{"id":"https://openalex.org/W2788700790","doi":"https://doi.org/10.1145/3162957.3163049","title":"A hierarchical grid algorithm for accelerating high-performance conjugate gradient benchmark on sunway many-core processor","display_name":"A hierarchical grid algorithm for accelerating high-performance conjugate gradient benchmark on sunway many-core processor","publication_year":2017,"publication_date":"2017-11-24","ids":{"openalex":"https://openalex.org/W2788700790","doi":"https://doi.org/10.1145/3162957.3163049","mag":"2788700790"},"language":"en","primary_location":{"id":"doi:10.1145/3162957.3163049","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3162957.3163049","pdf_url":null,"source":{"id":"https://openalex.org/S4306523808","display_name":"Proceedings of the 3rd International Conference on Communication and Information Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Communication and Information Processing","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/A5002768546","display_name":"Chenzhi Liao","orcid":"https://orcid.org/0009-0003-5645-4167"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenzhi Liao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101436158","display_name":"Junshi Chen","orcid":"https://orcid.org/0000-0002-6487-3658"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junshi Chen","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108198361","display_name":"Wenting Han","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenting Han","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016089490","display_name":"Huanqi Cao","orcid":"https://orcid.org/0000-0002-3870-106X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanqi Cao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070905264","display_name":"Zhichao Su","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhichao Su","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093259863","display_name":"Wanwang Yin","orcid":"https://orcid.org/0000-0003-3680-2681"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wanwang Yin","raw_affiliation_strings":["Computer Engineering and Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering and Technology, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085758579","display_name":"Hong An","orcid":"https://orcid.org/0000-0002-3900-3722"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong An","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5002768546"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.19587629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"361","last_page":"368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9973000288009644,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8393129110336304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.818777859210968},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.518210232257843},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5156782865524292},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.5083605647087097},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.47225871682167053},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.4572242796421051},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.43409931659698486},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3277170658111572},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.28780144453048706}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8393129110336304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.818777859210968},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.518210232257843},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5156782865524292},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.5083605647087097},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.47225871682167053},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.4572242796421051},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.43409931659698486},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3277170658111572},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.28780144453048706},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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:10.1145/3162957.3163049","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3162957.3163049","pdf_url":null,"source":{"id":"https://openalex.org/S4306523808","display_name":"Proceedings of the 3rd International Conference on Communication and Information Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Communication and Information Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"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/W1964639877","https://openalex.org/W2009196736","https://openalex.org/W2048835230","https://openalex.org/W2057361098","https://openalex.org/W2061126601","https://openalex.org/W2066943869","https://openalex.org/W2093166684","https://openalex.org/W2103598837","https://openalex.org/W2104093862","https://openalex.org/W2111784516","https://openalex.org/W2169076304","https://openalex.org/W2314577266","https://openalex.org/W2331164610","https://openalex.org/W2475126267","https://openalex.org/W2495635468","https://openalex.org/W2562913534"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W3012895752","https://openalex.org/W2767857528","https://openalex.org/W2185482126"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2,26],"analysis":[3],"and":[4,21,30,40,62,69,72,83,96,99,117,139,169,172,179],"optimizations":[5,101],"for":[6,81,86],"High":[7],"Performance":[8],"Conjugate":[9],"Gradient":[10],"benchmark":[11],"(HPCG)":[12],"on":[13,122,156,183],"the":[14,52,78,114,123,134,163,184],"Sunway":[15,157,185],"many-core":[16,22,187],"processor.":[17,128,188],"For":[18,76],"modern":[19],"multi-core":[20],"processors,":[23],"HPCG":[24],"always":[25],"a":[27,90],"poor":[28,79],"performance":[29,74,105,116],"under-utilizes":[31],"computation":[32],"resource":[33],"because":[34],"of":[35,106,113,126,165],"its":[36],"low":[37],"arithmetic":[38],"intensity":[39],"fine-grain":[41],"parallelism.":[42],"We":[43],"apply":[44],"two":[45],"conventional":[46],"methods":[47],"to":[48,151],"parallel":[49,167],"Gauss-Seidel":[50],"smoother":[51],"most":[53],"time":[54],"consumer":[55],"kernel":[56],"in":[57],"HPCG,":[58],"including":[59],"Level-Scheduling":[60],"(LS)":[61],"Multi-Coloring":[63],"(MC).":[64],"These":[65],"strategies":[66,171],"are":[67],"effective":[68],"achieve":[70,102],"1.54x":[71],"5.52x":[73],"improvement.":[75],"overcoming":[77],"locality":[80],"MC":[82],"limited":[84],"parallelism":[85],"LS,":[87],"we":[88,132,142,161],"propose":[89],"novel":[91],"Hierarchical":[92],"Grid":[93],"(HG)":[94],"algorithm":[95],"our":[97,166],"algorithmic":[98],"architecture-aware":[100],"an":[103],"aggregated":[104],"3.54":[107],"Gflops,":[108],"which":[109],"is":[110],"around":[111],"0.475%":[112],"peak":[115],"15.4x":[118],"higher":[119],"than":[120],"reference":[121],"single":[124],"core-group":[125],"SW26010":[127],"With":[129],"MPI":[130],"parallelize,":[131],"balance":[133],"parallelism,":[135],"pre-processing,":[136],"convergence":[137],"rate":[138],"communication":[140],"overheads,":[141],"achieved":[143],"192":[144],"TFlops":[145],"(70%":[146],"parallelization":[147],"efficiency)":[148],"when":[149,177],"scaling":[150],"81920":[152],"CGs":[153],"(5,324,800":[154],"cores)":[155],"Taihulight":[158],"System.":[159],"Moreover,":[160],"analyze":[162],"adaptability":[164],"method":[168],"optimization":[170],"summarize":[173],"several":[174],"key":[175],"points":[176],"refactoring":[178],"optimizing":[180],"HPC":[181],"applications":[182],"heterogeneous":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-10T00:00:00"}