{"id":"https://openalex.org/W2984305089","doi":"https://doi.org/10.1145/3295500.3356181","title":"Red-blue pebbling revisited","display_name":"Red-blue pebbling revisited","publication_year":2019,"publication_date":"2019-11-07","ids":{"openalex":"https://openalex.org/W2984305089","doi":"https://doi.org/10.1145/3295500.3356181","mag":"2984305089"},"language":"en","primary_location":{"id":"doi:10.1145/3295500.3356181","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3295500.3356181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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/A5056811919","display_name":"Grzegorz Kwa\u015bniewski","orcid":"https://orcid.org/0000-0001-8943-1381"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Grzegorz Kwasniewski","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075206643","display_name":"Marko Kabi\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marko Kabi\u0107","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056549312","display_name":"Maciej Besta","orcid":"https://orcid.org/0000-0002-6550-7916"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Maciej Besta","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046896923","display_name":"Joost VandeVondele","orcid":"https://orcid.org/0000-0002-0902-5111"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Joost VandeVondele","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083650104","display_name":"Raffaele Solc\u00e0","orcid":"https://orcid.org/0009-0009-9346-4376"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Raffaele Solc\u00e0","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026990786","display_name":"Torsten Hoefler","orcid":"https://orcid.org/0000-0002-1333-9797"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Torsten Hoefler","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.0551,"has_fulltext":false,"cited_by_count":104,"citation_normalized_percentile":{"value":0.99518866,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10829","display_name":"Interconnection Networks and Systems","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8022676706314087},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6790128350257874},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6570327281951904},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.6432704329490662},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5564586520195007},{"id":"https://openalex.org/keywords/constructive","display_name":"Constructive","score":0.5468123555183411},{"id":"https://openalex.org/keywords/mathematical-proof","display_name":"Mathematical proof","score":0.511358916759491},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4949726462364197},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.4879571795463562},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4699772894382477},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4432772696018219},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.43783196806907654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1482338309288025},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12171405553817749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8022676706314087},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6790128350257874},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6570327281951904},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.6432704329490662},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5564586520195007},{"id":"https://openalex.org/C2778701210","wikidata":"https://www.wikidata.org/wiki/Q28130034","display_name":"Constructive","level":3,"score":0.5468123555183411},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.511358916759491},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4949726462364197},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.4879571795463562},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4699772894382477},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4432772696018219},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.43783196806907654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1482338309288025},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12171405553817749},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3295500.3356181","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3295500.3356181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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":67,"referenced_works":["https://openalex.org/W201315547","https://openalex.org/W1487444668","https://openalex.org/W1512166633","https://openalex.org/W1530803551","https://openalex.org/W1559533846","https://openalex.org/W1585509108","https://openalex.org/W1598993252","https://openalex.org/W1605716176","https://openalex.org/W1665157575","https://openalex.org/W1709798952","https://openalex.org/W1947869163","https://openalex.org/W1964711958","https://openalex.org/W1965460093","https://openalex.org/W1966234748","https://openalex.org/W1972501001","https://openalex.org/W1996473026","https://openalex.org/W2003368909","https://openalex.org/W2003804316","https://openalex.org/W2010747199","https://openalex.org/W2011446797","https://openalex.org/W2012652661","https://openalex.org/W2030167104","https://openalex.org/W2035476608","https://openalex.org/W2038142281","https://openalex.org/W2039747889","https://openalex.org/W2056736187","https://openalex.org/W2056999868","https://openalex.org/W2061851195","https://openalex.org/W2063249715","https://openalex.org/W2068277524","https://openalex.org/W2073948477","https://openalex.org/W2082292996","https://openalex.org/W2091782827","https://openalex.org/W2095875205","https://openalex.org/W2105605904","https://openalex.org/W2113338557","https://openalex.org/W2117293168","https://openalex.org/W2119609467","https://openalex.org/W2127226421","https://openalex.org/W2129418947","https://openalex.org/W2164946224","https://openalex.org/W2165874743","https://openalex.org/W2168748809","https://openalex.org/W2207785195","https://openalex.org/W2399402693","https://openalex.org/W2461193710","https://openalex.org/W2483598939","https://openalex.org/W2498485724","https://openalex.org/W2505191697","https://openalex.org/W2572292438","https://openalex.org/W2587361583","https://openalex.org/W2618525552","https://openalex.org/W2677289244","https://openalex.org/W2732588537","https://openalex.org/W2750060229","https://openalex.org/W2752885492","https://openalex.org/W2767319308","https://openalex.org/W2788193959","https://openalex.org/W2884834742","https://openalex.org/W2924040443","https://openalex.org/W3098650335","https://openalex.org/W3100464736","https://openalex.org/W3102191699","https://openalex.org/W4236558082","https://openalex.org/W4239248483","https://openalex.org/W4298225400","https://openalex.org/W4301621763"],"related_works":["https://openalex.org/W2808944898","https://openalex.org/W3196207352","https://openalex.org/W2951724202","https://openalex.org/W3084261076","https://openalex.org/W1996614773","https://openalex.org/W4387820098","https://openalex.org/W2959217929","https://openalex.org/W4242866892","https://openalex.org/W84644661","https://openalex.org/W42551271"],"abstract_inverted_index":{"We":[0],"propose":[1],"COSMA:":[2],"a":[3,35,69],"parallel":[4,75],"matrix-matrix":[5],"multiplication":[6],"algorithm":[7],"that":[8],"is":[9,28,144],"near":[10],"communication-optimal":[11],"for":[12,39],"all":[13,118],"combinations":[14],"of":[15,37,41,130],"matrix":[16,97],"dimensions,":[17,98],"processor":[18,88],"counts,":[19],"and":[20,46,67,71,74,91,114,143],"memory":[21],"sizes.":[22],"The":[23],"key":[24],"idea":[25],"behind":[26],"COSMA":[27,108],"to":[29,34,62,81,95,105,121,128],"derive":[30,68],"an":[31,147],"optimal":[32],"(up":[33],"factor":[36],"0.03%":[38],"10MB":[40],"fast":[42],"memory)":[43],"sequential":[44,73],"schedule":[45],"then":[47,92],"parallelize":[48],"it,":[49],"preserving":[50],"I/O":[51,76],"optimality.":[52],"To":[53],"achieve":[54],"this,":[55],"we":[56],"use":[57],"the":[58,96,110],"red-blue":[59],"pebble":[60],"game":[61],"precisely":[63],"model":[64],"MMM":[65],"dependencies":[66],"constructive":[70],"tight":[72],"lower":[77],"bound":[78],"proofs.":[79],"Compared":[80],"2D":[82],"or":[83],"3D":[84],"algorithms,":[85],"which":[86],"fix":[87],"decomposition":[89],"upfront":[90],"map":[93],"it":[94,99],"reduces":[100],"communication":[101],"volume":[102],"by":[103],"up":[104,120,127],"\u221a":[106],"times.":[107],"outperforms":[109],"established":[111],"ScaLAPACK,":[112],"CARMA,":[113],"CTF":[115],"algorithms":[116],"in":[117],"scenarios":[119],"12.8x":[122],"(2.2x":[123],"on":[124],"average),":[125],"achieving":[126],"88%":[129],"Piz":[131],"Daint's":[132],"peak":[133],"performance.":[134],"Our":[135],"work":[136],"does":[137],"not":[138],"require":[139],"any":[140],"hand":[141],"tuning":[142],"maintained":[145],"as":[146],"open":[148],"source":[149],"implementation.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}