{"id":"https://openalex.org/W4386763491","doi":"https://doi.org/10.1109/dac56929.2023.10247901","title":"Automatic End-to-End Joint Optimization for Kernel Compilation on DSPs","display_name":"Automatic End-to-End Joint Optimization for Kernel Compilation on DSPs","publication_year":2023,"publication_date":"2023-07-09","ids":{"openalex":"https://openalex.org/W4386763491","doi":"https://doi.org/10.1109/dac56929.2023.10247901"},"language":"en","primary_location":{"id":"doi:10.1109/dac56929.2023.10247901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac56929.2023.10247901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 60th ACM/IEEE Design Automation Conference (DAC)","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/A5101455357","display_name":"Xiaolei Zhao","orcid":"https://orcid.org/0000-0002-5414-1162"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaolei Zhao","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101981758","display_name":"Zhaoyun Chen","orcid":"https://orcid.org/0000-0003-1552-8396"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyun Chen","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101825210","display_name":"Yang Shi","orcid":"https://orcid.org/0000-0001-5786-3171"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Shi","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101937502","display_name":"Mei Wen","orcid":"https://orcid.org/0000-0002-5875-3297"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Wen","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101679256","display_name":"Chunyun Zhang","orcid":"https://orcid.org/0000-0002-3156-754X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyun Zhang","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101455357"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.616,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63096734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9894000291824341,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.881589949131012},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7325026988983154},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7261605858802795},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.628214955329895},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.6068249940872192},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.590858519077301},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.5800644755363464},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.573610782623291},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.49459192156791687},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4829075336456299},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.4707511067390442},{"id":"https://openalex.org/keywords/very-long-instruction-word","display_name":"Very long instruction word","score":0.4700647294521332},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4536846876144409},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.44950661063194275},{"id":"https://openalex.org/keywords/digital-signal-processor","display_name":"Digital signal processor","score":0.42374539375305176},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4223541021347046},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4111538231372833},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.36332541704177856},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2701965272426605},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2500843405723572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2176915407180786},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1483692228794098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.881589949131012},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7325026988983154},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7261605858802795},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.628214955329895},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.6068249940872192},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.590858519077301},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.5800644755363464},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.573610782623291},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.49459192156791687},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4829075336456299},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.4707511067390442},{"id":"https://openalex.org/C170595534","wikidata":"https://www.wikidata.org/wiki/Q249743","display_name":"Very long instruction word","level":2,"score":0.4700647294521332},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4536846876144409},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.44950661063194275},{"id":"https://openalex.org/C161611012","wikidata":"https://www.wikidata.org/wiki/Q106370","display_name":"Digital signal processor","level":3,"score":0.42374539375305176},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4223541021347046},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4111538231372833},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36332541704177856},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2701965272426605},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2500843405723572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2176915407180786},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1483692228794098},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac56929.2023.10247901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac56929.2023.10247901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 60th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2011039300","https://openalex.org/W2018641575","https://openalex.org/W2079436606","https://openalex.org/W2590246587","https://openalex.org/W2592969254","https://openalex.org/W2804032941","https://openalex.org/W2804500013","https://openalex.org/W3030475914","https://openalex.org/W3099525000","https://openalex.org/W3117137355","https://openalex.org/W3153044352","https://openalex.org/W3172873298","https://openalex.org/W3177452048","https://openalex.org/W4213212800","https://openalex.org/W4214613759","https://openalex.org/W4250470790","https://openalex.org/W4288346477","https://openalex.org/W6763062957"],"related_works":["https://openalex.org/W2566637483","https://openalex.org/W2127324789","https://openalex.org/W2115688358","https://openalex.org/W3024308452","https://openalex.org/W4244894488","https://openalex.org/W1503212777","https://openalex.org/W4285390450","https://openalex.org/W2366442643","https://openalex.org/W2090268225","https://openalex.org/W2021715972"],"abstract_inverted_index":{"Digital":[0],"signal":[1],"processors":[2],"(DSPs)":[3],"commonly":[4],"adopt":[5],"VLIW-SIMD":[6],"architecture":[7],"and":[8,27,56,106,128],"are":[9],"extensively":[10],"applied":[11],"in":[12,72,103],"most":[13],"compute-heavy":[14],"embedded":[15],"sensing":[16],"applications.":[17],"The":[18],"performances":[19],"for":[20,92,111,124,134],"DSP":[21],"kernels":[22],"rely":[23],"heavily":[24],"on":[25,36,46,59,96],"compilations":[26],"handwritten":[28],"optimizations.":[29],"Hand-crafted":[30],"methods":[31,42],"suffer":[32],"from":[33,80],"heavy":[34],"burden":[35],"programmers,":[37],"while":[38],"state-of-the-art":[39],"automatic":[40,87],"compilation":[41,62,116],"always":[43],"focus":[44],"more":[45],"a":[47,119],"certain":[48],"aspect":[49],"(tiling":[50],"or":[51],"auto-vectorization),":[52],"lacking":[53],"of":[54,101],"global":[55,125],"sequential":[57],"vision":[58],"the":[60,73],"intact":[61],"optimization":[63,95],"process.":[64],"It":[65,114],"still":[66],"requires":[67],"empirical":[68],"adjustments":[69],"by":[70],"programmers":[71,79],"actual":[74],"scenario.In":[75],"order":[76],"to":[77],"release":[78],"kernel":[81,93,132],"tuning,":[82],"we":[83],"propose":[84],"JOKer,":[85],"an":[86,108],"end-to-end":[88,109],"multi-level":[89],"code":[90],"generator":[91],"joint":[94],"DSPs.":[97],"JOKer":[98],"integrates":[99],"means":[100],"optimizations":[102],"compiling":[104],"process":[105],"provides":[107],"workflow":[110],"performance":[112,131],"tuning.":[113],"explores":[115],"configurations":[117],"through":[118],"reinforcement":[120],"learning":[121],"based":[122],"agent":[123],"optimal":[126],"solution":[127],"generates":[129],"high":[130],"codes":[133],"DSPs":[135],"automatically.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}
