{"id":"https://openalex.org/W2618525552","doi":"https://doi.org/10.1145/3093172.3093228","title":"Increasing the Efficiency of Sparse Matrix-Matrix Multiplication with a 2.5D Algorithm and One-Sided MPI","display_name":"Increasing the Efficiency of Sparse Matrix-Matrix Multiplication with a 2.5D Algorithm and One-Sided MPI","publication_year":2017,"publication_date":"2017-06-23","ids":{"openalex":"https://openalex.org/W2618525552","doi":"https://doi.org/10.1145/3093172.3093228","mag":"2618525552"},"language":"en","primary_location":{"id":"doi:10.1145/3093172.3093228","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3093172.3093228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1705.10218","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101815936","display_name":"Alfio Lazzaro","orcid":"https://orcid.org/0000-0003-4256-8270"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Alfio Lazzaro","raw_affiliation_strings":["University of Z\u00fcrich, Department of Chemistry C, Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Z\u00fcrich, Department of Chemistry C, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046896923","display_name":"Joost VandeVondele","orcid":"https://orcid.org/0000-0002-0902-5111"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joost VandeVondele","raw_affiliation_strings":["CSCS, Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSCS, Z\u00fcrich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045830246","display_name":"J\u00fcrg Hutter","orcid":"https://orcid.org/0000-0002-6887-8229"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"J\u00fcrg Hutter","raw_affiliation_strings":["University of Z\u00fcrich, Department of Chemistry C, Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Z\u00fcrich, Department of Chemistry C, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018822775","display_name":"Ole Sch\u00fctt","orcid":"https://orcid.org/0009-0005-8661-3418"},"institutions":[{"id":"https://openalex.org/I71824836","display_name":"Swiss Federal Laboratories for Materials Science and Technology","ror":"https://ror.org/02x681a42","country_code":"CH","type":"facility","lineage":["https://openalex.org/I2799323385","https://openalex.org/I71824836"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ole Sch\u00fctt","raw_affiliation_strings":["Empa, D\u00fcbendorf, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Empa, D\u00fcbendorf, Switzerland","institution_ids":["https://openalex.org/I71824836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7745,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91812529,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9952999949455261,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7691468000411987},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.732392430305481},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6851929426193237},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6660911440849304},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5765429139137268},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5479684472084045},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5299977660179138},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49369677901268005},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4926379323005676},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.4804646372795105},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.43311256170272827},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4116475582122803},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.351615846157074},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15888795256614685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7691468000411987},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.732392430305481},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6851929426193237},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6660911440849304},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5765429139137268},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5479684472084045},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5299977660179138},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49369677901268005},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4926379323005676},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.4804646372795105},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43311256170272827},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4116475582122803},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.351615846157074},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15888795256614685},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3093172.3093228","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3093172.3093228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1705.10218","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.10218","pdf_url":"https://arxiv.org/pdf/1705.10218","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.5167/uzh-142892","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:dora:empa_29432","is_oa":false,"landing_page_url":"https://www.dora.lib4ri.ch/empa/islandora/object/empa%3A29432","pdf_url":null,"source":{"id":"https://openalex.org/S4306401298","display_name":"DORA