{"id":"https://openalex.org/W4383501647","doi":"https://doi.org/10.1109/aicas57966.2023.10168586","title":"Task-aware Scheduling and Performance Optimization on Yitian710 SoC for GEMM-based Workloads on the Cloud","display_name":"Task-aware Scheduling and Performance Optimization on Yitian710 SoC for GEMM-based Workloads on the Cloud","publication_year":2023,"publication_date":"2023-06-11","ids":{"openalex":"https://openalex.org/W4383501647","doi":"https://doi.org/10.1109/aicas57966.2023.10168586"},"language":"en","primary_location":{"id":"doi:10.1109/aicas57966.2023.10168586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas57966.2023.10168586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","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/A5101135416","display_name":"Guosheng Yu","orcid":"https://orcid.org/0009-0007-2552-3982"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guosheng Yu","raw_affiliation_strings":["Alibaba Group,T-Head Semiconductor Co., Ltd,Hangzhou,China","T-Head Semiconductor Co., Ltd, Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,T-Head Semiconductor Co., Ltd,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"T-Head Semiconductor Co., Ltd, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102604832","display_name":"Zhihong Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihong Lv","raw_affiliation_strings":["Alibaba Group,T-Head Semiconductor Co., Ltd,Hangzhou,China","T-Head Semiconductor Co., Ltd, Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,T-Head Semiconductor Co., Ltd,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"T-Head Semiconductor Co., Ltd, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977870","display_name":"Haijiang Wang","orcid":"https://orcid.org/0000-0002-9386-2536"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijiang Wang","raw_affiliation_strings":["Alibaba Group,T-Head Semiconductor Co., Ltd,Hangzhou,China","T-Head Semiconductor Co., Ltd, Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,T-Head Semiconductor Co., Ltd,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"T-Head Semiconductor Co., Ltd, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100958866","display_name":"Zilong Huang","orcid":"https://orcid.org/0009-0009-4735-0749"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilong Huang","raw_affiliation_strings":["Alibaba Group,T-Head Semiconductor Co., Ltd,Hangzhou,China","T-Head Semiconductor Co., Ltd, Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,T-Head Semiconductor Co., Ltd,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"T-Head Semiconductor Co., Ltd, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102995032","display_name":"Jicheng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jicheng Chen","raw_affiliation_strings":["Alibaba Group,T-Head Semiconductor Co., Ltd,Hangzhou,China","T-Head Semiconductor Co., Ltd, Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,T-Head Semiconductor Co., Ltd,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"T-Head Semiconductor Co., Ltd, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9990000128746033,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8943986892700195},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.589926540851593},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5781495571136475},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5561702847480774},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5184506773948669},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5121626853942871},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.49760034680366516},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4585729241371155},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35342907905578613},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19470268487930298}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8943986892700195},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.589926540851593},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5781495571136475},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5561702847480774},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5184506773948669},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5121626853942871},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.49760034680366516},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4585729241371155},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35342907905578613},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19470268487930298},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aicas57966.2023.10168586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas57966.2023.10168586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.44999998807907104,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1970270050","https://openalex.org/W1972541235","https://openalex.org/W1983157164","https://openalex.org/W2027753527","https://openalex.org/W2059094285","https://openalex.org/W2073061372","https://openalex.org/W2076491133","https://openalex.org/W2888498443","https://openalex.org/W2902578338","https://openalex.org/W3043571714","https://openalex.org/W3166510811","https://openalex.org/W4210485326","https://openalex.org/W4241749013","https://openalex.org/W6769454693","https://openalex.org/W6812105144"],"related_works":["https://openalex.org/W986318368","https://openalex.org/W2000785801","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2990194547","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W1480123525","https://openalex.org/W2620865396","https://openalex.org/W2414054180"],"abstract_inverted_index":{"The":[0,39,146,169],"YiTian710":[1,125,162],"SoC":[2],"is":[3,43,64,84],"a":[4,67,131],"server":[5],"processor":[6],"based":[7,163],"on":[8],"ARM":[9],"Neoverse":[10],"N2":[11],"architecture":[12],"and":[13,46,71,96,115,120],"developed":[14,151],"by":[15],"T-HEAD":[16],"Semiconductor":[17],"Co.,":[18],"Ltd.":[19],"to":[20,77,110,142,152],"accelerate":[21],"the":[22,28,44,47,56,60,72,79,86,89,105,112,117,121,124,139,154,159],"compute-intensive":[23],"tasks":[24],"in":[25,36,55,161],"Alicloud,":[26],"where":[27],"ML":[29,57,113],"related":[30],"workloads":[31,91,114],"play":[32],"an":[33],"important":[34,49],"role":[35],"various":[37],"applications.":[38,168,182],"General":[40],"Matrix":[41],"Multiplication":[42],"fundamental":[45],"most":[48],"computing":[50],"kernel":[51],"routine":[52],"extensively":[53],"utilized":[54],"workloads.":[58],"Generally,":[59],"whole":[61],"GEMM":[62,140,148],"workload":[63],"partitioned":[65],"into":[66],"series":[68],"of":[69,123],"blocks":[70],"sub-tasks":[73,141],"are":[74,150],"professionally":[75],"assembled":[76],"exploit":[78],"parallel":[80,107],"hardware.":[81],"However,":[82],"it":[83],"not":[85],"case":[87],"for":[88,100,138,166,180],"cloud":[90],"which":[92],"process":[93,111],"multi-tasks":[94],"concurrently":[95],"expect":[97],"guaranteed":[98],"QoS":[99],"commercial":[101],"consideration.":[102],"We":[103,128,157],"introduce":[104],"task-aware":[106],"scheduling":[108,133],"method":[109,174],"balance":[116],"response":[118],"delay":[119],"throughput":[122],"ECS":[126,165],"instance.":[127],"furtherly":[129],"design":[130],"multi-thread":[132],"algorithm":[134],"with":[135],"two-level":[136],"division":[137],"achieve":[143,176],"high":[144],"efficiency.":[145],"optimized":[147],"kernels":[149],"attain":[153],"optimal":[155],"performance.":[156],"evaluate":[158],"performance":[160,178],"Alicloud":[164],"different":[167,181],"results":[170],"show":[171],"that":[172],"our":[173],"can":[175],"remarkable":[177],"improvement":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
