958586931228638},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5952374935150146},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5937753915786743},{"id":"https://openalex.org/C200307862","wikidata":"https://www.wikidata.org/wiki/Q7797175","display_name":"Threading (protein sequence)","level":3,"score":0.4716695249080658},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4515671730041504},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4375303387641907},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3400048017501831},{"id":"https://openalex.org/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3236367.3236371","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3236367.3236371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th European MPI Users' Group Meeting","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W204388420","https://openalex.org/W2021685712","https://openalex.org/W2065292293","https://openalex.org/W2071249960","https://openalex.org/W2071336726","https://openalex.org/W2129418947","https://openalex.org/W2141662114","https://openalex.org/W2143114052","https://openalex.org/W2154111453","https://openalex.org/W2157443293","https://openalex.org/W2165301438","https://openalex.org/W2405528883","https://openalex.org/W3102191699","https://openalex.org/W4365800003"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W2384867379","https://openalex.org/W1554180614","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W4253186488","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W2251285835"],"abstract_inverted_index":{"Intel":[0],"Knights":[1],"Landing":[2],"(KNL)":[3],"and":[4,67,71,89,103,123,132,185,194],"IBM":[5],"POWER":[6,104,160,195],"architectures":[7],"are":[8,114],"becoming":[9],"widely":[10],"deployed":[11],"on":[12,101,142,158,192],"modern":[13],"supercomputing":[14],"systems":[15],"due":[16],"to":[17,76,79,116,127,130,183],"its":[18],"powerful":[19],"components.":[20],"MPI":[21,72,94,168,187],"Remote":[22],"Memory":[23],"Access":[24],"(RMA)":[25],"model":[26],"that":[27],"provides":[28],"one-sided":[29],"communication":[30,52],"semantics":[31],"has":[32],"been":[33],"seen":[34],"as":[35,47,96,98],"an":[36],"attractive":[37],"approach":[38],"for":[39],"developing":[40],"High-Performance":[41],"Data":[42],"Analytics":[43],"(HPDA)":[44],"applications":[45,70,191],"such":[46],"graph":[48,189],"processing":[49,190],"with":[50,139],"irregular":[51],"characteristics.":[53],"To":[54,172],"take":[55],"advantage":[56],"of":[57,61,120,175],"a":[58],"large":[59],"number":[60],"hardware":[62],"threads":[63],"offered":[64],"by":[65,125,153,170],"KNL":[66,102,144,193],"POWER,":[68],"HPDA":[69],"RMA":[73],"runtime":[74,95],"need":[75],"be":[77],"re-designed":[78],"get":[80],"optimal":[81],"performance.":[82],"In":[83],"this":[84,178],"paper,":[85],"we":[86],"propose":[87],"multi-threading":[88],"lock-free":[90],"designs":[91,113],"in":[92],"the":[93,107,118,136,173,180],"well":[97],"Graph500":[99],"application":[100,137],"architectures.":[105,196],"At":[106,135],"micro-bench":[108],"level,":[109,138],"our":[110,146,162,176],"proposed":[111,147,163],"runtime-level":[112],"able":[115],"reduce":[117],"latency":[119],"uni-directional":[121],"MPI_Put":[122],"MPI_Get":[124],"up":[126],"3X":[128],"compared":[129],"IntelMPI":[131,151],"Spectrum":[133,167],"MPI.":[134],"1,024":[140],"processes":[141,157],"32":[143],"nodes,":[145,161],"design":[148,164,184],"could":[149,165],"outperform":[150,166],"library":[152,169],"32%.":[154],"With":[155],"512":[156],"eight":[159],"19%.":[171],"best":[174],"knowledge,":[177],"is":[179],"first":[181],"paper":[182],"evaluate":[186],"RMA-based":[188]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
