{"id":"https://openalex.org/W2066943869","doi":"https://doi.org/10.1109/padsw.2014.7097852","title":"Accelerating HPCG on Tianhe-2: A hybrid CPU-MIC algorithm","display_name":"Accelerating HPCG on Tianhe-2: A hybrid CPU-MIC algorithm","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2066943869","doi":"https://doi.org/10.1109/padsw.2014.7097852","mag":"2066943869"},"language":"en","primary_location":{"id":"doi:10.1109/padsw.2014.7097852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/padsw.2014.7097852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS)","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/A5100668127","display_name":"Yiqun Liu","orcid":"https://orcid.org/0009-0005-7882-5672"},"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"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"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":"Yiqun Liu","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101439309","display_name":"Xianyi Zhang","orcid":"https://orcid.org/0000-0003-4850-0672"},"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"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"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":"Xianyi Zhang","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005718995","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0001-7426-6248"},"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"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yang","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Comuter Science, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"raw_affiliation_string":"State Key Laboratory of Comuter Science, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386525","display_name":"Fangfang Liu","orcid":"https://orcid.org/0000-0003-1677-1128"},"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"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangfang Liu","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633465","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0001-5315-3375"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["Dept. of Computer Science & Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science & Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4107,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.80320537,"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":"542","last_page":"551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9973000288009644,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/xeon-phi","display_name":"Xeon Phi","score":0.7657345533370972},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7497282028198242},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7492570877075195},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.6418874263763428},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.5505868196487427},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5378707051277161},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4846213757991791},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.48012590408325195},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.46162062883377075},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4358361065387726},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.41792023181915283},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3739256262779236},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32465681433677673},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1536736786365509},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1161050796508789},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.09413197636604309}],"concepts":[{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.7657345533370972},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7497282028198242},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7492570877075195},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.6418874263763428},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.5505868196487427},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5378707051277161},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4846213757991791},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.48012590408325195},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.46162062883377075},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4358361065387726},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.41792023181915283},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3739256262779236},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32465681433677673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1536736786365509},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1161050796508789},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.09413197636604309},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/padsw.2014.7097852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/padsw.2014.7097852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324150","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W105754624","https://openalex.org/W993511226","https://openalex.org/W1252105715","https://openalex.org/W1525058640","https://openalex.org/W1588915715","https://openalex.org/W1917878424","https://openalex.org/W1964639877","https://openalex.org/W1987840949","https://openalex.org/W2045175083","https://openalex.org/W2049846809","https://openalex.org/W2087479145","https://openalex.org/W2099625934","https://openalex.org/W2103877122","https://openalex.org/W2150319905","https://openalex.org/W2160106616","https://openalex.org/W2169076304","https://openalex.org/W2518567779","https://openalex.org/W2587647010","https://openalex.org/W4241696959"],"related_works":["https://openalex.org/W2213533160","https://openalex.org/W4252450863","https://openalex.org/W2467043670","https://openalex.org/W2085105049","https://openalex.org/W3203561460","https://openalex.org/W3009624197","https://openalex.org/W4251138667","https://openalex.org/W2682544458","https://openalex.org/W1981810806","https://openalex.org/W2279642117"],"abstract_inverted_index":{"In":[0,29],"this":[1],"paper,":[2],"we":[3,119,187],"propose":[4],"a":[5,20,38,41,60,71,168],"hybrid":[6,31],"algorithm":[7],"to":[8,37,50,70,79,91,102,126],"enable":[9],"and":[10,55,74,93,108,147,159,164,181],"accelerate":[11],"the":[12,30,75,81,94,113,132,141,148,201],"High":[13],"Performance":[14],"Conjugate":[15],"Gradient":[16],"(HPCG)":[17],"benchmark":[18],"on":[19,161],"heterogeneous":[21],"node":[22,39,170],"with":[23,59,116,131],"an":[24,56,121,177,190],"arbitrary":[25],"number":[26],"of":[27,96,171,176,193,200],"accelerators.":[28],"algorithm,":[32],"each":[33],"subdomain":[34,46],"is":[35,47,68,77,89,99,174,197],"assigned":[36,69,90],"after":[40],"three-dimensional":[42],"domain":[43],"decomposition.":[44],"The":[45,85],"further":[48],"divided":[49],"several":[51],"regular":[52],"inner":[53,66],"blocks":[54],"outer":[57,87],"part":[58,88],"flexible":[61],"inner-outer":[62],"partitioning":[63],"strategy.":[64],"Each":[65],"task":[67],"MIC":[72],"device":[73],"size":[76,98],"adjustable":[78,101],"adapt":[80],"accelerator's":[82],"computational":[83,114],"power.":[84],"only":[86],"CPU":[92,107,158],"thickness":[95],"boundary":[97],"also":[100],"maintain":[103],"load":[104],"balance":[105],"between":[106],"MICs.":[109],"By":[110],"properly":[111],"fusing":[112],"kernels":[115],"preceding":[117],"ones,":[118],"present":[120],"asynchronous":[122],"data":[123,134],"transfer":[124],"scheme":[125],"better":[127],"overlap":[128],"local":[129],"computation":[130],"PCI-express":[133],"transfer.":[135],"All":[136],"basic":[137],"HPCG":[138],"kernels,":[139],"especially":[140],"time-consuming":[142],"sparse":[143],"matrix-vector":[144],"multiplication":[145],"(SpMV)":[146],"symmetric":[149],"Gauss-Seidel":[150],"relaxation":[151],"(SymGS),":[152],"are":[153],"extensively":[154],"optimized":[155],"for":[156],"both":[157,162],"MIC,":[160],"algorithmic":[163],"architectural":[165],"levels.":[166],"On":[167],"single":[169],"Tianhe-2":[172],"which":[173,196],"composed":[175],"Intel":[178,183],"Xeon":[179,184],"processor":[180],"three":[182],"Phi":[185],"coprocessors,":[186],"successfully":[188],"obtain":[189],"aggregated":[191],"performance":[192],"50.2":[194],"Gflops,":[195],"around":[198],"1.5%":[199],"peak":[202],"performance.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
