{"id":"https://openalex.org/W2915551302","doi":"https://doi.org/10.1109/cahpc.2018.8645938","title":"Multicore Performance Engineering of Sparse Triangular Solves Using a Modified Roofline Model","display_name":"Multicore Performance Engineering of Sparse Triangular Solves Using a Modified Roofline Model","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2915551302","doi":"https://doi.org/10.1109/cahpc.2018.8645938","mag":"2915551302"},"language":"en","primary_location":{"id":"doi:10.1109/cahpc.2018.8645938","is_oa":false,"landing_page_url":"http://doi.org/10.1109/cahpc.2018.8645938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","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/A5003949750","display_name":"Markus Wittmann","orcid":"https://orcid.org/0000-0002-4812-9052"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Markus Wittmann","raw_affiliation_strings":["Friedrich-Alexander University, Erlangen Regional Computing Center, Erlangen-N\u00fcrnberg, Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander University, Erlangen Regional Computing Center, Erlangen-N\u00fcrnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082552227","display_name":"Georg Hager","orcid":"https://orcid.org/0000-0002-8723-2781"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georg Hager","raw_affiliation_strings":["Friedrich-Alexander University, Erlangen Regional Computing Center, Erlangen-N\u00fcrnberg, Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander University, Erlangen Regional Computing Center, Erlangen-N\u00fcrnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069917571","display_name":"Radim Janal\u00edk","orcid":null},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Radim Janalik","raw_affiliation_strings":["Faculty of Informatics, Universit\u00e1 della Svizzera italiana, Institute of Computational Science, Switzerland"],"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Universit\u00e1 della Svizzera italiana, Institute of Computational Science, Switzerland","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033189715","display_name":"Martin Lanser","orcid":"https://orcid.org/0000-0002-4232-9395"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Lanser","raw_affiliation_strings":["University of Cologne, Faculty of Mathematics and Natural Sciences, Germany"],"affiliations":[{"raw_affiliation_string":"University of Cologne, Faculty of Mathematics and Natural Sciences, Germany","institution_ids":["https://openalex.org/I180923762"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041978201","display_name":"Axel Klawonn","orcid":"https://orcid.org/0000-0003-4765-7387"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Axel Klawonn","raw_affiliation_strings":["University of Cologne, Faculty of Mathematics and Natural Sciences, Germany"],"affiliations":[{"raw_affiliation_string":"University of Cologne, Faculty of Mathematics and Natural Sciences, Germany","institution_ids":["https://openalex.org/I180923762"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012521841","display_name":"Oliver Rheinbach","orcid":"https://orcid.org/0000-0002-9310-8533"},"institutions":[{"id":"https://openalex.org/I61893789","display_name":"TU Bergakademie Freiberg","ror":"https://ror.org/031vc2293","country_code":"DE","type":"education","lineage":["https://openalex.org/I61893789"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oliver Rheinbach","raw_affiliation_strings":["TU Bergakademie Freiberg, Faculty of Mathematics and Computer Science, Germany"],"affiliations":[{"raw_affiliation_string":"TU Bergakademie Freiberg, Faculty of Mathematics and Computer Science, Germany","institution_ids":["https://openalex.org/I61893789"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017590193","display_name":"Olaf Schenk","orcid":"https://orcid.org/0000-0001-8636-1023"},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Olaf Schenk","raw_affiliation_strings":["Faculty of Informatics, Universit\u00e1 della Svizzera italiana, Institute of Computational Science, Switzerland"],"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Universit\u00e1 della Svizzera italiana, Institute of Computational Science, Switzerland","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070209050","display_name":"Gerhard Wellein","orcid":"https://orcid.org/0000-0001-7371-3026"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Wellein","raw_affiliation_strings":["Friedrich-Alexander University, Department of Computer Science, Erlangen-N\u00fcrnberg, Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander University, Department of Computer