{"id":"https://openalex.org/W2026024102","doi":"https://doi.org/10.1109/hipc.2013.6799131","title":"Compiler generation and autotuning of communication-avoiding operators for geometric multigrid","display_name":"Compiler generation and autotuning of communication-avoiding operators for geometric multigrid","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2026024102","doi":"https://doi.org/10.1109/hipc.2013.6799131","mag":"2026024102"},"language":"en","primary_location":{"id":"doi:10.1109/hipc.2013.6799131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2013.6799131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th Annual International Conference on High Performance Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1407166","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032219555","display_name":"Protonu Basu","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Protonu Basu","raw_affiliation_strings":["University of Utah, Salt Lake City, Utah","University of Utah, Salt Lake City, UT, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, Utah","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah, Salt Lake City, UT, USA#TAB#","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078599914","display_name":"Anand Venkat","orcid":"https://orcid.org/0000-0002-4167-4525"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Venkat","raw_affiliation_strings":["University of Utah, Salt Lake City, Utah","University of Utah, Salt Lake City, UT, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, Utah","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah, Salt Lake City, UT, USA#TAB#","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030152493","display_name":"Mary Hall","orcid":"https://orcid.org/0000-0002-3058-7573"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Hall","raw_affiliation_strings":["University of Utah, Salt Lake City, Utah","University of Utah, Salt Lake City, UT, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, Utah","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah, Salt Lake City, UT, USA#TAB#","institution_ids":["https://openalex.org/I223532165"]}]},{"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":["Lawrence Berkeley National Laboratory, Berkeley, CA","Lawrence Berkeley National Lab, Berkeley, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Lab, Berkeley, CA, USA#TAB#","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082058497","display_name":"Brian Van Straalen","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":"Brian Van Straalen","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA","Lawrence Berkeley National Lab, Berkeley, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Lab, Berkeley, CA, USA#TAB#","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113842004","display_name":"Leonid Oliker","orcid":"https://orcid.org/0000-0002-7923-2896"},"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":"Leonid Oliker","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA","Lawrence Berkeley National Lab, Berkeley, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Lab, Berkeley, CA, USA#TAB#","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5032219555"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":1.9029,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.85720438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"452","last_page":"461"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9970999956130981,"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":0.9901999831199646,"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":0.8491746187210083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8168196678161621},{"id":"https://openalex.org/keywords/multigrid-method","display_name":"Multigrid method","score":0.7556736469268799},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.631178617477417},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6231403946876526},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5820059776306152},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.49137774109840393},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.41293978691101074},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3558042049407959},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23926514387130737},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18383058905601501},{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.16940534114837646},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.1110156774520874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07927489280700684},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07543385028839111}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8491746187210083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8168196678161621},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.7556736469268799},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.631178617477417},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6231403946876526},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5820059776306152},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.49137774109840393},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.41293978691101074},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3558042049407959},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23926514387130737},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18383058905601501},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.16940534114837646},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.1110156774520874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07927489280700684},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07543385028839111},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/hipc.2013.6799131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2013.6799131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th