{"id":"https://openalex.org/W2765277644","doi":"https://doi.org/10.1145/3149704.3149766","title":"Evaluation of Knight Landing High Bandwidth Memory for HPC Workloads","display_name":"Evaluation of Knight Landing High Bandwidth Memory for HPC Workloads","publication_year":2017,"publication_date":"2017-11-03","ids":{"openalex":"https://openalex.org/W2765277644","doi":"https://doi.org/10.1145/3149704.3149766","mag":"2765277644"},"language":"en","primary_location":{"id":"doi:10.1145/3149704.3149766","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3149704.3149766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Workshop on Irregular Applications: Architectures and Algorithms","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/A5028518972","display_name":"Solmaz Salehian","orcid":null},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Solmaz Salehian","raw_affiliation_strings":["Oakland University, Rochester, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oakland University, Rochester, MI","institution_ids":["https://openalex.org/I177721651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102715061","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0002-5274-8526"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["University of South Carolina, Columbia, SC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Carolina, Columbia, SC","institution_ids":["https://openalex.org/I155781252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7608,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.69155338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.759588360786438},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6226356625556946},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5741219520568848},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5729113221168518},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4826219975948334},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.42710429430007935},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.4112854301929474},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34202128648757935},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.33584609627723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759588360786438},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6226356625556946},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5741219520568848},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5729113221168518},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4826219975948334},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.42710429430007935},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.4112854301929474},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34202128648757935},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.33584609627723694},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3149704.3149766","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3149704.3149766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Workshop on Irregular Applications: Architectures and Algorithms","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.5899999737739563,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G7237673497","display_name":"CAREER: Programming the Existing and Emerging Memory Systems for Extreme-scale Parallel Performance","funder_award_id":"1652732","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W858404628","https://openalex.org/W1133087070","https://openalex.org/W2026247162","https://openalex.org/W2098602979","https://openalex.org/W2129960401","https://openalex.org/W2131413854","https://openalex.org/W2485412435","https://openalex.org/W2746871167","https://openalex.org/W3139689176"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2794038527","https://openalex.org/W2327638088","https://openalex.org/W2984139344"],"abstract_inverted_index":{"The":[0,56],"Intel":[1],"Knight":[2],"Landing":[3],"(KNL)":[4],"manycore":[5],"chip":[6],"includes":[7],"3D-stacked":[8],"memory":[9,66],"named":[10],"MCDRAM,":[11],"also":[12,110],"known":[13],"as":[14,70,72,85,87],"High":[15],"Bandwidth":[16],"Memory":[17],"(HBM)":[18],"for":[19,41,69,84],"parallel":[20],"applications":[21,44,68],"that":[22,59,112],"needs":[23],"to":[24,26,107,123],"scale":[25],"high":[27],"thread":[28],"count.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"provide":[34],"a":[35],"quantitative":[36],"study":[37],"of":[38,65,100],"the":[39,63,92,97,113],"KNL":[40],"HPC":[42],"proxy":[43],"including":[45],"Lulesh,":[46],"HPCG,":[47,79],"AMG,":[48],"and":[49,54,80,82,89],"Hotspot":[50],"when":[51],"using":[52],"DDR4":[53,77,103],"MCDRAM.":[55],"results":[57],"indicate":[58],"HBM":[60],"significantly":[61],"improves":[62],"performance":[64,98],"intensive":[67,95],"many":[71,86],"three":[73],"times":[74],"better":[75],"than":[76],"in":[78],"Lulesh":[81],"HPCG":[83],"40%":[88],"200%.":[90],"For":[91],"selected":[93],"compute":[94],"applications,":[96],"advantage":[99],"MCDRAM":[101,116],"over":[102],"varies":[104],"from":[105],"2%":[106],"28%.":[108],"We":[109],"observed":[111],"cross-points,":[114],"where":[115],"starts":[117],"outperforming":[118],"DDR4,":[119],"are":[120],"around":[121],"8":[122],"16":[124],"threads.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}