{"id":"https://openalex.org/W7133511850","doi":"https://doi.org/10.1109/hpca68181.2026.11408456","title":"SFD: Towards Segment Fusion Dataflow for Spatial Accelerators","display_name":"SFD: Towards Segment Fusion Dataflow for Spatial Accelerators","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7133511850","doi":"https://doi.org/10.1109/hpca68181.2026.11408456"},"language":null,"primary_location":{"id":"doi:10.1109/hpca68181.2026.11408456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca68181.2026.11408456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","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/A5029787563","display_name":"Fang Wang","orcid":"https://orcid.org/0000-0002-3327-4177"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fuyu Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002840650","display_name":"Minghua Shen","orcid":"https://orcid.org/0000-0003-4747-8020"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghua Shen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124057457","display_name":"Yufei Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufei Ding","raw_affiliation_strings":["University of California,San Diego"],"affiliations":[{"raw_affiliation_string":"University of California,San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057221447","display_name":"Nong Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nong Xiao","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074890784","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0002-0421-9566"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5029787563"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54990878,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.32019999623298645,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.32019999623298645,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.08919999748468399,"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"}},{"id":"https://openalex.org/T12490","display_name":"Software Engineering and Design Patterns","score":0.03460000082850456,"subfield":{"id":"https://openalex.org/subfields/3303","display_name":"Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.6414999961853027},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4284000098705292},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.29910001158714294},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2793000042438507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6432999968528748},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.6414999961853027},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3522999882698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33469998836517334},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3140000104904175},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2955000102519989},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca68181.2026.11408456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca68181.2026.11408456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6651040689","display_name":null,"funder_award_id":"62332021","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":39,"referenced_works":["https://openalex.org/W2067523571","https://openalex.org/W2194775991","https://openalex.org/W2466675884","https://openalex.org/W2906043559","https://openalex.org/W2912012512","https://openalex.org/W2940862705","https://openalex.org/W2945146780","https://openalex.org/W2949967139","https://openalex.org/W2963163009","https://openalex.org/W2963446712","https://openalex.org/W2980104813","https://openalex.org/W2998732502","https://openalex.org/W3012249773","https://openalex.org/W3036079062","https://openalex.org/W3036878841","https://openalex.org/W3102790199","https://openalex.org/W3130554079","https://openalex.org/W3135807226","https://openalex.org/W3174529902","https://openalex.org/W3177452048","https://openalex.org/W3189877953","https://openalex.org/W3190092209","https://openalex.org/W3192336523","https://openalex.org/W3193212547","https://openalex.org/W3206453033","https://openalex.org/W4213249026","https://openalex.org/W4249932213","https://openalex.org/W4280489237","https://openalex.org/W4281932226","https://openalex.org/W4308083846","https://openalex.org/W4318541538","https://openalex.org/W4318541578","https://openalex.org/W4360831828","https://openalex.org/W4380881063","https://openalex.org/W4389491877","https://openalex.org/W4389491911","https://openalex.org/W4394871723","https://openalex.org/W4401211619","https://openalex.org/W4401211784"],"related_works":[],"abstract_inverted_index":{"Spatial":[0],"accelerators":[1,216],"are":[2,40],"promising":[3],"to":[4,20,88,105,146,163,191,208],"satiate":[5],"the":[6,21,80,109],"growing":[7],"demands":[8],"for":[9,188,214],"performance":[10],"and":[11,28,39,69,86,119,142,167],"energy":[12],"efficiency":[13],"in":[14,49],"deep":[15],"neural":[16],"networks":[17],"(DNNs).":[18],"Due":[19],"speed":[22],"gap":[23],"between":[24],"onchip":[25],"compute":[26],"cores":[27],"off-chip":[29],"memory":[30,169],"bandwidth,":[31],"common":[32],"DNNs":[33,200],"suffer":[34,55],"from":[35,56],"poor":[36],"operational":[37],"intensity":[38],"increasingly":[41],"memory-bound.":[42],"While":[43],"operator":[44,115],"fusion":[45,64,98,116,219],"has":[46],"shown":[47],"potential":[48,81],"alleviating":[50],"this":[51,92,106,129],"bottleneck,":[52],"existing":[53],"approaches":[54],"two":[57],"key":[58],"limitations.":[59],"They":[60],"rely":[61],"on":[62,128],"predefined":[63],"templates":[65],"before":[66],"tensor":[67,165],"mapping":[68,118,161],"impose":[70],"tile":[71,121,125,181],"constraints":[72],"during":[73],"mapping.":[74],"As":[75],"a":[76,96,134,139,179,185],"result,":[77],"they":[78],"overlook":[79],"of":[82],"fusing":[83,171],"more":[84],"operators":[85,172],"lead":[87],"sub-optimal":[89],"performance.":[90],"In":[91],"paper,":[93],"we":[94,131,153,177],"propose":[95,154],"segment":[97,190],"dataflow":[99,110],"optimization":[100],"framework":[101,107],"called":[102],"SFD.":[103],"Central":[104],"is":[108],"abstraction":[111],"that":[112],"enables":[113],"template-free":[114],"after":[117],"supports":[120],"constraint":[122],"relaxation":[123],"through":[124],"scheduling.":[126],"Based":[127],"abstraction,":[130],"first":[132],"introduce":[133,178],"memory-centric":[135],"mapper,":[136],"which":[137,159,183],"defines":[138],"design":[140,148],"space":[141,149],"incorporates":[143],"an":[144,155],"algorithm":[145],"facilitate":[147],"exploration":[150],"(DSE).":[151],"Then":[152],"analytical":[156],"network":[157],"segmenter,":[158],"leverages":[160],"results":[162],"analyze":[164],"lifetimes":[166],"on-chip":[168],"usage,":[170],"into":[173],"variable-length":[174],"segments.":[175],"Finally,":[176],"dependency-aware":[180],"scheduler,":[182],"develops":[184],"priority":[186],"queue":[187],"each":[189],"ensure":[192],"correct":[193],"execution":[194],"order.":[195],"Extensive":[196],"experiments":[197],"with":[198],"different":[199],"demonstrate":[201],"SFD":[202],"achieves":[203],"<tex":[204,209],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[205,210],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$1.4":[206],"\\times$</tex>":[207,212],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$2.2":[211],"speedup":[213],"spatial":[215],"over":[217],"state-of-the-art":[218],"frameworks.":[220]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-03-05T00:00:00"}