{"id":"https://openalex.org/W2543333295","doi":"https://doi.org/10.1109/ipps.1998.669887","title":"Compiler optimization of implicit reductions for distributed memory multiprocessors","display_name":"Compiler optimization of implicit reductions for distributed memory multiprocessors","publication_year":2002,"publication_date":"2002-11-27","ids":{"openalex":"https://openalex.org/W2543333295","doi":"https://doi.org/10.1109/ipps.1998.669887","mag":"2543333295"},"language":"en","primary_location":{"id":"doi:10.1109/ipps.1998.669887","doi":"https://doi.org/10.1109/ipps.1998.669887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipps.1998.669887","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"IEEE International Parallel and Distributed Processing Symposium (IPDPS)","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Merged International Parallel Processing Symposium and Symposium on Parallel and Distributed Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5029031565","display_name":"Bo Lu","orcid":"https://orcid.org/0009-0007-8285-776X","observed_orcids":["https://orcid.org/0009-0007-8285-776X"]},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"B. Lu","raw_affiliation_strings":["Department of Computer Science, Rice University, USA","Dept of Computer Science, Rice University, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rice University, USA","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Dept of Computer Science, Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089709469","display_name":"John Mellor\u2010Crummey","orcid":"https://orcid.org/0000-0002-9026-5453","observed_orcids":["https://orcid.org/0000-0002-9026-5453"]},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Mellor-Crummey","raw_affiliation_strings":["Department of Computer Science, Rice University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rice University, USA","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":1.0063,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.73404783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":9.999999747378752e-05,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.0,"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/parallel-code-generation","display_name":"parallel code generation","score":0.8180000185966492},{"id":"https://openalex.org/keywords/distributed-memory-multiprocessors","display_name":"distributed memory multiprocessors","score":0.9509999752044678},{"id":"https://openalex.org/keywords/data-locality","display_name":"data locality","score":0.8519999980926514},{"id":"https://openalex.org/keywords/high-performance-fortran","display_name":"High Performance Fortran","score":0.9860000014305115},{"id":"https://openalex.org/keywords/ibm-sp2","display_name":"IBM SP2","score":0.7789999842643738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8579623103141785},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7837732434272766},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.77756667137146},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6365293860435486},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5618724822998047},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.5559563040733337},{"id":"https://openalex.org/C177225278","wikidata":"https://www.wikidata.org/wiki/Q192674","display_name":"Factoring","level":2,"score":0.47309568524360657},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.4321918785572052},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4200282096862793},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2749669551849365},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ipps.1998.669887","doi":"https://doi.org/10.1109/ipps.1998.669887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipps.1998.669887","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"IEEE International Parallel and Distributed Processing Symposium (IPDPS)","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Merged International Parallel Processing Symposium and Symposium on Parallel and Distributed Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.35.9045","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.35.9045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eece.unm.edu/~dbader/ipdps/1998/papers/108.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.43.4118","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.43.4118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.rice.edu/~johnmc/hpf/LuMellorCrummey-ipps98.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1521571223","https://openalex.org/W1534227216","https://openalex.org/W1589918049","https://openalex.org/W1982205631","https://openalex.org/W1983413115","https://openalex.org/W2008677874","https://openalex.org/W2021235324","https://openalex.org/W2029655013","https://openalex.org/W2050120391","https://openalex.org/W2108251255","https://openalex.org/W2118735733","https://openalex.org/W2134693673","https://openalex.org/W3007497337","https://openalex.org/W4206525843"],"related_works":["https://openalex.org/W2598829669","https://openalex.org/W1983413115","https://openalex.org/W1550611068","https://openalex.org/W1581778783","https://openalex.org/W3137783668","https://openalex.org/W2170180242","https://openalex.org/W2059599783","https://openalex.org/W1773004029","https://openalex.org/W2144263584","https://openalex.org/W2157466744"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"reduction":[3,23,70,99],"recognition":[4,125],"and":[5,34,52,55,71,103,108,130,135],"parallel":[6],"code":[7,115],"generation":[8],"strategies":[9],"for":[10,50,86],"distributed-memory":[11],"multiprocessors.":[12],"We":[13,40,77,91],"describe":[14],"techniques":[15,81,126],"to":[16,64],"recognize":[17],"a":[18,60,142],"broad":[19],"range":[20],"of":[21,112,144],"implicit":[22],"operations,":[24],"including":[25],"those":[26],"involving":[27],"statements":[28],"at":[29],"multiple":[30],"loop":[31],"nesting":[32],"levels":[33],"intermixed":[35],"with":[36,101],"conditional":[37],"control":[38],"flow.":[39],"introduce":[41],"two":[42,104,145],"new":[43],"optimizations:":[44],"factoring":[45,136],"which":[46,58],"increases":[47],"data":[48],"locality":[49],"SUM":[51],"PRODUCT":[53],"reductions,":[54],"index":[56,133],"encoding":[57,134],"enables":[59],"single":[61],"global":[62],"communication":[63],"accomplish":[65],"both":[66],"an":[67,72,117],"extreme":[68,73],"value":[69,74],"location":[75],"reduction.":[76],"have":[78],"implemented":[79],"these":[80],"in":[82],"the":[83,110,113],"dHPF":[84,102],"compiler":[85],"High":[87],"Performance":[88],"Fortran":[89],"(HPF).":[90],"evaluate":[92],"their":[93],"effectiveness":[94],"experimentally":[95],"by":[96,141],"compiling":[97],"several":[98],"benchmarks":[100],"commercial":[105],"HPF":[106],"compilers,":[107],"comparing":[109],"performance":[111,140],"generated":[114],"on":[116],"IBM":[118],"SP2.":[119],"Our":[120],"results":[121],"show":[122],"that":[123,131],"our":[124,132],"are":[127],"more":[128],"powerful":[129],"optimizations":[137],"can":[138],"improve":[139],"factor":[143],"where":[146],"they":[147],"apply.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-11-04T00:00:00"}