{"id":"https://openalex.org/W4318618048","doi":"https://doi.org/10.1145/3572547","title":"SASA: A Scalable and Automatic Stencil Acceleration Framework for Optimized Hybrid Spatial and Temporal Parallelism on HBM-based FPGAs","display_name":"SASA: A Scalable and Automatic Stencil Acceleration Framework for Optimized Hybrid Spatial and Temporal Parallelism on HBM-based FPGAs","publication_year":2023,"publication_date":"2023-01-31","ids":{"openalex":"https://openalex.org/W4318618048","doi":"https://doi.org/10.1145/3572547"},"language":"en","primary_location":{"id":"doi:10.1145/3572547","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572547","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","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/A5047352513","display_name":"Xingyu Tian","orcid":"https://orcid.org/0000-0001-6244-2101"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Xingyu Tian","raw_affiliation_strings":["School of Engineering Science, Simon Fraser Universityr, Burnaby, BC, Canada"],"raw_orcid":"https://orcid.org/0000-0001-6244-2101","affiliations":[{"raw_affiliation_string":"School of Engineering Science, Simon Fraser Universityr, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020142088","display_name":"Zhifan Ye","orcid":"https://orcid.org/0000-0003-0755-8843"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifan Ye","raw_affiliation_strings":["School of the Gifted Young, University of Science and Technology of China, Jinzhai Road, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-0755-8843","affiliations":[{"raw_affiliation_string":"School of the Gifted Young, University of Science and Technology of China, Jinzhai Road, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067662998","display_name":"Alec Lu","orcid":"https://orcid.org/0000-0002-3315-7368"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alec Lu","raw_affiliation_strings":["School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada,"],"raw_orcid":"https://orcid.org/0000-0002-3315-7368","affiliations":[{"raw_affiliation_string":"School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada,","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032647120","display_name":"Licheng Guo","orcid":"https://orcid.org/0000-0002-0705-9510"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Licheng Guo","raw_affiliation_strings":["Computer Science Department, University of California, Los Angeles, Westwood Plaza, Los Angeles, California, United States"],"raw_orcid":"https://orcid.org/0000-0002-0705-9510","affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, Westwood Plaza, Los Angeles, California, United States","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074835029","display_name":"Yuze Chi","orcid":"https://orcid.org/0000-0002-5885-0425"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuze Chi","raw_affiliation_strings":["Computer Science Department, University of California, Los Angeles, Westwood Plaza, Los Angeles, California, United States"],"raw_orcid":"https://orcid.org/0000-0002-5885-0425","affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, Westwood Plaza, Los Angeles, California, United States","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065889904","display_name":"Zhenman Fang","orcid":"https://orcid.org/0000-0003-0603-9697"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhenman Fang","raw_affiliation_strings":["School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0603-9697","affiliations":[{"raw_affiliation_string":"School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5047352513"],"corresponding_institution_ids":["https://openalex.org/I18014758"],"apc_list":null,"apc_paid":null,"fwci":2.0562,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85333536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"16","issue":"2","first_page":"1","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9986000061035156,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.9245202541351318},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.830079972743988},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.801671028137207},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7726452946662903},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5372808575630188},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4912676215171814},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43287163972854614},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4159410297870636},{"id":"https://openalex.org/keywords/sasa","display_name":"Sasa","score":0.4106295704841614},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.36122965812683105},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.253020703792572},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.16118568181991577}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9245202541351318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.830079972743988},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.801671028137207},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7726452946662903},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5372808575630188},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4912676215171814},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43287163972854614},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4159410297870636},{"id":"https://openalex.org/C2776335000","wikidata":"https://www.wikidata.org/wiki/Q2322484","display_name":"Sasa","level":2,"score":0.4106295704841614},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.36122965812683105},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.253020703792572},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.16118568181991577},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3572547","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572547","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3112144374","display_name":null,"funder_award_id":"RGPIN-2019-04613 and DGECR-2019-00120","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1493774699","https://openalex.org/W2000331453","https://openalex.org/W2000540895","https://openalex.org/W2117998419","https://openalex.org/W2129549365","https://openalex.org/W2154078685","https://openalex.org/W2547057562","https://openalex.org/W2792647449","https://openalex.org/W2891911973","https://openalex.org/W2912779084","https://openalex.org/W2943018941","https://openalex.org/W2996929894","https://openalex.org/W3047624873","https://openalex.org/W3099814709","https://openalex.org/W3130309348","https://openalex.org/W3195130375","https://openalex.org/W4211095909","https://openalex.org/W4229487452","https://openalex.org/W4300845283"],"related_works":["https://openalex.org/W2983282793","https://openalex.org/W1973046741","https://openalex.org/W2177020196","https://openalex.org/W3189307731","https://openalex.org/W1428699136","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1998560227","https://openalex.org/W1429949169","https://openalex.org/W3139770841"],"abstract_inverted_index":{"Stencil":[0],"computation":[1],"is":[2],"one":[3],"of":[4,138,157],"the":[5,73,84,99,104,146],"fundamental":[6],"computing":[7,16],"patterns":[8],"in":[9,108],"many":[10],"application":[11],"domains":[12],"such":[13],"as":[14,80,113,115],"scientific":[15],"and":[17,41,62,77,87,97,140],"image":[18],"processing.":[19],"While":[20],"there":[21,30],"are":[22],"promising":[23],"studies":[24],"that":[25,47,128],"accelerate":[26],"stencils":[27,46],"on":[28,67,92,145],"FPGAs,":[29],"lacks":[31],"an":[32,135],"automated":[33],"acceleration":[34,65,125],"framework":[35,66,126],"to":[36,121,142],"systematically":[37],"explore":[38],"both":[39],"spatial":[40,86],"temporal":[42,88,131],"parallelisms":[43],"for":[44,153],"iterative":[45],"could":[48],"be":[49],"either":[50],"computation-bound":[51],"or":[52],"memory-bound.":[53],"In":[54],"this":[55],"article,":[56],"we":[57],"present":[58],"SASA,":[59],"a":[60,154],"scalable":[61],"automatic":[63,123],"stencil":[64,75,124,158],"modern":[68],"HBM-based":[69,147],"FPGAs.":[70],"SASA":[71,133],"takes":[72],"high-level":[74,110],"DSL":[76],"FPGA":[78,101,151],"platform":[79],"inputs,":[81],"automatically":[82],"exploits":[83,130],"best":[85,105],"parallelism":[89,106],"configuration":[90,107],"based":[91],"our":[93],"accurate":[94],"analytical":[95],"model,":[96],"generates":[98],"optimized":[100],"design":[102],"with":[103],"TAPA":[109],"synthesis":[111],"C++":[112],"well":[114],"its":[116],"corresponding":[117],"host":[118],"code.":[119],"Compared":[120],"state-of-the-art":[122],"SODA":[127],"only":[129],"parallelism,":[132],"achieves":[134],"average":[136],"speedup":[137,144],"3.41\u00d7":[139],"up":[141],"15.73\u00d7":[143],"Xilinx":[148],"Alveo":[149],"U280":[150],"board":[152],"wide":[155],"range":[156],"kernels.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
