{"id":"https://openalex.org/W3175437177","doi":"https://doi.org/10.1145/3431379.3460645","title":"TEMPI","display_name":"TEMPI","publication_year":2021,"publication_date":"2021-06-17","ids":{"openalex":"https://openalex.org/W3175437177","doi":"https://doi.org/10.1145/3431379.3460645","mag":"3175437177"},"language":"en","primary_location":{"id":"doi:10.1145/3431379.3460645","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3431379.3460645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th International Symposium on High-Performance Parallel and Distributed Computing","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/A5032990831","display_name":"Carl Pearson","orcid":"https://orcid.org/0000-0001-6481-970X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carl Pearson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073106039","display_name":"Kun Wu","orcid":"https://orcid.org/0000-0002-0149-1409"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Wu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108479300","display_name":"I\u2010Hsin Chung","orcid":"https://orcid.org/0000-0003-4555-9257"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I-Hsin Chung","raw_affiliation_strings":["IBM T. J. Watson Research, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030156276","display_name":"Jinjun Xiong","orcid":"https://orcid.org/0000-0002-2620-4859"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinjun Xiong","raw_affiliation_strings":["IBM T. J. Watson Research, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040404999","display_name":"Wen\u2010mei Hwu","orcid":"https://orcid.org/0000-0003-2532-5349"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-Mei Hwu","raw_affiliation_strings":["Nvidia Research, Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia Research, Champaign, IL, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983000159263611,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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":0.9070864915847778},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8730977773666382},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7835135459899902},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6624971032142639},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6611445546150208},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6209442019462585},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4723155200481415},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.4511342942714691},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.33464741706848145},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1788286566734314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9070864915847778},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8730977773666382},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7835135459899902},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6624971032142639},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6611445546150208},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6209442019462585},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4723155200481415},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.4511342942714691},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.33464741706848145},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1788286566734314}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3431379.3460645","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3431379.3460645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th International Symposium on High-Performance Parallel and Distributed Computing","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":16,"referenced_works":["https://openalex.org/W1555373975","https://openalex.org/W1581386200","https://openalex.org/W1670978437","https://openalex.org/W1974299554","https://openalex.org/W1994531540","https://openalex.org/W2063057407","https://openalex.org/W2109977639","https://openalex.org/W2344706860","https://openalex.org/W2604208239","https://openalex.org/W2805739788","https://openalex.org/W3005695646","https://openalex.org/W3028644900","https://openalex.org/W3083442288","https://openalex.org/W3096835151","https://openalex.org/W4236390280","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1973046741","https://openalex.org/W2983282793","https://openalex.org/W2124048060","https://openalex.org/W1902983110","https://openalex.org/W4386915331","https://openalex.org/W2378910916","https://openalex.org/W2086666199","https://openalex.org/W1511717675","https://openalex.org/W2116006827","https://openalex.org/W2361929291"],"abstract_inverted_index":{"MPI":[0,13,29,39,48,56,70,135,151,161,192],"derived":[1],"datatypes":[2,16],"are":[3,17],"an":[4,150],"abstraction":[5],"that":[6,103],"simplifies":[7],"handling":[8,79,95,110],"of":[9,37,45,66,107,172,178,185,202],"non-contiguous":[10,108,130],"data":[11,109,132],"in":[12,27,96,206],"applications.":[14],"These":[15],"recursively":[18],"constructed":[19],"at":[20],"runtime":[21],"from":[22],"primitive":[23],"Named":[24],"Types":[25],"defined":[26],"the":[28,33,43,91,104,169,191],"standard.":[30],"More":[31],"recently,":[32],"development":[34],"and":[35,118,133,182],"deployment":[36],"CUDA-aware":[38,134],"implementations":[40,54],"has":[41],"encouraged":[42],"transition":[44],"distributed":[46],"high-performance":[47],"codes":[49],"to":[50,58,120,129,180,187,190],"use":[51],"GPUs.":[52],"Such":[53],"allow":[55],"functions":[57],"directly":[59],"operate":[60],"on":[61,195],"GPU":[62,67,131],"buffers,":[63],"easing":[64],"integration":[65],"compute":[68],"into":[69],"codes.":[71],"This":[72,99,144,199],"work":[73,100,145,174],"first":[74],"presents":[75],"a":[76,87,196,207],"novel":[77],"datatype":[78],"strategy":[80],"for":[81,142],"nested":[82],"strided":[83],"datatypes,":[84],"which":[85],"finds":[86],"middle":[88],"ground":[89],"between":[90],"specialized":[92],"or":[93,165],"generic":[94],"prior":[97],"work.":[98],"also":[101],"shows":[102],"performance":[105,138],"characteristics":[106],"can":[111,156],"be":[112,140,157],"modeled":[113],"with":[114,159,211],"empirical":[115],"system":[116,164],"measurements,":[117],"used":[119,158],"transparently":[121],"improve":[122],"MPI_Send/Recv":[123],"latency.":[124],"Finally,":[125],"despite":[126],"substantial":[127],"attention":[128],"implementations,":[136],"good":[137],"cannot":[139],"taken":[141],"granted.":[143],"demonstrates":[146,175],"its":[147],"contributions":[148],"through":[149],"interposer":[152],"library,":[153],"TEMPI.":[154],"TEMPI":[155],"existing":[160],"deployments":[162],"without":[163],"application":[166],"changes.":[167],"Ultimately,":[168],"interposed-library":[170],"model":[171],"this":[173],"MPI_Pack":[176],"speedup":[177,184,201],"up":[179,186],"242000x":[181],"MPI_Send":[183],"59000x":[188],"compared":[189],"implementation":[193],"deployed":[194],"leadership-class":[197],"supercomputer.":[198],"yields":[200],"more":[203],"than":[204],"917x":[205],"3D":[208],"halo":[209],"exchange":[210],"3072":[212],"processes.":[213]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-07-05T00:00:00"}