{"id":"https://openalex.org/W7143406229","doi":"https://doi.org/10.1109/lca.2026.3678312","title":"FlowFlash: An Efficient Dataflow Strategy for FlashAttention Execution on Systolic Arrays","display_name":"FlowFlash: An Efficient Dataflow Strategy for FlashAttention Execution on Systolic Arrays","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7143406229","doi":"https://doi.org/10.1109/lca.2026.3678312"},"language":null,"primary_location":{"id":"doi:10.1109/lca.2026.3678312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2026.3678312","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-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/A5059525054","display_name":"Baosen Wang","orcid":"https://orcid.org/0009-0009-4424-4019"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210124847","display_name":"National Engineering Research Center of Electromagnetic Radiation Control Materials","ror":"https://ror.org/02k4dcs46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210124847"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baosen Wang","raw_affiliation_strings":["State Key Laboratory of Thin Solid Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0009-4424-4019","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Thin Solid Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I4210124847","https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junjie Wang","orcid":"https://orcid.org/0000-0001-7183-422X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210124847","display_name":"National Engineering Research Center of Electromagnetic Radiation Control Materials","ror":"https://ror.org/02k4dcs46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210124847"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Wang","raw_affiliation_strings":["State Key Laboratory of Thin Solid Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-7183-422X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Thin Solid Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I4210124847","https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130948015","display_name":"Siyu Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210124847","display_name":"National Engineering Research Center of Electromagnetic Radiation Control Materials","ror":"https://ror.org/02k4dcs46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210124847"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Xiao","raw_affiliation_strings":["State Key Laboratory of Thin Solid Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0006-3095-3242","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Thin Solid Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I4210124847","https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130964730","display_name":"Y. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210124847","display_name":"National Engineering Research Center of Electromagnetic Radiation Control Materials","ror":"https://ror.org/02k4dcs46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210124847"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Y. Liu","raw_affiliation_strings":["State Key Laboratory of Thin Solid Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-0615-7036","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Thin Solid Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I4210124847","https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46517224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"1","first_page":"138","last_page":"141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.40059998631477356,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.40059998631477356,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.2540000081062317,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.054499998688697815,"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/dataflow","display_name":"Dataflow","score":0.7347000241279602},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.3273000121116638},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.32190001010894775},{"id":"https://openalex.org/keywords/parallel-processing","display_name":"Parallel processing","score":0.3183000087738037},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.2754000127315521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878999710083008},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.7347000241279602},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.489300012588501},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3305000066757202},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.3273000121116638},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32679998874664307},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2842000126838684},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.2754000127315521},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.265500009059906}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2026.3678312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2026.3678312","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44712933897972107,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1368944445","display_name":null,"funder_award_id":"62404034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7142779107","display_name":null,"funder_award_id":"62404033","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"To":[0],"tackle":[1],"the":[2],"severe":[3],"underutilization":[4],"of":[5],"systolic":[6,48],"arrays":[7],"in":[8],"FlashAttention,":[9],"we":[10],"propose":[11],"FlowFlash,":[12],"a":[13,28,43],"dataflow":[14],"strategy":[15],"employing":[16],"Inter-Block":[17],"Overlap":[18],"and":[19,55],"Unroll":[20],"techniques.":[21],"By":[22],"fusing":[23],"three":[24],"consecutive":[25],"blocks":[26],"into":[27],"single":[29],"hardware":[30],"loop":[31],"to":[32],"eliminate":[33],"pipeline":[34],"stalls,":[35],"FlowFlash":[36],"achieves":[37],"85.8%":[38],"FLOPs/s":[39],"utilization.":[40],"This":[41],"represents":[42],"2.10\u00d7-10.14\u00d7":[44],"improvement":[45],"over":[46],"state-of-the-art":[47],"array-based":[49],"accelerators,":[50],"while":[51],"maintaining":[52],"high":[53],"area":[54],"power":[56],"efficiency.":[57]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-31T00:00:00"}
