{"id":"https://openalex.org/W1987274898","doi":"https://doi.org/10.1145/2642769.2642773","title":"GPU-Aware Intranode MPI_Allreduce","display_name":"GPU-Aware Intranode MPI_Allreduce","publication_year":2014,"publication_date":"2014-08-29","ids":{"openalex":"https://openalex.org/W1987274898","doi":"https://doi.org/10.1145/2642769.2642773","mag":"1987274898"},"language":"en","primary_location":{"id":"doi:10.1145/2642769.2642773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2642769.2642773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st 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/A5080002194","display_name":"Iman Faraji","orcid":"https://orcid.org/0000-0001-9442-7424"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Iman Faraji","raw_affiliation_strings":["ECE Dept., Queen's University Kingston, ON, Canada K7L 3N6"],"affiliations":[{"raw_affiliation_string":"ECE Dept., Queen's University Kingston, ON, Canada K7L 3N6","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039854005","display_name":"Ahmad Afsahi","orcid":"https://orcid.org/0000-0002-2924-6851"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmad Afsahi","raw_affiliation_strings":["ECE Dept., Queen's University Kingston, ON, Canada K7L 3N6"],"affiliations":[{"raw_affiliation_string":"ECE Dept., Queen's University Kingston, ON, Canada K7L 3N6","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080002194"],"corresponding_institution_ids":["https://openalex.org/I204722609"],"apc_list":null,"apc_paid":null,"fwci":1.5752,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82201006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987999796867371,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9056329727172852},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7598628997802734},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6898618936538696},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6787519454956055},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5165566205978394},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4834509789943695},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4181334376335144},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4110291600227356},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3515205979347229}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9056329727172852},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7598628997802734},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6898618936538696},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6787519454956055},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5165566205978394},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4834509789943695},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4181334376335144},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4110291600227356},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3515205979347229},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2642769.2642773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2642769.2642773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European MPI Users' Group Meeting","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.644.3642","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.644.3642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://post.queensu.ca/~pprl/papers/Iman_EuroMPI-2014.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8600000143051147,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1574750619","https://openalex.org/W1603927537","https://openalex.org/W1637731592","https://openalex.org/W1964981582","https://openalex.org/W1965378199","https://openalex.org/W1974211642","https://openalex.org/W2024565525","https://openalex.org/W2043143850","https://openalex.org/W2110813866","https://openalex.org/W2156416954"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W17155033","https://openalex.org/W2150291671","https://openalex.org/W1973046741","https://openalex.org/W2983282793","https://openalex.org/W3012895752","https://openalex.org/W4205439893"],"abstract_inverted_index":{"Modern":[0],"multi-core":[1],"clusters":[2],"are":[3],"increasingly":[4],"using":[5],"GPUs":[6],"to":[7,31,85],"achieve":[8],"higher":[9],"performance":[10,33],"and":[11,59,72,87],"power":[12],"efficiency.":[13],"In":[14],"such":[15],"clusters,":[16],"efficient":[17,41],"communication":[18,62],"among":[19],"processes":[20],"with":[21],"data":[22],"residing":[23],"in":[24,47],"GPU":[25,48,68],"memory":[26],"is":[27],"of":[28,34,43,64],"paramount":[29],"importance":[30],"the":[32,40],"MPI":[35],"applications.":[36],"This":[37],"paper":[38],"investigates":[39],"design":[42,53,71],"intranode":[44,61],"MPI_Allreduce":[45],"operation":[46],"clusters.":[49],"We":[50],"propose":[51],"two":[52],"alternatives":[54],"that":[55],"exploit":[56],"in-GPU":[57],"reduction":[58],"fast":[60],"capabilities":[63],"modern":[65],"GPUs.":[66],"Our":[67],"shared-buffer":[69],"aware":[70],"GPU-aware":[73],"Binomial":[74],"reduce-broadcast":[75],"algorithmic":[76],"approach":[77],"provide":[78],"significant":[79],"speedup":[80],"over":[81],"MVAPICH2":[82],"by":[83],"up":[84],"22":[86],"16":[88],"times,":[89],"respectively.":[90]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
