{"id":"https://openalex.org/W2532546572","doi":"https://doi.org/10.1145/2966884.2966918","title":"Using InfiniBand Hardware Gather-Scatter Capabilities to Optimize MPI All-to-All","display_name":"Using InfiniBand Hardware Gather-Scatter Capabilities to Optimize MPI All-to-All","publication_year":2016,"publication_date":"2016-09-25","ids":{"openalex":"https://openalex.org/W2532546572","doi":"https://doi.org/10.1145/2966884.2966918","mag":"2532546572"},"language":"en","primary_location":{"id":"doi:10.1145/2966884.2966918","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2966884.2966918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd 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/A5021627261","display_name":"Ana Gainaru","orcid":"https://orcid.org/0000-0002-1375-9468"},"institutions":[{"id":"https://openalex.org/I4210088690","display_name":"Mellanox Technologies (United States)","ror":"https://ror.org/006zwjq84","country_code":"US","type":"company","lineage":["https://openalex.org/I4210088690"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ana Gainaru","raw_affiliation_strings":["Mellanox Technologies, Inc., Oakmead Parkway, Sunnyvale, CA"],"affiliations":[{"raw_affiliation_string":"Mellanox Technologies, Inc., Oakmead Parkway, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210088690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109559556","display_name":"Richard L. Graham","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088690","display_name":"Mellanox Technologies (United States)","ror":"https://ror.org/006zwjq84","country_code":"US","type":"company","lineage":["https://openalex.org/I4210088690"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard L. Graham","raw_affiliation_strings":["Mellanox Technologies, Inc., Oakmead Parkway, Sunnyvale, CA"],"affiliations":[{"raw_affiliation_string":"Mellanox Technologies, Inc., Oakmead Parkway, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210088690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102887842","display_name":"Artem Y. Polyakov","orcid":"https://orcid.org/0000-0001-6759-1448"},"institutions":[{"id":"https://openalex.org/I4210088690","display_name":"Mellanox Technologies (United States)","ror":"https://ror.org/006zwjq84","country_code":"US","type":"company","lineage":["https://openalex.org/I4210088690"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Artem Polyakov","raw_affiliation_strings":["Mellanox Technologies, Inc., Oakmead Parkway, Sunnyvale, CA"],"affiliations":[{"raw_affiliation_string":"Mellanox Technologies, Inc., Oakmead Parkway, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210088690"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062577862","display_name":"Gilad Shainer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088690","display_name":"Mellanox Technologies (United States)","ror":"https://ror.org/006zwjq84","country_code":"US","type":"company","lineage":["https://openalex.org/I4210088690"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gilad Shainer","raw_affiliation_strings":["Mellanox Technologies, Inc., Oakmead Parkway, Sunnyvale, CA"],"affiliations":[{"raw_affiliation_string":"Mellanox Technologies, Inc., Oakmead Parkway, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210088690"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021627261"],"corresponding_institution_ids":["https://openalex.org/I4210088690"],"apc_list":null,"apc_paid":null,"fwci":0.3153,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.58623284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/infiniband","display_name":"InfiniBand","score":0.9470221996307373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8594578504562378},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.7004959583282471},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6504117250442505},{"id":"https://openalex.org/keywords/unpacking","display_name":"Unpacking","score":0.5974987149238586},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.5837507843971252},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5697736144065857},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4425649642944336},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.34735095500946045}],"concepts":[{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.9470221996307373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8594578504562378},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.7004959583282471},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6504117250442505},{"id":"https://openalex.org/C2777256151","wikidata":"https://www.wikidata.org/wiki/Q7897273","display_name":"Unpacking","level":2,"score":0.5974987149238586},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.5837507843971252},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5697736144065857},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4425649642944336},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.34735095500946045},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2966884.2966918","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2966884.2966918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd European MPI Users' Group Meeting","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1020185495","https://openalex.org/W1559860755","https://openalex.org/W1825216778","https://openalex.org/W1980008253","https://openalex.org/W2000531806","https://openalex.org/W2027508400","https://openalex.org/W2076167255","https://openalex.org/W2086473105","https://openalex.org/W2091780466","https://openalex.org/W2111144707","https://openalex.org/W2131613942","https://openalex.org/W2133557963","https://openalex.org/W2164945803","https://openalex.org/W2189311730","https://openalex.org/W4386616824"],"related_works":["https://openalex.org/W2154082760","https://openalex.org/W1997919677","https://openalex.org/W2023054716","https://openalex.org/W2584017495","https://openalex.org/W2294370818","https://openalex.org/W1985151924","https://openalex.org/W2532546572","https://openalex.org/W4241954130","https://openalex.org/W34067342","https://openalex.org/W4244053896"],"abstract_inverted_index":{"The":[0,111],"MPI":[1,104],"all-to-all":[2,100],"algorithm":[3,10],"is":[4,59,80],"a":[5,115],"data":[6,22,58],"intensive,":[7],"high-cost":[8],"collective":[9],"used":[11,81],"by":[12,106],"many":[13],"scientific":[14],"High":[15],"Performance":[16],"Computing":[17],"applications.":[18],"Optimizations":[19],"for":[20,73,114],"small":[21],"exchange":[23],"use":[24],"aggregation":[25],"techniques,":[26],"such":[27],"as":[28],"the":[29,34,50,56,68,95,118],"Bruck":[30,51],"algorithm,":[31,52],"to":[32,83],"minimize":[33,40],"number":[35],"of":[36,49,67,123],"messages":[37],"sent,":[38],"and":[39,88,97,108,125],"overall":[41],"operation":[42],"latency.":[43],"This":[44],"paper":[45],"presents":[46],"three":[47],"variants":[48],"which":[53],"differ":[54],"in":[55,62,117],"way":[57],"laid":[60],"out":[61],"memory":[63,120],"at":[64],"intermediate":[65],"steps":[66],"algorithm.":[69],"Mellanox's":[70],"InfiniBand":[71],"support":[72],"Host":[74],"Channel":[75],"Adapter":[76],"(HCA)":[77],"hardware":[78],"scatter/gather":[79],"selectively":[82],"replace":[84],"CPU-based":[85],"buffer":[86],"packing":[87],"unpacking.":[89],"Using":[90],"this":[91],"offload":[92],"capability":[93],"reduces":[94],"eight":[96],"sixteen":[98],"byte":[99],"latency":[101],"on":[102],"1024":[103],"Processes":[105],"9.7%":[107],"9.1%,":[109],"respectively.":[110,127],"optimization":[112],"accounts":[113],"decrease":[116],"total":[119],"handling":[121],"time":[122],"40.6%":[124],"57.9%,":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
