{"id":"https://openalex.org/W4401308356","doi":"https://doi.org/10.1145/3675018.3675768","title":"A Comparative Analysis of Kunpeng 920 on HPC Workloads","display_name":"A Comparative Analysis of Kunpeng 920 on HPC Workloads","publication_year":2024,"publication_date":"2024-06-07","ids":{"openalex":"https://openalex.org/W4401308356","doi":"https://doi.org/10.1145/3675018.3675768"},"language":"en","primary_location":{"id":"doi:10.1145/3675018.3675768","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3675018.3675768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on High Performance Compilation, Computing and Communications","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":null,"display_name":"Yinchuan Guo","orcid":"https://orcid.org/0009-0002-5841-8330"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinchuan Guo","raw_affiliation_strings":["Sun Yat-Sen University, China"],"raw_orcid":"https://orcid.org/0009-0002-5841-8330","affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039843650","display_name":"Xianwei Zhang","orcid":"https://orcid.org/0000-0003-3507-4299"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianwei Zhang","raw_affiliation_strings":["Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0000-0003-3507-4299","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10666358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"53"},"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":0.9988999962806702,"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":0.9976000189781189,"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":0.7115321159362793},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5081844329833984},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4245016872882843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7115321159362793},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5081844329833984},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4245016872882843}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3675018.3675768","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3675018.3675768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on High Performance Compilation, Computing and Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2002555321","https://openalex.org/W2013062050","https://openalex.org/W2470920449","https://openalex.org/W2886189612","https://openalex.org/W3003489587","https://openalex.org/W3097283637","https://openalex.org/W3127172286","https://openalex.org/W3166510811","https://openalex.org/W3196990253","https://openalex.org/W4290000672","https://openalex.org/W4297492907","https://openalex.org/W4387494538","https://openalex.org/W4389433560"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"As":[0],"ARM":[1],"architecture":[2],"gains":[3],"traction":[4],"in":[5,117,130],"server":[6],"usage,":[7],"the":[8,60,91,108,141],"Kunpeng":[9,38,61,109,114,146],"920":[10,39,115],"processor,":[11],"developed":[12],"by":[13],"HiSilicon":[14],"specifically":[15],"for":[16,47,103,145],"cloud":[17],"computing,":[18],"has":[19],"emerged":[20],"as":[21],"a":[22,33,56],"notable":[23],"contender.":[24],"With":[25],"its":[26,45,64,77,122],"impressive":[27],"configuration":[28],"of":[29,35,59],"64":[30],"cores":[31],"and":[32,83,94],"bandwidth":[34],"200":[36],"GB/s,":[37],"delivers":[40],"formidable":[41],"computational":[42,78],"capability.":[43],"However,":[44],"suitability":[46],"HPC":[48,72,104],"applications":[49,105],"remains":[50],"relatively":[51],"unexplored.":[52],"This":[53],"study":[54],"conducts":[55],"comprehensive":[57],"evaluation":[58],"920,":[62],"comparing":[63],"performance":[65,84,129],"to":[66,121],"AMD":[67],"EPYC":[68],"7302":[69],"across":[70],"various":[71],"workloads.":[73,87],"We":[74,111],"delve":[75],"into":[76],"capabilities,":[79],"memory":[80,124],"subsystem":[81],"efficiency,":[82],"under":[85],"real-world":[86],"Employing":[88],"methodologies":[89],"like":[90],"roofline":[92],"model":[93],"Top-down":[95],"Microarchitecture":[96],"Analysis":[97],"(TMA),":[98],"we":[99],"identify":[100],"potential":[101],"bottlenecks":[102],"running":[106],"on":[107],"920.":[110],"reveals":[112],"that":[113],"excels":[116],"memory-intensive":[118],"tasks":[119],"due":[120],"superior":[123],"bandwidth,":[125],"while":[126],"gaining":[127],"poor":[128],"compute-intensive":[131],"tasks.":[132],"Furthermore,":[133],"this":[134],"research":[135],"uncovers":[136],"previously":[137],"unrecognized":[138],"issues":[139],"with":[140],"TMA":[142],"model\u2019s":[143],"definition":[144],"processors.":[147]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}