{"id":"https://openalex.org/W4389476360","doi":"https://doi.org/10.1145/3613424.3623782","title":"Snake: A Variable-length Chain-based Prefetching for GPUs","display_name":"Snake: A Variable-length Chain-based Prefetching for GPUs","publication_year":2023,"publication_date":"2023-10-28","ids":{"openalex":"https://openalex.org/W4389476360","doi":"https://doi.org/10.1145/3613424.3623782"},"language":"en","primary_location":{"id":"doi:10.1145/3613424.3623782","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3623782","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623782","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623782","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093446961","display_name":"Saba Mostofi","orcid":"https://orcid.org/0009-0000-3485-0036"},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Saba Mostofi","raw_affiliation_strings":["Department of Computer Engineering, Sharif University of Technology, Iran"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Sharif University of Technology, Iran","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019048190","display_name":"Hajar Falahati","orcid":"https://orcid.org/0000-0001-8375-3339"},"institutions":[{"id":"https://openalex.org/I4210146419","display_name":"Institute for Research in Fundamental Sciences","ror":"https://ror.org/04xreqs31","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210146419"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Hajar Falahati","raw_affiliation_strings":["School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Iran"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Iran","institution_ids":["https://openalex.org/I4210146419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053374807","display_name":"Negin Mahani","orcid":"https://orcid.org/0000-0001-5232-3539"},"institutions":[{"id":"https://openalex.org/I4210146419","display_name":"Institute for Research in Fundamental Sciences","ror":"https://ror.org/04xreqs31","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210146419"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Negin Mahani","raw_affiliation_strings":["Department of Computer Engineering, Shahid Bahonar University, Iran and School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Iran"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Shahid Bahonar University, Iran and School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Iran","institution_ids":["https://openalex.org/I4210146419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032350195","display_name":"Pejman Lotfi-Kamran","orcid":"https://orcid.org/0000-0003-3293-8274"},"institutions":[{"id":"https://openalex.org/I4210146419","display_name":"Institute for Research in Fundamental Sciences","ror":"https://ror.org/04xreqs31","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210146419"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Pejman Lotfi-Kamran","raw_affiliation_strings":["School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Iran"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Iran","institution_ids":["https://openalex.org/I4210146419"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040238844","display_name":"Hamid Sarbazi\u2010Azad","orcid":"https://orcid.org/0000-0003-4079-8603"},"institutions":[{"id":"https://openalex.org/I4210146419","display_name":"Institute for Research in Fundamental Sciences","ror":"https://ror.org/04xreqs31","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210146419"]},{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Hamid Sarbazi-Azad","raw_affiliation_strings":["Department of Computer Engineering, Sharif University of Technology, Iran and School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Iran"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Sharif University of Technology, Iran and School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Iran","institution_ids":["https://openalex.org/I4210146419","https://openalex.org/I133529467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5093446961"],"corresponding_institution_ids":["https://openalex.org/I133529467"],"apc_list":null,"apc_paid":null,"fwci":2.1634,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87594221,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"728","last_page":"741"},"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":0.9993000030517578,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.8610588312149048},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7843567728996277},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5301721096038818},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.5254180431365967},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5217117667198181},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.49615678191185},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.4809638559818268},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4645148813724518},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4591197073459625},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4477151930332184},{"id":"https://openalex.org/keywords/non-uniform-memory-access","display_name":"Non-uniform memory access","score":0.44671934843063354},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.437588095664978},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.42604148387908936},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.3680769205093384},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.29735836386680603},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2567773759365082},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.22585904598236084},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.21317607164382935},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.14959770441055298},{"id":"https://openalex.org/keywords/memory-controller","display_name":"Memory