{"id":"https://openalex.org/W4416203837","doi":"https://doi.org/10.1145/3712285.3759771","title":"HyTiS: Hybrid Tile Scheduling for GPU GEMM with Enhanced Wave Utilization and Cache Locality","display_name":"HyTiS: Hybrid Tile Scheduling for GPU GEMM with Enhanced Wave Utilization and Cache Locality","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416203837","doi":"https://doi.org/10.1145/3712285.3759771"},"language":null,"primary_location":{"id":"doi:10.1145/3712285.3759771","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712285.3759771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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/A5013177309","display_name":"Zheng Zhang","orcid":"https://orcid.org/0000-0001-6599-9976"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6599-9976","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036278941","display_name":"H. Wang","orcid":"https://orcid.org/0009-0003-8329-0145"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hulin Wang","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0003-8329-0145","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongming Xu","orcid":"https://orcid.org/0009-0009-6255-263X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongming Xu","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0009-6255-263X","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005205340","display_name":"Donglin Yang","orcid":"https://orcid.org/0000-0002-3913-3623"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donglin Yang","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0002-3913-3623","affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101677080","display_name":"Xiaobo Zhou","orcid":"https://orcid.org/0009-0004-9500-3390"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Xiaobo Zhou","raw_affiliation_strings":["University of Macau, Macau, Macao"],"raw_orcid":"https://orcid.org/0009-0004-9500-3390","affiliations":[{"raw_affiliation_string":"University of Macau, Macau, Macao","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063911669","display_name":"Dazhao Cheng","orcid":"https://orcid.org/0000-0003-2869-7623"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dazhao Cheng","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-2869-7623","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5013177309"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":6.4639,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96802057,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1604","last_page":"1618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6736000180244446,"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":0.6736000180244446,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.07940000295639038,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.06390000134706497,"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/cache","display_name":"Cache","score":0.6263999938964844},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6155999898910522},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6108999848365784},{"id":"https://openalex.org/keywords/tile","display_name":"Tile","score":0.5855000019073486},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.41200000047683716},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.39149999618530273},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.3693999946117401}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8503999710083008},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7422000169754028},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6263999938964844},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6155999898910522},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6108999848365784},{"id":"https://openalex.org/C2780728851","wikidata":"https://www.wikidata.org/wiki/Q468402","display_name":"Tile","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.41200000047683716},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34869998693466187},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3343999981880188},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.266400009393692},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712285.3759771","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712285.3759771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3830727860","display_name":null,"funder_award_id":"62341410","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4191718541","display_name":null,"funder_award_id":"0078/2023/AMJ, 001/2024/SKL","funder_id":"https://openalex.org/F4320321655","funder_display_name":"Science and Technology Development Fund"},{"id":"https://openalex.org/G4803673267","display_name":null,"funder_award_id":"2023YFE0205700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321655","display_name":"Science and Technology Development Fund","ror":"https://ror.org/044vr6g03"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1968391520","https://openalex.org/W2025540709","https://openalex.org/W2079038734","https://openalex.org/W2098274770","https://openalex.org/W2194775991","https://openalex.org/W2793599434","https://openalex.org/W2921898934","https://openalex.org/W2954698171","https://openalex.org/W2981758446","https://openalex.org/W3089469538","https://openalex.org/W3093933627","https://openalex.org/W3115898397","https://openalex.org/W3168173119","https://openalex.org/W3174529902","https://openalex.org/W4220818654","https://openalex.org/W4321446237","https://openalex.org/W4324292875","https://openalex.org/W4384705378","https://openalex.org/W4388031349","https://openalex.org/W4389491877","https://openalex.org/W4392265896","https://openalex.org/W4392910976","https://openalex.org/W4394564255","https://openalex.org/W4394841768","https://openalex.org/W4394998528","https://openalex.org/W4394998532","https://openalex.org/W4404133651","https://openalex.org/W4405390006","https://openalex.org/W4405755978","https://openalex.org/W4405756380","https://openalex.org/W4408903522"],"related_works":[],"abstract_inverted_index":{"General":[0],"matrix-matrix":[1],"multiplication":[2],"(GEMM)":[3],"is":[4],"a":[5,21],"fundamental":[6],"operation":[7],"in":[8,36,54],"both":[9],"deep":[10],"learning":[11],"and":[12,39,58],"scientific":[13],"computing.":[14],"To":[15],"accelerate":[16],"these":[17],"workloads,":[18],"GPUs":[19,34],"with":[20],"large":[22],"number":[23],"of":[24],"streaming":[25],"multiprocessors":[26],"(SMs)":[27],"are":[28],"widely":[29],"used.":[30],"However,":[31],"as":[32],"modern":[33],"scale":[35],"core":[37],"count":[38],"adopt":[40],"larger":[41],"tile":[42],"sizes,":[43],"the":[44],"wave":[45],"quantization":[46],"problem":[47,66],"induced":[48],"by":[49],"partially":[50],"filled":[51],"waves":[52],"results":[53],"growing":[55],"hardware":[56],"underutilization":[57],"substantially":[59],"degraded":[60],"performance.":[61],"Existing":[62],"solutions":[63],"to":[64],"this":[65],"often":[67],"suffer":[68],"from":[69],"low":[70],"execution":[71],"efficiency":[72],"or":[73],"introduce":[74],"additional":[75],"synchronization":[76],"overhead.":[77]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-12T00:00:00"}