{"id":"https://openalex.org/W2892120148","doi":"https://doi.org/10.1145/3236367.3236376","title":"Efficient Asynchronous Communication Progress for MPI without Dedicated Resources","display_name":"Efficient Asynchronous Communication Progress for MPI without Dedicated Resources","publication_year":2018,"publication_date":"2018-09-19","ids":{"openalex":"https://openalex.org/W2892120148","doi":"https://doi.org/10.1145/3236367.3236376","mag":"2892120148"},"language":"en","primary_location":{"id":"doi:10.1145/3236367.3236376","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3236367.3236376","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":"conference-paper","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/A5012040774","display_name":"Amit Ruhela","orcid":"https://orcid.org/0000-0001-6547-714X"},"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":"Amit Ruhela","raw_affiliation_strings":["The Ohio State University, Columbus, Ohio"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, Ohio","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101626747","display_name":"Sourav Chakraborty","orcid":"https://orcid.org/0000-0001-9518-6204"},"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":"Sourav Chakraborty","raw_affiliation_strings":["The Ohio State University, Columbus, Ohio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, Ohio","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013350491","display_name":"Mohammadreza Bayatpour","orcid":null},"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":"Mohammadreza Bayatpour","raw_affiliation_strings":["The Ohio State University, Columbus, Ohio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, Ohio","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057608531","display_name":"Pouya Kousha","orcid":"https://orcid.org/0009-0004-7507-0940"},"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":"Pouya Kousha","raw_affiliation_strings":["The Ohio State University, Columbus, Ohio"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, Ohio","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.4234,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90004671,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9976999759674072,"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":0.888738214969635},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7608882188796997},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.7593176364898682},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.611642062664032},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5771439671516418},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5714319348335266},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.5284098386764526},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5175025463104248},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5078368782997131},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4569317698478699},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.43822985887527466},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3907780051231384},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3818478584289551},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.33829742670059204},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1304229497909546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.888738214969635},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7608882188796997},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.7593176364898682},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.611642062664032},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5771439671516418},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5714319348335266},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.5284098386764526},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5175025463104248},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5078368782997131},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4569317698478699},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.43822985887527466},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3907780051231384},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3818478584289551},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.33829742670059204},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1304229497909546}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3236367.3236376","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3236367.3236376","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":0.5799999833106995,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309374","display_name":"Ohio State University","ror":"https://ror.org/00rs6vg23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1485684178","https://openalex.org/W1521427322","https://openalex.org/W1530542361","https://openalex.org/W1568002392","https://openalex.org/W1803873461","https://openalex.org/W1825216778","https://openalex.org/W1990294766","https://openalex.org/W2019465613","https://openalex.org/W2044738731","https://openalex.org/W2051507892","https://openalex.org/W2091780466","https://openalex.org/W2100121182","https://openalex.org/W2122929502","https://openalex.org/W2135183195","https://openalex.org/W2151445386","https://openalex.org/W2152994038","https://openalex.org/W2165102815","https://openalex.org/W2165808215","https://openalex.org/W2173839706","https://openalex.org/W2215735188","https://openalex.org/W2485412435","https://openalex.org/W2564999662","https://openalex.org/W2612249218","https://openalex.org/W2746871167","https://openalex.org/W2784114077","https://openalex.org/W2786941134","https://openalex.org/W2804858003","https://openalex.org/W2962778695","https://openalex.org/W3099989736","https://openalex.org/W3103952756","https://openalex.org/W4239248483","https://openalex.org/W4250119831"],"related_works":["https://openalex.org/W1974923383","https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W2085105049","https://openalex.org/W1971725090","https://openalex.org/W2526069705","https://openalex.org/W2124048060","https://openalex.org/W2024016913","https://openalex.org/W1970720081","https://openalex.org/W2751263050"],"abstract_inverted_index":{"The":[0,88],"overlap":[1,79],"of":[2,11,40,54,107,142],"computation":[3],"and":[4,52,69,103,109,115,136,148,167,172,187,193,216],"communication":[5,99,195],"is":[6,101],"critical":[7],"for":[8,17,58,190,208],"good":[9,78],"performance":[10,206,218],"many":[12],"HPC":[13],"applications.":[14,60],"State-of-the-art":[15],"designs":[16,127],"the":[18,105,112,116,122,143,221],"asynchronous":[19,98,117],"progress":[20,100,118],"require":[21],"specially":[22],"designed":[23],"hardware":[24,84],"resources":[25,57],"(advanced":[26],"switches":[27],"or":[28,35,85],"network":[29],"interface":[30],"cards),":[31],"dedicated":[32],"processor":[33],"cores":[34],"application":[36,150,223],"modification":[37],"(e.g.":[38],"use":[39],"MPI_Test).":[41],"These":[42],"techniques":[43],"suffer":[44],"from":[45],"various":[46],"issues":[47],"like":[48],"increasing":[49],"code":[50],"complexity/cost":[51],"loss":[53],"available":[55],"compute":[56],"end":[59],"In":[61],"this":[62,67],"paper,":[63],"we":[64],"take":[65],"up":[66],"challenge":[68],"propose":[70],"a":[71],"simple":[72],"yet":[73],"effective":[74],"technique":[75],"to":[76,95,176],"achieve":[77],"without":[80],"needing":[81],"any":[82],"additional":[83],"software":[86],"resources.":[87],"proposed":[89,123,144,181],"thread-based":[90],"design":[91,124],"allows":[92],"MPI":[93,130,210],"libraries":[94,131],"self-detect":[96],"when":[97],"needed":[102],"minimizes":[104],"number":[106],"context-switches":[108],"preemption":[110],"between":[111],"main":[113],"thread":[114],"thread.":[119],"We":[120,139,202],"evaluate":[121],"against":[125],"state-of-the-art":[126,178],"in":[128],"other":[129,177],"including":[132,158],"MVAPICH2,":[133],"Intel":[134,159,161,168],"MPI,":[135],"Open":[137],"MPI.":[138],"demonstrate":[140],"benefits":[141],"approach":[145,182],"at":[146,149,152],"microbenchmark":[147],"level":[151],"scale":[153],"on":[154,199,213,224],"four":[155],"different":[156],"architectures":[157],"Broadwell,":[160],"Xeon":[162],"Phi":[163],"(KNL),":[164],"IBM":[165],"OpenPOWER,":[166],"Skylake":[169],"with":[170,220],"InfiniBand":[171],"Omni-Path":[173],"interconnects.":[174],"Compared":[175],"designs,":[179],"our":[180],"shows":[183],"upto":[184],"46%,":[185],"37%,":[186],"49%":[188],"improvement":[189,207,219],"All-to-one,":[191],"One-to-all,":[192],"All-to-all":[194],"patterns":[196],"respectively":[197],"collectives":[198],"1,024":[200],"processes.":[201,226],"also":[203],"show":[204],"38%":[205],"SPEC":[209],"compute-intensive":[211],"applications":[212],"384":[214],"processes":[215],"44%":[217],"P3DFFT":[222],"448":[225]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
