{"id":"https://openalex.org/W2144004530","doi":"https://doi.org/10.1109/asap.2014.6868656","title":"An approach of processor core customization for stencil computation","display_name":"An approach of processor core customization for stencil computation","publication_year":2014,"publication_date":"2014-06-01","ids":{"openalex":"https://openalex.org/W2144004530","doi":"https://doi.org/10.1109/asap.2014.6868656","mag":"2144004530"},"language":"en","primary_location":{"id":"doi:10.1109/asap.2014.6868656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2014.6868656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 25th International Conference on Application-Specific Systems, Architectures and Processors","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100630059","display_name":"Yanhua Li","orcid":"https://orcid.org/0000-0001-8972-503X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhua Li","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016596981","display_name":"Youhui Zhang","orcid":"https://orcid.org/0000-0003-2333-3580"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youhui Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104806125","display_name":"Jianfeng Yang","orcid":"https://orcid.org/0000-0002-9526-2438"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Yang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057940557","display_name":"Wayne Luk","orcid":"https://orcid.org/0000-0002-6750-927X"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wayne Luk","raw_affiliation_strings":["Department of Computing, Imperial College, London, UK","Dept. of Comput., Imperial Coll. London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Dept. of Comput., Imperial Coll. London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678397","display_name":"Guangwen Yang","orcid":"https://orcid.org/0000-0002-8673-8254"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwen Yang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108050911","display_name":"Weimin Zheng","orcid":"https://orcid.org/0000-0002-4450-5428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Zheng","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"182","last_page":"183"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9991999864578247,"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":0.9958999752998352,"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/computer-science","display_name":"Computer science","score":0.8481618165969849},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.681135892868042},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.6745564937591553},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6617905497550964},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.6004320383071899},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5561794638633728},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5472148060798645},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5093613862991333},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.48567995429039},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4737825393676758},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4353763163089752},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.41745561361312866},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.41601309180259705},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.41405826807022095},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.39711594581604004},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.25786709785461426},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.1380508542060852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8481618165969849},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.681135892868042},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.6745564937591553},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6617905497550964},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.6004320383071899},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5561794638633728},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5472148060798645},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5093613862991333},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.48567995429039},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4737825393676758},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4353763163089752},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.41745561361312866},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.41601309180259705},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41405826807022095},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.39711594581604004},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25786709785461426},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.1380508542060852},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asap.2014.6868656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2014.6868656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 25th International Conference on Application-Specific Systems, Architectures and Processors","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1987873989","https://openalex.org/W2063970596","https://openalex.org/W2071930640","https://openalex.org/W2096672917","https://openalex.org/W3151489216","https://openalex.org/W3152199537"],"related_works":["https://openalex.org/W2129537883","https://openalex.org/W1559264847","https://openalex.org/W2911551207","https://openalex.org/W4225987401","https://openalex.org/W2057234250","https://openalex.org/W4236526691","https://openalex.org/W4226140811","https://openalex.org/W2003690377","https://openalex.org/W88028992","https://openalex.org/W1992352827"],"abstract_inverted_index":{"Architecture":[0],"customization":[1],"is":[2],"believed":[3],"as":[4,56,73,75,85],"one":[5],"of":[6,91,97],"the":[7,39,44,76,86,95],"most":[8],"promising":[9],"methods":[10],"to":[11,25,36,38,93,111,125],"meet":[12],"ever-increasing":[13],"computing":[14,127],"needs":[15],"and":[16,68,106,114],"power":[17,107],"density":[18],"limitations.":[19],"This":[20],"paper":[21],"presents":[22],"an":[23],"approach":[24],"enhance":[26],"a":[27],"preliminary":[28],"customizable":[29],"core":[30],"with":[31],"some":[32],"common":[33],"architecture":[34],"features,":[35],"adapt":[37],"specific":[40],"applications":[41],"while":[42],"keeping":[43],"programming":[45],"flexibility.":[46],"Those":[47],"features":[48],"include":[49],"several":[50],"effective":[51],"software/hardware":[52],"co-optimizing":[53],"strategies,":[54],"such":[55],"loop":[57],"tiling,":[58],"pre-fetching,":[59],"cache":[60],"customization,":[61],"customized":[62],"Single":[63],"Instruction":[64],"Multiple":[65],"Data":[66],"(SIMD)":[67],"Direct":[69],"Memory":[70],"Access":[71],"(DMA),":[72],"well":[74],"necessary":[77],"ISA":[78],"extensions.":[79],"Currently":[80],"we":[81],"select":[82],"stencil":[83],"computation":[84],"research":[87],"target.":[88],"Detailed":[89],"tests":[90],"power-efficiency":[92],"evaluate":[94],"effect":[96],"all":[98],"these":[99,118],"optimizations":[100],"comprehensively":[101],"shows":[102],"impressive":[103],"performance":[104],"speedup":[105],"efficiency,":[108],"even":[109],"compared":[110],"X86,":[112],"GPU":[113],"FPGA":[115],"platforms.":[116],"All":[117],"proposed":[119],"customizations":[120],"here":[121],"could":[122],"be":[123],"applied":[124],"other":[126],"applications.":[128]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
