{"id":"https://openalex.org/W3006682113","doi":"https://doi.org/10.1145/3332466.3374530","title":"Revisiting linpack algorithm on large-scale CPU-GPU heterogeneous systems","display_name":"Revisiting linpack algorithm on large-scale CPU-GPU heterogeneous systems","publication_year":2020,"publication_date":"2020-02-19","ids":{"openalex":"https://openalex.org/W3006682113","doi":"https://doi.org/10.1145/3332466.3374530","mag":"3006682113"},"language":"en","primary_location":{"id":"doi:10.1145/3332466.3374530","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3332466.3374530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","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/A5046523383","display_name":"Chaoyang Shui","orcid":"https://orcid.org/0000-0003-4008-0036"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoyang Shui","raw_affiliation_strings":["Chinese Academy of Sciences and University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences and University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008294692","display_name":"Xianzhi Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianzhi Yu","raw_affiliation_strings":["Chinese Academy of Sciences and University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences and University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112618380","display_name":"Yujin Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujin Yan","raw_affiliation_strings":["Chinese Academy of Sciences and University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences and University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067345513","display_name":"Yinshan Wang","orcid":"https://orcid.org/0000-0001-7773-887X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinshan Wang","raw_affiliation_strings":["Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085785563","display_name":"Ke Meng","orcid":"https://orcid.org/0000-0001-7293-0248"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Meng","raw_affiliation_strings":["Chinese Academy of Sciences and University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences and University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104072170","display_name":"Guangming Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Tan","raw_affiliation_strings":["Chinese Academy of Sciences and University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences and University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"411","last_page":"412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.4918000102043152,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.4918000102043152,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.4235999882221222,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7798576951026917},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7212783098220825},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5386741757392883},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4841064214706421},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4033247232437134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7798576951026917},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7212783098220825},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5386741757392883},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4841064214706421},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4033247232437134},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3332466.3374530","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3332466.3374530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W1777209000"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857"],"abstract_inverted_index":{"As":[0],"the":[1,39,63,86,107],"widening":[2],"gap":[3],"between":[4],"GPU":[5,43],"computing":[6],"capability":[7],"and":[8,14,73],"other":[9],"components":[10],"(CPU,":[11],"PCIe":[12,51],"bus":[13],"communication":[15,54],"network),":[16],"it's":[17],"increasingly":[18],"challenging":[19],"to":[20,42,71],"design":[21,89],"high":[22],"performance":[23],"parallel":[24],"algorithms":[25],"for":[26],"large":[27,45],"CPU-GPU":[28],"heterogeneous":[29],"systems.":[30],"There":[31],"are":[32],"mainly":[33],"two":[34],"reasons.":[35],"Firstly,":[36],"simply":[37],"offloading":[38],"kernel":[40],"library":[41],"incurs":[44],"volume":[46],"data":[47],"transfer":[48],"through":[49,56],"low-speed":[50],"bus.":[52],"Secondly,":[53],"overheads":[55],"network":[57],"severely":[58],"affects":[59],"scalability.":[60],"To":[61],"solve":[62],"above":[64],"issues,":[65],"we":[66],"advocate":[67],"a":[68,83],"paradigm":[69,90],"shift":[70],"CPU-centric":[72],"fine-grained":[74],"pipelining":[75],"algorithm":[76,88],"design.":[77],"By":[78],"taking":[79],"Linpack":[80,96],"benchmark":[81],"as":[82],"case":[84],"study,":[85],"new":[87],"shows":[91],"its":[92],"effectiveness.":[93],"Our":[94],"optimized":[95],"program":[97],"achieves":[98],"63.79PFlops":[99],"on":[100,113],"16384":[101],"GPUs.":[102],"Its":[103],"floating-point":[104],"efficiency":[105],"outperforms":[106],"NVIDIA":[108],"proprietary":[109],"counterparts":[110],"by":[111],"5%":[112],"average.":[114]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}