Science, Erlangen-N\u00fcrnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5003949750"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":1.2623,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80029333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"31","issue":null,"first_page":"233","last_page":"241"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9993000030517578,"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":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.8354638814926147},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.7136966586112976},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6892997026443481},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6873306035995483},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.664281964302063},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5553344488143921},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5509011149406433},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5432263016700745},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.46057748794555664},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4523738622665405},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.33748751878738403},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.19106191396713257},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14979815483093262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8354638814926147},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.7136966586112976},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6892997026443481},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6873306035995483},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.664281964302063},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5553344488143921},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5509011149406433},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5432263016700745},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.46057748794555664},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4523738622665405},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33748751878738403},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.19106191396713257},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14979815483093262},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cahpc.2018.8645938","is_oa":false,"landing_page_url":"http://doi.org/10.1109/cahpc.2018.8645938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W23806513","https://openalex.org/W151246516","https://openalex.org/W993511226","https://openalex.org/W1480947737","https://openalex.org/W1515233362","https://openalex.org/W1548589512","https://openalex.org/W1556969930","https://openalex.org/W1596846800","https://openalex.org/W1640020431","https://openalex.org/W1884004174","https://openalex.org/W1970009422","https://openalex.org/W1973166496","https://openalex.org/W2002555321","https://openalex.org/W2003105834","https://openalex.org/W2049472110","https://openalex.org/W2057577013","https://openalex.org/W2059882081","https://openalex.org/W2070299075","https://openalex.org/W2070571481","https://openalex.org/W2078636996","https://openalex.org/W2088160222","https://openalex.org/W2096642134","https://openalex.org/W2174805139","https://openalex.org/W2193930533","https://openalex.org/W2469975815","https://openalex.org/W2754559815","https://openalex.org/W3106055984","https://openalex.org/W3125983777","https://openalex.org/W3145241477","https://openalex.org/W4298218678","https://openalex.org/W6626020745","https://openalex.org/W6635603319","https://openalex.org/W6891731598"],"related_works":["https://openalex.org/W1980322368","https://openalex.org/W2096357811","https://openalex.org/W2072005592","https://openalex.org/W2031026393","https://openalex.org/W233983175","https://openalex.org/W2063611263","https://openalex.org/W2355089277","https://openalex.org/W2030992542","https://openalex.org/W2312486021","https://openalex.org/W4247995867"],"abstract_inverted_index":{"The":[0,29,72],"Roofline":[1],"model":[2,30],"is":[3,64,81,105],"widely":[4],"used":[5],"to":[6,44,108],"visualize":[7],"the":[8,15,21,25,50,68,75,99,111,119,134],"performance":[9,17,73,143],"of":[10,37,55,67,74,89],"executed":[11],"code":[12],"together":[13],"with":[14],"upper":[16],"bounds":[18],"given":[19],"by":[20],"memory":[22],"bandwidth":[23,47],"and":[24,77,83,98,118,136],"processor":[26],"peak":[27],"performance.":[28],"can":[31],"thus":[32],"provide":[33],"an":[34],"insightful":[35],"visualization":[36],"bottlenecks.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"try":[43],"establish":[45],"realistic":[46],"ceilings":[48],"for":[49,85,115,141],"sparse":[51,59,90],"triangular":[52],"solve":[53],"step":[54],"PARDISO,":[56],"a":[57,86],"leading":[58],"direct":[60],"solver":[61],"package,":[62],"which":[63],"also":[65,114],"part":[66],"Intel":[69],"MKL":[70],"library.":[71],"forward":[76],"backward":[78],"substitution":[79],"process":[80],"analyzed":[82],"benchmarked":[84],"representative":[87],"set":[88],"matrices":[91],"on":[92],"seven":[93],"modern":[94],"x86-type":[95],"multicore":[96],"architectures":[97],"Knights":[100],"Landing":[101],"manycore":[102],"architecture.":[103],"It":[104],"shown":[106],"how":[107],"accurately":[109],"measure":[110],"necessary":[112],"quantities":[113],"threaded":[116],"code,":[117],"measurement":[120],"approach,":[121],"its":[122],"validation,":[123],"as":[124,126],"well":[125],"limitations":[127],"are":[128],"discussed.":[129],"Our":[130],"modeling":[131],"approach":[132],"covers":[133],"serial":[135],"parallel":[137],"execution":[138],"phases,":[139],"allowing":[140],"in-socket":[142],"predictions.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
