{"id":"https://openalex.org/W2075140534","doi":"https://doi.org/10.1145/2751205.2751242","title":"Exploiting Process Imbalance to Improve MPI Collective Operations in Hierarchical Systems","display_name":"Exploiting Process Imbalance to Improve MPI Collective Operations in Hierarchical Systems","publication_year":2015,"publication_date":"2015-06-02","ids":{"openalex":"https://openalex.org/W2075140534","doi":"https://doi.org/10.1145/2751205.2751242","mag":"2075140534"},"language":"en","primary_location":{"id":"doi:10.1145/2751205.2751242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2751205.2751242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM on International Conference on Supercomputing","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/A5073379106","display_name":"Benjamin S. Parsons","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Benjamin S. Parsons","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110871804","display_name":"Vijay S. Pai","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay S. Pai","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073379106"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.3328,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65277036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9994000196456909,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8439186811447144},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8017224669456482},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.7379406690597534},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7220656275749207},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.6907212734222412},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6894375085830688},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5683388113975525},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5111430287361145},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3369608223438263},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.32791417837142944},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08653932809829712}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8439186811447144},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8017224669456482},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.7379406690597534},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7220656275749207},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6907212734222412},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6894375085830688},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5683388113975525},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5111430287361145},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3369608223438263},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.32791417837142944},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08653932809829712},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2751205.2751242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2751205.2751242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM on International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337538","display_name":"U.S. Army Corps of Engineers","ror":"https://ror.org/05w4e8v21"},{"id":"https://openalex.org/F4320337573","display_name":"Information Technology Laboratory","ror":"https://ror.org/0440c3437"},{"id":"https://openalex.org/F4320338258","display_name":"Engineer Research and Development Center","ror":"https://ror.org/027mhn368"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W83535271","https://openalex.org/W1488305958","https://openalex.org/W1672316377","https://openalex.org/W1980008253","https://openalex.org/W1991732708","https://openalex.org/W2021216254","https://openalex.org/W2037492572","https://openalex.org/W2058694702","https://openalex.org/W2097493498","https://openalex.org/W2102977580","https://openalex.org/W2105800835","https://openalex.org/W2111144707","https://openalex.org/W2143300065","https://openalex.org/W2168281730","https://openalex.org/W2677178705"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W4401278057","https://openalex.org/W1980801634"],"abstract_inverted_index":{"This":[0],"work":[1],"improves":[2],"the":[3,11,25,47,58,80],"performance":[4,19,26],"of":[5,13,29,49,60],"MPI":[6],"collective":[7,20],"communication":[8],"operations":[9],"in":[10,38],"presence":[12],"imbalanced":[14,32],"process":[15,33,50],"arrival":[16,34],"times.":[17],"High":[18],"communications":[21],"are":[22,36,67],"crucial":[23],"for":[24],"and":[27,31,56,75],"scalability":[28],"applications,":[30],"times":[35],"common":[37],"these":[39],"applications.":[40],"A":[41],"micro-benchmark":[42],"is":[43],"used":[44,69],"to":[45,70],"investigate":[46],"nature":[48,59],"imbalance":[51],"with":[52],"perfectly":[53],"balanced":[54],"workloads,":[55],"understand":[57],"inter-":[61],"versus":[62],"intra-node":[63],"imbalance.":[64],"These":[65],"insights":[66],"then":[68],"develop":[71],"imbalance-tolerant":[72],"reduction,":[73],"broadcast,":[74],"all-to-all":[76],"algorithms,":[77],"which":[78],"minimize":[79],"synchronization":[81],"delay":[82],"observed":[83],"by":[84],"early":[85],"arriving":[86],"processes.":[87]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"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"}