controller","score":0.12433609366416931}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8610588312149048},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7843567728996277},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5301721096038818},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.5254180431365967},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5217117667198181},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.49615678191185},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.4809638559818268},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4645148813724518},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4591197073459625},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4477151930332184},{"id":"https://openalex.org/C133371097","wikidata":"https://www.wikidata.org/wiki/Q868014","display_name":"Non-uniform memory access","level":5,"score":0.44671934843063354},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.437588095664978},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.42604148387908936},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3680769205093384},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.29735836386680603},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2567773759365082},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.22585904598236084},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.21317607164382935},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.14959770441055298},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.12433609366416931},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3613424.3623782","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3623782","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623782","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3613424.3623782","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3623782","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623782","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389476360.pdf","grobid_xml":"https://content.openalex.org/works/W4389476360.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1972971542","https://openalex.org/W1979527452","https://openalex.org/W1980136882","https://openalex.org/W1982439128","https://openalex.org/W1983235612","https://openalex.org/W2009946006","https://openalex.org/W2054604177","https://openalex.org/W2072837011","https://openalex.org/W2128462109","https://openalex.org/W2150073849","https://openalex.org/W2166918318","https://openalex.org/W2234679013","https://openalex.org/W2273440736","https://openalex.org/W2315868086","https://openalex.org/W2409197925","https://openalex.org/W2511318867","https://openalex.org/W2518607193","https://openalex.org/W2536535850","https://openalex.org/W2626312854","https://openalex.org/W2764065518","https://openalex.org/W2795232275","https://openalex.org/W2795326697","https://openalex.org/W2886858179","https://openalex.org/W2895553128","https://openalex.org/W2903738101","https://openalex.org/W2917720315","https://openalex.org/W2930718998","https://openalex.org/W2949486320","https://openalex.org/W2950969115","https://openalex.org/W3043167609","https://openalex.org/W3102510044","https://openalex.org/W3117273852","https://openalex.org/W3120481279","https://openalex.org/W3181975841","https://openalex.org/W4213435190","https://openalex.org/W4221109973","https://openalex.org/W4231299715","https://openalex.org/W4231970275","https://openalex.org/W4241590855","https://openalex.org/W4241687679","https://openalex.org/W4308968707"],"related_works":["https://openalex.org/W4311294724","https://openalex.org/W4255537604","https://openalex.org/W2586378910","https://openalex.org/W1998129367","https://openalex.org/W2606565524","https://openalex.org/W2148966412","https://openalex.org/W2807409404","https://openalex.org/W1655459528","https://openalex.org/W1531802798","https://openalex.org/W2018761720"],"abstract_inverted_index":{"Graphics":[0,133],"Processing":[1,134],"Units":[2],"(GPUs)":[3],"utilize":[4],"memory":[5,14,32,38,55,103,116],"hierarchy":[6],"and":[7,40,58,102,110,127],"Thread-Level":[8],"Parallelism":[9],"(TLP)":[10],"to":[11,45,53],"tolerate":[12],"off-chip":[13],"latency,":[15,57],"which":[16,34,92],"is":[17,49,93],"a":[18,28,87,120],"significant":[19],"bottleneck":[20],"for":[21,130],"memory-bound":[22,131],"applications.":[23,137],"However,":[24,71],"parallel":[25],"threads":[26],"generate":[27],"large":[29],"number":[30],"of":[31,65,97],"requests,":[33,117],"increases":[35],"the":[36,62],"average":[37],"latency":[39],"degrades":[41],"cache":[42],"performance":[43,126],"due":[44],"high":[46],"contention.":[47],"Prefetching":[48],"an":[50],"effective":[51],"technique":[52],"reduce":[54],"access":[56],"prior":[59],"research":[60],"shows":[61],"positive":[63],"impact":[64],"stride-based":[66],"prefetching":[67,73,89,114],"on":[68,77],"GPU":[69,125],"performance.":[70],"existing":[72],"methods":[74],"only":[75],"rely":[76],"fixed":[78],"strides.":[79],"To":[80],"address":[81],"this":[82,84],"limitation,":[83],"paper":[85],"proposes":[86],"new":[88],"technique,":[90],"Snake,":[91],"built":[94],"upon":[95],"chains":[96],"variable":[98],"strides,":[99],"using":[100],"throttling":[101],"decoupling":[104],"strategies.":[105],"Snake":[106],"achieves":[107],"80%":[108],"coverage":[109],"75%":[111],"accuracy":[112],"in":[113,119,123],"demand":[115],"resulting":[118],"17%":[121],"improvement":[122],"total":[124],"energy":[128],"consumption":[129],"General-Purpose":[132],"Unit":[135],"(GPGPU)":[136]},"counts_by_year":[{"year":2025,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
