{"id":"https://openalex.org/W3090685455","doi":"https://doi.org/10.1145/3410463.3414637","title":"Bandwidth-Aware Loop Tiling for DMA-Supported Scratchpad Memory","display_name":"Bandwidth-Aware Loop Tiling for DMA-Supported Scratchpad Memory","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3090685455","doi":"https://doi.org/10.1145/3410463.3414637","mag":"3090685455"},"language":"en","primary_location":{"id":"doi:10.1145/3410463.3414637","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3410463.3414637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques","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/A5101802949","display_name":"Ming-Chuan Wu","orcid":"https://orcid.org/0000-0002-7537-4803"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingchuan Wu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414281","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0002-6419-1980"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Liu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089123963","display_name":"Huimin Cui","orcid":"https://orcid.org/0009-0006-5884-3985"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimin Cui","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074531718","display_name":"Qingfu Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingfu Wei","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102877451","display_name":"Quanfeng Li","orcid":"https://orcid.org/0000-0001-9083-6204"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quanfeng Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100388546","display_name":"Limin Li","orcid":"https://orcid.org/0000-0003-3572-6832"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limin Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111562182","display_name":"Fang Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Lv","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024664385","display_name":"Jingling Xue","orcid":"https://orcid.org/0000-0003-0380-3506"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jingling Xue","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053070701","display_name":"Xiaobing Feng","orcid":"https://orcid.org/0000-0003-2909-7750"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobing Feng","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101802949"],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.1552,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.77424506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8592126965522766},{"id":"https://openalex.org/keywords/loop-tiling","display_name":"Loop tiling","score":0.6617696285247803},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6486823558807373},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5967799425125122},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5633936524391174},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35874107480049133},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3430463671684265},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20996615290641785},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13169732689857483}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8592126965522766},{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.6617696285247803},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6486823558807373},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5967799425125122},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5633936524391174},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35874107480049133},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3430463671684265},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20996615290641785},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13169732689857483},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3410463.3414637","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3410463.3414637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8999999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1964031104","https://openalex.org/W1983416598","https://openalex.org/W1991592471","https://openalex.org/W2006962349","https://openalex.org/W2034971312","https://openalex.org/W2078504799","https://openalex.org/W2108737583","https://openalex.org/W2475126267","https://openalex.org/W2623645495","https://openalex.org/W2790601347","https://openalex.org/W2791531244","https://openalex.org/W2805585626","https://openalex.org/W2908959276","https://openalex.org/W2954219808","https://openalex.org/W2995257150","https://openalex.org/W3103903655","https://openalex.org/W3187464963","https://openalex.org/W4206223197","https://openalex.org/W4213041029","https://openalex.org/W4239277337","https://openalex.org/W4245643018","https://openalex.org/W4247176905","https://openalex.org/W4248570190","https://openalex.org/W4250089307"],"related_works":["https://openalex.org/W2184722600","https://openalex.org/W1482922405","https://openalex.org/W2039378765","https://openalex.org/W2048382960","https://openalex.org/W1603958403","https://openalex.org/W4232563190","https://openalex.org/W1982351223","https://openalex.org/W1608801611","https://openalex.org/W2134174838","https://openalex.org/W2887282140"],"abstract_inverted_index":{"Scratchpad":[0],"Memory":[1],"(SPM)":[2],"is":[3],"widely":[4],"used":[5],"in":[6],"emerging":[7],"domain-specific":[8],"architectures":[9,21],"and":[10,16,30,55,73,85],"accelerators":[11],"for":[12,24,34],"improving":[13],"energy":[14],"efficiency":[15],"time":[17],"predictability.":[18],"Typically,":[19],"SPM-based":[20],"use":[22,52],"DMA":[23],"fetching":[25],"data":[26,37],"from":[27],"off-chip":[28],"memory":[29],"global":[31],"load":[32],"instructions":[33],"loading":[35],"fine-grained":[36],"directly":[38],"into":[39],"registers.":[40],"For":[41],"such":[42],"architectures,":[43],"neither":[44],"capacity-only":[45],"nor":[46],"bandwidth-only":[47],"loop":[48,62],"tiling":[49,63,83],"can":[50,95],"efficiently":[51],"the":[53,97],"bandwidth":[54,74],"SPM.":[56],"This":[57],"paper":[58],"introduces":[59],"a":[60,67,81,86,105],"bandwidth-aware":[61],"approach":[64,94],"that":[65,92],"enables":[66],"tradeoff":[68],"between":[69],"SPM":[70],"space":[71],"utilization":[72,75],"to":[76,102],"be":[77],"made,":[78],"by":[79],"leveraging":[80],"runtime":[82],"framework":[84],"cross-host-kernel":[87],"IPA.":[88],"Experimental":[89],"results":[90],"demonstrate":[91],"our":[93],"achieve":[96],"performance":[98],"improvement":[99],"of":[100,108],"up":[101],"4x,":[103],"with":[104],"geometric":[106],"average":[107],"26%.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
