{"id":"https://openalex.org/W4312901420","doi":"https://doi.org/10.1109/tc.2022.3214088","title":"ISPA: Exploiting Intra-SM Parallelism in GPUs via Fine-Grained Resource Management","display_name":"ISPA: Exploiting Intra-SM Parallelism in GPUs via Fine-Grained Resource Management","publication_year":2022,"publication_date":"2022-10-12","ids":{"openalex":"https://openalex.org/W4312901420","doi":"https://doi.org/10.1109/tc.2022.3214088"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2022.3214088","doi":"https://doi.org/10.1109/tc.2022.3214088","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tc.2022.3214088","pdf_url":"https://ieeexplore.ieee.org/ielx7/12/4358213/09917312.pdf","source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","jufo-3","norway-2","poland-140","russia-white-list-2"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/12/4358213/09917312.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063596525","display_name":"Han Zhao","orcid":"https://orcid.org/0000-0002-1561-5329","observed_orcids":["https://orcid.org/0000-0002-1561-5329"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008837660","display_name":"Weihao Cui","orcid":"https://orcid.org/0000-0002-6646-5260","observed_orcids":["https://orcid.org/0000-0002-6646-5260"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihao Cui","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6646-5260","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377840","display_name":"Quan Chen","orcid":"https://orcid.org/0000-0001-5832-0347","observed_orcids":["https://orcid.org/0000-0001-5832-0347"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5832-0347","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302","observed_orcids":["https://orcid.org/0000-0003-0034-2302"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0034-2302","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":{"value":2195,"currency":"USD","value_usd":2195},"fwci":1.21,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.7429887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"72","issue":"5","first_page":"1473","last_page":"1487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0003000000142492354,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/gpu-resource-management","display_name":"GPU resource management","score":0.6959999799728394},{"id":"https://openalex.org/keywords/tensor-cores","display_name":"tensor cores","score":0.9129999876022339},{"id":"https://openalex.org/keywords/shared-memory-contention","display_name":"shared memory contention","score":0.9950000047683716},{"id":"https://openalex.org/keywords/register-allocation","display_name":"register allocation","score":0.9649999737739563},{"id":"https://openalex.org/keywords/cudnn","display_name":"cuDNN","score":0.6000000238418579},{"id":"https://openalex.org/keywords/gpu-utilization","display_name":"GPU utilization","score":0.5879999995231628},{"id":"https://openalex.org/keywords/throughput-improvement","display_name":"throughput improvement","score":0.3370000123977661}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7676277756690979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.764533281326294},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7563422322273254},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5539761185646057},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4465239346027374},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.42879462242126465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13961473107337952},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.10330748558044434},{"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:10.1109/tc.2022.3214088","doi":"https://doi.org/10.1109/tc.2022.3214088","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tc.2022.3214088","pdf_url":"https://ieeexplore.ieee.org/ielx7/12/4358213/09917312.pdf","source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","jufo-3","norway-2","poland-140","russia-white-list-2"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tc.2022.3214088","doi":"https://doi.org/10.1109/tc.2022.3214088","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tc.2022.3214088","pdf_url":"https://ieeexplore.ieee.org/ielx7/12/4358213/09917312.pdf","source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","jufo-3","norway-2","poland-140","russia-white-list-2"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2465329715","display_name":null,"funder_award_id":"61832006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5564014484","display_name":"\u57fa\u4e8e\u533a\u5757\u94fe\u7684\u5206\u5e03\u5f0f\u8d44\u6e90\u7ba1\u7406\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61872240","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7942366687","display_name":null,"funder_award_id":"62022057","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8848817600","display_name":null,"funder_award_id":"62022057, 61832006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312901420.pdf","grobid_xml":"https://content.openalex.org/works/W4312901420.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W115476871","https://openalex.org/W1530262073","https://openalex.org/W1667652561","https://openalex.org/W1965327223","https://openalex.org/W1968391520","https://openalex.org/W2023214828","https://openalex.org/W2038666141","https://openalex.org/W2064026483","https://openalex.org/W2072652898","https://openalex.org/W2080592089","https://openalex.org/W2085434892","https://openalex.org/W2098274770","https://openalex.org/W2130336316","https://openalex.org/W2134427337","https://openalex.org/W2155893237","https://openalex.org/W2156077332","https://openalex.org/W2194775991","https://openalex.org/W2273440736","https://openalex.org/W2323693848","https://openalex.org/W2605178034","https://openalex.org/W2811206245","https://openalex.org/W2891285910","https://openalex.org/W2919115771","https://openalex.org/W2952562115","https://openalex.org/W3005664618","https://openalex.org/W3011377185","https://openalex.org/W3017091196","https://openalex.org/W3017148238","https://openalex.org/W3043571714","https://openalex.org/W3116103263","https://openalex.org/W3131071874","https://openalex.org/W3137551601","https://openalex.org/W4231332361","https://openalex.org/W4245867598"],"related_works":["https://openalex.org/W4200091031","https://openalex.org/W2794729807","https://openalex.org/W4402890055","https://openalex.org/W7043289252","https://openalex.org/W2900482429","https://openalex.org/W7133512870","https://openalex.org/W4312309118","https://openalex.org/W2765749513","https://openalex.org/W2605178034","https://openalex.org/W4243035950"],"abstract_inverted_index":{"Emerging":[0],"GPUs":[1],"have":[2,61],"multiple":[3],"Streaming":[4],"Multiprocessors":[5],"(SM),":[6],"while":[7],"each":[8],"SM":[9],"is":[10],"comprised":[11],"of":[12],"CUDA":[13,19,45,76],"Cores":[14,20,26,46],"and":[15,84,92,141],"Tensor":[16,25,48],"Cores.":[17],"While":[18],"do":[21],"the":[22,51,74,89,102,108,133],"general":[23],"computation,":[24],"are":[27,115],"designed":[28],"to":[29,64,67,87,106],"speed":[30],"up":[31],"matrix":[32],"multiplication":[33],"for":[34,117,138],"deep":[35],"learning":[36],"applications.":[37],"However,":[38],"a":[39],"GPU":[40,69,128],"kernel":[41],"often":[42],"either":[43],"uses":[44],"or":[47],"Cores,":[49],"leaving":[50],"other":[52],"processing":[53],"units":[54],"idle.":[55],"Although":[56],"many":[57],"prior":[58,147],"research":[59],"works":[60],"been":[62],"proposed":[63],"co-locate":[65],"kernels":[66,120],"improve":[68],"utilization,":[70],"they":[71],"cannot":[72],"leverage":[73],"Intra-SM":[75],"Core-Tensor":[77],"Core":[78],"Parallelism.":[79],"Specifically,":[80],"ISPA":[81,99,131],"designs":[82],"persistent":[83],"elastic":[85],"block":[86],"solve":[88],"thread":[90],"slot":[91],"shared":[93],"memory":[94],"contention":[95],"between":[96],"co-located":[97],"kernels.":[98],"also":[100],"adopts":[101],"register":[103,109],"allocation":[104],"method":[105],"manage":[107],"contention.":[110],"These":[111],"resource":[112],"management":[113],"methods":[114],"applicable":[116],"both":[118],"white-box":[119,139],"and$cudnn$kernels.":[121],"Experimental":[122],"results":[123],"on":[124],"an":[125],"Nvidia":[126],"2080Ti":[127],"show":[129],"that":[130],"improves":[132],"system-wide":[134],"throughput":[135],"by":[136],"15.3%":[137],"workloads,":[140],"7.1%":[142],"for$cudnn$-based":[143],"workloads":[144],"compared":[145],"with":[146],"co-location":[148],"work.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-01-05T00:00:00"}