Annual International Conference on High Performance Computing","raw_type":"proceedings-article"},{"id":"pmh:ark:/13030/qt5mj57586","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.428.9076","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.428.9076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.csail.mit.edu/skamil/wosc/papers/wosc13-basu.pdf","raw_type":"text"},{"id":"pmh:oai:escholarship.org/ark:/13030/qt5mj57586","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/5mj57586","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:osti.gov:1407166","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1407166","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:qt5mj57586","is_oa":false,"landing_page_url":"http://www.escholarship.org/uc/item/5mj57586","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Basu, P; Venkat, A; Hall, M; Williams, S; Van Straalen, B; &amp; Oliker, L. (2013). Compiler generation and autotuning of communication-avoiding operators for geometric multigrid. 20th Annual International Conference on High Performance Computing, HiPC 2013, 452 - 461. doi: 10.1109/HiPC.2013.6799131. Lawrence Berkeley National Laboratory: Lawrence Berkeley National Laboratory. Retrieved from: http://www.escholarship.org/uc/item/5mj57586","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:osti.gov:1407166","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1407166","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1494930385","https://openalex.org/W1774469134","https://openalex.org/W1779740778","https://openalex.org/W1825532946","https://openalex.org/W1968347730","https://openalex.org/W1975001341","https://openalex.org/W1979457157","https://openalex.org/W1985263109","https://openalex.org/W1997147891","https://openalex.org/W2002555321","https://openalex.org/W2003798513","https://openalex.org/W2003937683","https://openalex.org/W2016618963","https://openalex.org/W2032391783","https://openalex.org/W2035430533","https://openalex.org/W2038481157","https://openalex.org/W2039378765","https://openalex.org/W2076028817","https://openalex.org/W2087479145","https://openalex.org/W2103817093","https://openalex.org/W2104512032","https://openalex.org/W2109859355","https://openalex.org/W2119042753","https://openalex.org/W2128746953","https://openalex.org/W2136504964","https://openalex.org/W2147127704","https://openalex.org/W2150319905","https://openalex.org/W2152914333","https://openalex.org/W2154078685","https://openalex.org/W2154118576","https://openalex.org/W2154786353","https://openalex.org/W2158626113","https://openalex.org/W2160106616","https://openalex.org/W2407443438","https://openalex.org/W2997945685","https://openalex.org/W3152199537","https://openalex.org/W4249968602","https://openalex.org/W6637981811","https://openalex.org/W6638047330","https://openalex.org/W6672213795","https://openalex.org/W6677899545"],"related_works":["https://openalex.org/W650988184","https://openalex.org/W2162410319","https://openalex.org/W2002505081","https://openalex.org/W2083681681","https://openalex.org/W2137356287","https://openalex.org/W2577630842","https://openalex.org/W1172579163","https://openalex.org/W1488300410","https://openalex.org/W4321184925","https://openalex.org/W2138790427"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,124],"compiler":[4,76],"approach":[5,95],"to":[6,55,84,89,117,138],"introducing":[7,46],"communication-avoiding":[8],"optimizations":[9,26,54],"in":[10,114],"geometric":[11],"multigrid":[12,163],"(GMG),":[13],"one":[14],"of":[15,45,70,142,155],"the":[16,31,43,56,62,67,71,94,102,120,140,143,147,161],"most":[17],"popular":[18],"methods":[19],"for":[20,66,123],"solving":[21],"partial":[22],"differential":[23],"equations.":[24],"Communication-avoiding":[25],"reduce":[27],"vertical":[28],"communication":[29,36,106],"through":[30],"memory":[32],"hierarchy":[33],"and":[34,64,81,107,127],"horizontal":[35],"across":[37],"processes":[38],"or":[39],"threads,":[40],"usually":[41],"at":[42,128],"expense":[44],"redundant":[47],"computation.":[48],"We":[49],"focus":[50],"on":[51,146],"applying":[52],"these":[53],"smooth":[57,144],"operator,":[58],"which":[59],"successively":[60],"reduces":[61],"error":[63],"accounts":[65],"largest":[68],"fraction":[69],"GMG":[72],"execution":[73],"time.":[74],"Our":[75],"technology":[77],"applies":[78],"both":[79],"novel":[80],"known":[82],"transformations":[83],"derive":[85],"an":[86,97],"implementation":[87,122],"comparable":[88],"manually-tuned":[90,156],"code.":[91,157],"To":[92],"make":[93],"portable,":[96],"underlying":[98],"autotuning":[99],"system":[100],"explores":[101],"tradeoff":[103],"between":[104],"reduced":[105],"increased":[108],"computation,":[109],"as":[110,112],"well":[111],"tradeoffs":[113],"threading":[115],"schemes,":[116],"automatically":[118],"identify":[119],"best":[121],"particular":[125],"architecture":[126],"each":[129],"computation":[130],"phase.":[131],"Results":[132],"show":[133],"that":[134],"we":[135,159],"are":[136],"able":[137],"quadruple":[139],"performance":[141,152],"operation":[145],"finest":[148],"grids":[149],"while":[150],"attaining":[151],"within":[153],"94%":[154],"Overall":[158],"improve":[160],"overall":[162],"solve":[164],"time":[165],"by":[166],"2.5\u00d7":[167],"without":[168],"sacrificing":[169],"programer":[170],"productivity.":[171]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
