{"id":"https://openalex.org/W2002505081","doi":"https://doi.org/10.1145/1542275.1542321","title":"MPI-aware compiler optimizations for improving communication-computation overlap","display_name":"MPI-aware compiler optimizations for improving communication-computation overlap","publication_year":2009,"publication_date":"2009-06-08","ids":{"openalex":"https://openalex.org/W2002505081","doi":"https://doi.org/10.1145/1542275.1542321","mag":"2002505081"},"language":"en","primary_location":{"id":"doi:10.1145/1542275.1542321","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1542275.1542321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Supercomputing","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/A5018398543","display_name":"Anthony Danalis","orcid":null},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Danalis","raw_affiliation_strings":["University of Delaware, Newark, DE, USA","University of Delaware, Newark, DE. USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of Delaware, Newark, DE. USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068927917","display_name":"Lori Pollock","orcid":"https://orcid.org/0000-0002-4388-4892"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lori Pollock","raw_affiliation_strings":["University of Delaware, Newark, DE, USA","University of Delaware, Newark, DE. USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of Delaware, Newark, DE. USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044461835","display_name":"Martin Swany","orcid":"https://orcid.org/0000-0001-8028-1161"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Swany","raw_affiliation_strings":["University of Delaware, Newark, DE, USA","University of Delaware, Newark, DE. USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of Delaware, Newark, DE. USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103791820","display_name":"John Cavazos","orcid":null},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Cavazos","raw_affiliation_strings":["University of Delaware, Newark, DE, USA","University of Delaware, Newark, DE. USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of Delaware, Newark, DE. USA","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":2.1948,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.88315004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"316","last_page":"325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991999864578247,"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":0.9980000257492065,"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/compiler","display_name":"Compiler","score":0.9404110908508301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9239476919174194},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.7901318073272705},{"id":"https://openalex.org/keywords/interprocedural-optimization","display_name":"Interprocedural optimization","score":0.6909805536270142},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6746848225593567},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6536983847618103},{"id":"https://openalex.org/keywords/loop-optimization","display_name":"Loop optimization","score":0.5826413035392761},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5355989933013916},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5100687146186829},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4425320327281952},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.420034259557724},{"id":"https://openalex.org/keywords/compiler-correctness","display_name":"Compiler correctness","score":0.4195302128791809},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11612701416015625}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.9404110908508301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9239476919174194},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.7901318073272705},{"id":"https://openalex.org/C111564260","wikidata":"https://www.wikidata.org/wiki/Q4288856","display_name":"Interprocedural optimization","level":5,"score":0.6909805536270142},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6746848225593567},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6536983847618103},{"id":"https://openalex.org/C29331672","wikidata":"https://www.wikidata.org/wiki/Q3354468","display_name":"Loop optimization","level":4,"score":0.5826413035392761},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5355989933013916},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5100687146186829},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4425320327281952},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.420034259557724},{"id":"https://openalex.org/C68366613","wikidata":"https://www.wikidata.org/wiki/Q5156378","display_name":"Compiler correctness","level":3,"score":0.4195302128791809},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11612701416015625}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1542275.1542321","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1542275.1542321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.153.6174","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.153.6174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.udel.edu/~danalis/files/papers/Danalis_ICS09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.215.8424","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.215.8424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eecis.udel.edu/~cavazos/ics-2009.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W179815580","https://openalex.org/W191103954","https://openalex.org/W1491761826","https://openalex.org/W1496120840","https://openalex.org/W1524418295","https://openalex.org/W1554250422","https://openalex.org/W1562297782","https://openalex.org/W1562339741","https://openalex.org/W1861151562","https://openalex.org/W1916536045","https://openalex.org/W1967337968","https://openalex.org/W1974470587","https://openalex.org/W2053454864","https://openalex.org/W2078526874","https://openalex.org/W2100431052","https://openalex.org/W2100808563","https://openalex.org/W2114067856","https://openalex.org/W2114489740","https://openalex.org/W2120827897","https://openalex.org/W2121255426","https://openalex.org/W2122814645","https://openalex.org/W2132777761","https://openalex.org/W2140300123","https://openalex.org/W2140476198","https://openalex.org/W2145528851","https://openalex.org/W2160670045","https://openalex.org/W2165808215","https://openalex.org/W2177970944","https://openalex.org/W2274995094","https://openalex.org/W2294743625","https://openalex.org/W3140467006","https://openalex.org/W4210409048","https://openalex.org/W4253735066","https://openalex.org/W6677084613"],"related_works":["https://openalex.org/W2352584311","https://openalex.org/W2036668966","https://openalex.org/W2004605222","https://openalex.org/W2911899620","https://openalex.org/W1601646354","https://openalex.org/W1606851719","https://openalex.org/W2049890071","https://openalex.org/W2479014312","https://openalex.org/W1583465708","https://openalex.org/W4232453487"],"abstract_inverted_index":{"Several":[0],"existing":[1,91],"compiler":[2,44,81,92],"transformations":[3,48,93,116],"can":[4,46,82,149],"help":[5],"improve":[6],"communication-computation":[7,120],"overlap":[8],"in":[9],"MPI":[10,19,52,76],"applications.":[11],"However,":[12],"traditional":[13],"compilers":[14],"treat":[15],"calls":[16],"to":[17,55,69,112,117,128],"the":[18,38,71,85,99,125,134],"library":[20],"as":[21],"a":[22,61],"black":[23],"box":[24],"with":[25],"unknown":[26],"side":[27,72],"effects":[28,54,73],"and":[29,67,110,133],"thus":[30],"miss":[31],"potential":[32],"optimizations.":[33],"This":[34],"paper's":[35],"contributions":[36],"enable":[37],"development":[39],"of":[40,51,63,74,87,155],"an":[41,79,104,153],"MPI-aware":[42,80],"optimizing":[43,115],"that":[45,107,139],"perform":[47],"exploiting":[49],"knowledge":[50],"call":[53],"increase":[56],"communication-computa-tion":[57],"overlap.":[58,121],"We":[59],"formulate":[60],"set":[62],"data":[64],"flow":[65],"equations":[66],"rules":[68],"describe":[70],"key":[75],"functions":[77],"so":[78],"automatically":[83],"assess":[84],"safety":[86],"transformations.":[88],"After":[89],"categorizing":[90],"based":[94],"on":[95,98],"their":[96],"effect":[97],"application":[100],"code,":[101],"we":[102,137],"present":[103],"optimization":[105,126],"algorithm":[106,127],"specifies":[108],"when":[109,141],"how":[111],"apply":[113],"these":[114,143],"achieve":[118],"improved":[119],"By":[122],"manually":[123],"applying":[124],"kernels":[129],"extracted":[130],"from":[131],"HYCOM":[132],"NAS":[135],"benchmarks,":[136],"show":[138],"even":[140],"transforming":[142],"highly":[144],"optimized":[145],"codes,":[146],"execution":[147],"time":[148],"be":[150],"decreased":[151],"by":[152],"average":[154],"over":[156],"30%.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