Empa (Swiss Federal Laboratories for Materials Science and Technology (Empa))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71824836","host_organization_name":"Swiss Federal Laboratories for Materials Science and Technology","host_organization_lineage":["https://openalex.org/I71824836"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1705.10218","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.10218","pdf_url":"https://arxiv.org/pdf/1705.10218","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W171922849","https://openalex.org/W201315547","https://openalex.org/W988471318","https://openalex.org/W1483804921","https://openalex.org/W1554065806","https://openalex.org/W1598993252","https://openalex.org/W1810694562","https://openalex.org/W1928489786","https://openalex.org/W1997882689","https://openalex.org/W2010747199","https://openalex.org/W2012652661","https://openalex.org/W2029342163","https://openalex.org/W2080353445","https://openalex.org/W2089437293","https://openalex.org/W2122948532","https://openalex.org/W2139316564","https://openalex.org/W2235832317","https://openalex.org/W2288478597","https://openalex.org/W2298920323","https://openalex.org/W2332437841","https://openalex.org/W2416967003","https://openalex.org/W2473773726","https://openalex.org/W2479443192","https://openalex.org/W2565236682","https://openalex.org/W2950119333","https://openalex.org/W3105937213","https://openalex.org/W3121465581","https://openalex.org/W3122598445","https://openalex.org/W4244254628","https://openalex.org/W4256464778","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2124433837","https://openalex.org/W4206811032","https://openalex.org/W2995605830","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063"],"abstract_inverted_index":{"Matrix-matrix":[0],"multiplication":[1,111],"is":[2,83,103,172,177,191,201,255],"a":[3,15,115,147,150,168,240],"basic":[4,85],"operation":[5],"in":[6,20,64,99,145,243,265],"linear":[7,68,89],"algebra":[8],"and":[9,25,60,94,132,149,158,214],"an":[10,47,137],"essential":[11],"building":[12,86],"block":[13,87],"for":[14,27,88,161,194,203,245],"wide":[16],"range":[17],"of":[18,55,67,112,124,188,209,262],"algorithms":[19,59],"various":[21],"scientific":[22],"fields.":[23],"Theory":[24],"implementation":[26,45,127,138,190],"the":[28,43,53,65,77,84,122,125,189,207,210,216,222,227,232,246,260,266],"dense,":[29],"square":[30],"matrix":[31,80,218],"case":[32],"are":[33,37,229],"well-developed.":[34],"If":[35],"matrices":[36,113],"sparse,":[38],"with":[39,114,136,182,235,259],"application-specific":[40],"sparsity":[41,212],"patterns,":[42],"optimal":[44],"remains":[46],"open":[48],"question.":[49],"Here,":[50,119],"we":[51,75,120],"explore":[52],"performance":[54,123,244],"communication":[56,63,171],"reducing":[57],"2.5D":[58,151,154,175,249],"one-sided":[61,142,183],"MPI":[62,133,141],"context":[66],"scaling":[69,90,96],"electronic":[70,91],"structure":[71,92],"theory.":[72],"In":[73],"particular,":[74],"extend":[76],"DBCSR":[78],"sparse":[79],"library,":[81],"which":[82,164,220,254],"theory":[93],"low":[95],"correlated":[97],"methods":[98],"CP2K.":[100],"The":[101,153,174],"library":[102],"specifically":[104],"designed":[105],"to":[106,167,180,252,257],"efficiently":[107],"perform":[108],"block-sparse":[109],"matrix-matrix":[110],"relatively":[116],"large":[117],"occupation.":[118],"compare":[121],"original":[126],"based":[128,139,248],"on":[129,140],"Cannon's":[130],"algorithm":[131,176],"point-to-point":[134],"communication,":[135,163],"communications":[143],"(RMA),":[144],"both":[146],"2D":[148],"approach.":[152],"approach":[155],"trades":[156],"memory":[157],"auxiliary":[159],"operations":[160],"reduced":[162],"can":[165],"lead":[166],"speedup":[169],"if":[170],"dominant.":[173],"somewhat":[178],"easier":[179],"implement":[181],"communications.":[184],"A":[185],"detailed":[186],"description":[187],"provided,":[192],"also":[193],"non":[195],"ideal":[196],"processor":[197],"topologies,":[198],"since":[199],"this":[200],"important":[202],"actual":[204,217],"applications.":[205],"Given":[206],"importance":[208],"precise":[211],"pattern,":[213],"even":[215],"data,":[219],"decides":[221],"effective":[223],"fill-in":[224],"upon":[225],"multiplication,":[226],"tests":[228],"performed":[230],"within":[231],"CP2K":[233],"package":[234],"application":[236],"benchmarks.":[237],"Results":[238],"show":[239],"substantial":[241],"boost":[242],"RMA":[247],"algorithm,":[250],"up":[251],"1.80x,":[253],"observed":[256],"increase":[258],"number":[261],"processes":[263],"involved":[264],"parallelization.":[267]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2017-06-05T00:00:00"}