{"id":"https://openalex.org/W2913395963","doi":"https://doi.org/10.1109/pmbs.2018.8641632","title":"Improving MPI Reduction Performance for Manycore Architectures with OpenMP and Data Compression","display_name":"Improving MPI Reduction Performance for Manycore Architectures with OpenMP and Data Compression","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2913395963","doi":"https://doi.org/10.1109/pmbs.2018.8641632","mag":"2913395963"},"language":"en","primary_location":{"id":"doi:10.1109/pmbs.2018.8641632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pmbs.2018.8641632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)","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/A5113595336","display_name":"Hongzhang Shan","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongzhang Shan","raw_affiliation_strings":["Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102746800","display_name":"Samuel Williams","orcid":"https://orcid.org/0000-0002-8327-5717"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Williams","raw_affiliation_strings":["Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004593477","display_name":"Calvin W. Johnson","orcid":"https://orcid.org/0000-0003-1059-7384"},"institutions":[{"id":"https://openalex.org/I26538001","display_name":"San Diego State University","ror":"https://ror.org/0264fdx42","country_code":"US","type":"education","lineage":["https://openalex.org/I26538001"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Calvin W. Johnson","raw_affiliation_strings":["Department of Physics, San Diego State University, San Diego, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physics, San Diego State University, San Diego, CA","institution_ids":["https://openalex.org/I26538001"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5422,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82975245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.998199999332428,"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":0.9900000095367432,"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":0.8703492283821106},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8059269189834595},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.743197500705719},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.705136239528656},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5879798531532288},{"id":"https://openalex.org/keywords/parallel-processing","display_name":"Parallel processing","score":0.5170934200286865},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4746299982070923},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4467313587665558},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4379483759403229},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4148203730583191},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22031426429748535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8703492283821106},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8059269189834595},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.743197500705719},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.705136239528656},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5879798531532288},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.5170934200286865},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4746299982070923},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4467313587665558},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4379483759403229},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4148203730583191},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22031426429748535},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pmbs.2018.8641632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pmbs.2018.8641632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W112345847","https://openalex.org/W1482169852","https://openalex.org/W1518038022","https://openalex.org/W1542192632","https://openalex.org/W1558115001","https://openalex.org/W1937799376","https://openalex.org/W1988113008","https://openalex.org/W2042670967","https://openalex.org/W2071340307","https://openalex.org/W2082879210","https://openalex.org/W2088210916","https://openalex.org/W2099507400","https://openalex.org/W2107406335","https://openalex.org/W2131613942","https://openalex.org/W2164303766","https://openalex.org/W2168281730","https://openalex.org/W2625835793","https://openalex.org/W2784663755","https://openalex.org/W6633548947","https://openalex.org/W6684779596"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W2973364623","https://openalex.org/W2015080616","https://openalex.org/W1628845727","https://openalex.org/W2105882587"],"abstract_inverted_index":{"The":[0],"following":[1],"topics":[2],"are":[3],"dealt":[4],"with:":[5],"parallel":[6,16,22],"processing;":[7],"learning":[8],"(artificial":[9],"intelligence);":[10],"graphics":[11],"processing":[12],"units;":[13],"message":[14],"passing;":[15],"machines;":[17],"data":[18],"analysis;":[19],"benchmark":[20],"testing;":[21],"architectures;":[23],"multiprocessing":[24],"systems;":[25],"application":[26],"program":[27],"interfaces.":[28]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}