{"id":"https://openalex.org/W2145194992","doi":"https://doi.org/10.1109/ipdps.2008.4536305","title":"Avoiding communication in sparse matrix computations","display_name":"Avoiding communication in sparse matrix computations","publication_year":2008,"publication_date":"2008-04-01","ids":{"openalex":"https://openalex.org/W2145194992","doi":"https://doi.org/10.1109/ipdps.2008.4536305","mag":"2145194992"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2008.4536305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2008.4536305","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"Proceedings - IEEE International Parallel and Distributed Processing Symposium","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Symposium on Parallel and Distributed Processing","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/A5091434158","display_name":"J. Demmel","orcid":"https://orcid.org/0000-0002-0550-5476"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Demmel","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California Berkeley, USA","Dept. of Electr. Eng. & Comput. Sci., Univ. of California at Berkeley, Berkeley, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Dept. of Electr. Eng. & Comput. Sci., Univ. of California at Berkeley, Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071661180","display_name":"Mark Frederick Hoemmen","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hoemmen","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California Berkeley, USA","Dept. of Electr. Eng. & Comput. Sci., Univ. of California at Berkeley, Berkeley, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Dept. of Electr. Eng. & Comput. Sci., Univ. of California at Berkeley, Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005444139","display_name":"Marghoob Mohiyuddin","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marghoob Mohiyuddin","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California Berkeley, USA","Dept. of Electr. Eng. & Comput. Sci., Univ. of California at Berkeley, Berkeley, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Dept. of Electr. Eng. & Comput. Sci., Univ. of California at Berkeley, Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091741596","display_name":"Katherine Yelick","orcid":"https://orcid.org/0000-0003-0957-701X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine Yelick","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California Berkeley, USA","Dept. of Electr. Eng. & Comput. Sci., Univ. of California at Berkeley, Berkeley, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Dept. of Electr. Eng. & Comput. Sci., Univ. of California at Berkeley, Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":134,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9980000257492065,"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":0.7506273984909058},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.647621750831604},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5896893739700317},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5145401358604431},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4993252754211426},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4648861587047577},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4512525796890259},{"id":"https://openalex.org/keywords/krylov-subspace","display_name":"Krylov subspace","score":0.4416520893573761},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.41430145502090454},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4049660563468933},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3899051547050476},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.21347546577453613},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17071691155433655},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.1275559961795807},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.10250577330589294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506273984909058},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.647621750831604},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5896893739700317},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5145401358604431},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4993252754211426},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4648861587047577},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4512525796890259},{"id":"https://openalex.org/C147060835","wikidata":"https://www.wikidata.org/wiki/Q1757151","display_name":"Krylov subspace","level":3,"score":0.4416520893573761},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.41430145502090454},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4049660563468933},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3899051547050476},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.21347546577453613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17071691155433655},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.1275559961795807},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.10250577330589294},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2008.4536305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2008.4536305","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"Proceedings - IEEE International Parallel and Distributed Processing Symposium","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Symposium on Parallel and Distributed Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.218.7402","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.218.7402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bebop.cs.berkeley.edu/pubs/mohiyuddin2008-ipdps-akx.