{"id":"https://openalex.org/W3084268001","doi":"https://doi.org/10.1109/hpcs48598.2019.9188154","title":"Scalability of Hybrid SpMV on Intel Xeon Phi Knights Landing","display_name":"Scalability of Hybrid SpMV on Intel Xeon Phi Knights Landing","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W3084268001","doi":"https://doi.org/10.1109/hpcs48598.2019.9188154","mag":"3084268001"},"language":"en","primary_location":{"id":"doi:10.1109/hpcs48598.2019.9188154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs48598.2019.9188154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on High Performance Computing & Simulation (HPCS)","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/A5090370401","display_name":"Brian A. Page","orcid":"https://orcid.org/0000-0001-5563-9678"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Brian A. Page","raw_affiliation_strings":["Dept. of Computer Science and Engineering, Univ. of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, Univ. of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029212199","display_name":"Peter M. Kogge","orcid":"https://orcid.org/0000-0002-3329-547X"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter M. Kogge","raw_affiliation_strings":["Dept. of Computer Science and Engineering, Univ. of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, Univ. of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090370401"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":1.2038,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79206888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"104","issue":null,"first_page":"348","last_page":"357"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9973999857902527,"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":0.8487741351127625},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.8375515937805176},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8161529302597046},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.7850158214569092},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6296567320823669},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5611483454704285},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5342954993247986},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.5093079805374146},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1625272035598755},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.10806602239608765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8487741351127625},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.8375515937805176},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8161529302597046},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.7850158214569092},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6296567320823669},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5611483454704285},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5342954993247986},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.5093079805374146},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1625272035598755},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.10806602239608765},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcs48598.2019.9188154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs48598.2019.9188154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on High Performance Computing & Simulation (HPCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W26556108","https://openalex.org/W858404628","https://openalex.org/W1252105715","https://openalex.org/W1525132831","https://openalex.org/W1776498962","https://openalex.org/W1984788566","https://openalex.org/W1987840949","https://openalex.org/W1993704253","https://openalex.org/W2024017047","https://openalex.org/W2035080386","https://openalex.org/W2113342867","https://openalex.org/W2124007994","https://openalex.org/W2187009734","https://openalex.org/W2217983214","https://openalex.org/W2340076492","https://openalex.org/W2527122211","https://openalex.org/W2568669383","https://openalex.org/W2600222141","https://openalex.org/W2754016293","https://openalex.org/W2791012218","https://openalex.org/W2886043722","https://openalex.org/W2898706692","https://openalex.org/W3086833716","https://openalex.org/W4293767000","https://openalex.org/W6638245406","https://openalex.org/W6743677923"],"related_works":["https://openalex.org/W1908180445","https://openalex.org/W2739740241","https://openalex.org/W1974923383","https://openalex.org/W2597386847","https://openalex.org/W2035419609","https://openalex.org/W2912502764","https://openalex.org/W1766386015","https://openalex.org/W2895895456","https://openalex.org/W1981810806","https://openalex.org/W2279642117"],"abstract_inverted_index":{"SpMV,":[0],"the":[1,61,96,134],"product":[2],"of":[3,13,17,42,60,73,118],"a":[4,8,14,54,71,116],"sparse":[5,64],"matrix":[6,119],"and":[7,23,29,52,110],"dense":[9],"vector,":[10],"is":[11,45,131],"emblematic":[12],"new":[15],"class":[16],"applications":[18],"that":[19,124],"are":[20,113],"memory":[21],"bandwidth":[22],"communication,":[24],"not":[25,94],"flop,":[26],"driven.":[27],"Sparsity":[28],"randomness":[30],"in":[31],"such":[32],"computations":[33],"play":[34],"havoc":[35],"with":[36,105],"performance,":[37,91],"especially":[38],"when":[39],"strong,":[40],"instead":[41],"weak,":[43],"scaling":[44,59],"attempted.":[46],"In":[47],"this":[48],"study":[49],"we":[50],"develop":[51],"evaluate":[53],"hybrid":[55,85],"implementation":[56,87],"for":[57],"strong":[58],"Compressed":[62],"Vectorization-oriented":[63],"Row":[65],"(CVR)":[66],"approach":[67],"to":[68],"SpMV":[69,86],"on":[70],"cluster":[72],"Intel":[74],"Xeon":[75],"Phi":[76],"Knights":[77],"Landing":[78],"(KNL)":[79],"processors.":[80],"We":[81],"show":[82],"how":[83],"our":[84],"achieves":[88],"increased":[89],"computational":[90,139],"yet":[92],"does":[93],"address":[95],"dominant":[97,135],"communication":[98,129],"overhead":[99,130],"factor":[100,136],"at":[101],"extreme":[102],"scale.":[103],"Issues":[104],"workload":[106],"distribution,":[107],"data":[108],"placement,":[109],"remote":[111],"reductions":[112],"assessed":[114],"over":[115],"range":[117],"characteristics.":[120],"Our":[121],"results":[122],"indicate":[123],"as":[125],"P":[126],"\u2192":[127],"\u221e":[128],"by":[132],"far":[133],"despite":[137],"improved":[138],"performance.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}