{"id":"https://openalex.org/W4404132821","doi":"https://doi.org/10.1145/3649329.3655683","title":"GSPO: A Graph Substitution and Parallelization Joint Optimization Framework for DNN Inference","display_name":"GSPO: A Graph Substitution and Parallelization Joint Optimization Framework for DNN Inference","publication_year":2024,"publication_date":"2024-06-23","ids":{"openalex":"https://openalex.org/W4404132821","doi":"https://doi.org/10.1145/3649329.3655683"},"language":"en","primary_location":{"id":"doi:10.1145/3649329.3655683","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3655683","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3649329.3655683","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113937118","display_name":"Zheng Xu","orcid":"https://orcid.org/0009-0009-5264-2818"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Xu","raw_affiliation_strings":["School of Integrated Circuits, Tsinghua University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-5264-2818","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101530760","display_name":"Xu Dai","orcid":"https://orcid.org/0009-0009-4702-0635"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Dai","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-4702-0635","affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036023084","display_name":"Shaojun Wei","orcid":"https://orcid.org/0000-0001-5117-7920"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun Wei","raw_affiliation_strings":["School of Integrated Circuits, BNRist, Tsinghua University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5117-7920","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, BNRist, Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054524841","display_name":"Shouyi Yin","orcid":"https://orcid.org/0000-0003-2309-572X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouyi Yin","raw_affiliation_strings":["School of Integrated Circuits, BNRist, Tsinghua University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2309-572X","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, BNRist, Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066434078","display_name":"Yang Hu","orcid":"https://orcid.org/0000-0001-6942-4395"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Hu","raw_affiliation_strings":["School of Integrated Circuits, Tsinghua University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6942-4395","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7950196266174316},{"id":"https://openalex.org/keywords/substitution","display_name":"Substitution (logic)","score":0.7137042880058289},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6866957545280457},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5051408410072327},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4760458469390869},{"id":"https://openalex.org/keywords/factor-graph","display_name":"Factor graph","score":0.4589565396308899},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4588435888290405},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4343544542789459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30327337980270386},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2659702003002167},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21178513765335083},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.0601157546043396},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05990716814994812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950196266174316},{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.7137042880058289},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6866957545280457},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5051408410072327},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4760458469390869},{"id":"https://openalex.org/C159246509","wikidata":"https://www.wikidata.org/wiki/Q5428725","display_name":"Factor graph","level":3,"score":0.4589565396308899},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4588435888290405},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4343544542789459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30327337980270386},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2659702003002167},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21178513765335083},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.0601157546043396},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05990716814994812},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649329.3655683","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3655683","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3649329.3655683","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3655683","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2113137767","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2964081807","https://openalex.org/W2981758446","https://openalex.org/W3084654275","https://openalex.org/W4382202854"],"related_works":["https://openalex.org/W2379444625","https://openalex.org/W2393147081","https://openalex.org/W2575869988","https://openalex.org/W4308647020","https://openalex.org/W2370088286","https://openalex.org/W2385568494","https://openalex.org/W2912058948","https://openalex.org/W2588424405","https://openalex.org/W144183602","https://openalex.org/W2767022047"],"abstract_inverted_index":{"This":[0],"work":[1],"proposes":[2],"GSPO,":[3],"an":[4,72],"automatic":[5],"unified":[6],"framework":[7],"that":[8],"jointly":[9],"applies":[10],"graph":[11,24,28,51,57,81],"substitution":[12,29,82],"and":[13,30,59,94],"parallelization":[14,31],"for":[15,42],"DNN":[16],"inference.":[17],"GSPO":[18,63,85],"uses":[19],"a":[20,37],"joint":[21,43,68],"optimization":[22,44,69],"computation":[23,50],"(JOCG)":[25],"to":[26,47,77,89,100],"represent":[27],"at":[32],"the":[33,49,56,66],"operator":[34],"level.":[35],"Then,":[36],"novel":[38],"cost":[39],"model":[40],"customized":[41],"is":[45],"used":[46],"evaluate":[48],"execution":[52],"time":[53,97],"quickly.":[54],"With":[55],"partition":[58],"backtracking":[60],"search":[61,74,96],"algorithm,":[62],"can":[64,86],"find":[65],"optimal":[67],"solution":[70],"within":[71],"acceptable":[73],"time.":[75],"Compared":[76],"existing":[78],"frameworks":[79],"applying":[80],"or":[83],"parallelization,":[84],"achieve":[87],"up":[88,99],"27.1%":[90],"end-to-end":[91],"performance":[92],"improvement":[93],"reduce":[95],"by":[98],"94.3%.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}