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":29,"referenced_works":["https://openalex.org/W11206411","https://openalex.org/W28521761","https://openalex.org/W143824389","https://openalex.org/W1498251975","https://openalex.org/W1506457201","https://openalex.org/W1600567712","https://openalex.org/W1605308404","https://openalex.org/W1774469134","https://openalex.org/W1968347730","https://openalex.org/W1972501001","https://openalex.org/W1990832096","https://openalex.org/W1999563089","https://openalex.org/W2008946650","https://openalex.org/W2029830594","https://openalex.org/W2055253125","https://openalex.org/W2066692739","https://openalex.org/W2099625934","https://openalex.org/W2105745683","https://openalex.org/W2124613228","https://openalex.org/W2129471558","https://openalex.org/W2160106616","https://openalex.org/W2167713801","https://openalex.org/W2167868137","https://openalex.org/W2296218291","https://openalex.org/W6600451905","https://openalex.org/W6638047330","https://openalex.org/W6684745099","https://openalex.org/W6902605983","https://openalex.org/W7057659579"],"related_works":["https://openalex.org/W2798286561","https://openalex.org/W3161880765","https://openalex.org/W1599640686","https://openalex.org/W2116573255","https://openalex.org/W2119553411","https://openalex.org/W2575167716","https://openalex.org/W2606609430","https://openalex.org/W2104334788","https://openalex.org/W164069037","https://openalex.org/W4245173885"],"abstract_inverted_index":{"The":[0],"performance":[1,189,226],"of":[2,116,123,138,145,156,191,207,228,238,277],"sparse":[3,10,36,51,181],"iterative":[4,52],"solvers":[5],"is":[6,14,121,143,154,281],"typically":[7],"limited":[8,16],"by":[9,17,74],"matrix-vector":[11],"multiplication,":[12],"which":[13,113,166,280],"itself":[15],"memory":[18,99],"system":[19],"and":[20,28,71,98,127,136,150,196,199,215,246,259,273],"network":[21,93],"performance.":[22],"As":[23],"the":[24,54,114,124,134,169,222,229,266,284],"gap":[25],"between":[26],"computation":[27,220],"communication":[29,84,88,94],"speed":[30],"continues":[31],"to":[32,160,209,217,240,248,255,261,283],"widen,":[33],"these":[34,174],"traditional":[35],"methods":[37],"will":[38],"suffer.":[39],"In":[40,105],"this":[41,78],"paper":[42],"we":[43,80,107,251,264],"focus":[44],"on":[45,211,219,242,268],"an":[46,243,269],"alternative":[47],"building":[48],"block":[49],"for":[50,112,179],"solvers,":[53],"\"matrix":[55],"powers":[56],"kernel\"":[57],"[x,":[58],"Ax,":[59],"A":[60,66],"<sup":[61,67],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[62,68],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[63],"x,":[64],"...,":[65],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">k</sup>":[69],"x],":[70],"show":[72,200],"that":[73,131,141,183],"organizing":[75],"computations":[76],"around":[77],"kernel,":[79],"can":[81],"achieve":[82],"near-minimal":[83],"costs.":[85,152],"We":[86,186],"consider":[87],"very":[89],"broadly":[90],"as":[91],"both":[92,133,148],"in":[95,102,147],"parallel":[96,110,188],"code":[97],"hierarchy":[100],"access":[101],"sequential":[103,129,225,271],"code.":[104],"particular,":[106],"introduce":[108,187],"a":[109,128,157,204,212,235,275],"algorithm":[111,206,237],"number":[115,135],"messages":[117],"(total":[118],"latency":[119,149,258],"cost)":[120],"independent":[122,144],"power":[125],"k,":[126],"algorithm,":[130],"reduces":[132],"volume":[137],"accesses,":[139],"so":[140],"it":[142],"k":[146],"bandwidth":[151,260],"This":[153],"part":[155],"larger":[158],"project":[159],"develop":[161],"\"communication-avoiding":[162],"Krylov":[163],"subspace":[164],"methods,\"":[165],"also":[167],"addresses":[168],"numerical":[170],"issues":[171],"associated":[172],"with":[173],"methods.":[175],"Our":[176],"algorithms":[177],"work":[178],"general":[180],"matrices":[182,192],"\"partition":[184],"well\".":[185],"models":[190,227],"arising":[193],"from":[194],"2D":[195],"3D":[197],"problems":[198,231],"predicted":[201,285],"speedups":[202,233],"over":[203,234,278],"conventional":[205,236],"up":[208,216,239,247],"7times":[210],"petaflop-scale":[213],"machine":[214],"22times":[218],"across":[221],"grid.":[223],"Analogous":[224],"same":[230],"predict":[232],"10times":[241],"out-of-core":[244,270],"implementation,":[245],"2.5times":[249],"when":[250],"use":[252],"our":[253],"ideas":[254],"reduce":[256],"off-chip":[257],"DRAM.":[262],"Finally,":[263],"validate":[265],"model":[267],"implementation":[272],"measured":[274],"speedup":[276],"3times,":[279],"close":[282],"speedup.":[286]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}