{"id":"https://openalex.org/W3176001158","doi":"https://doi.org/10.1145/3461648.3463845","title":"Automatic mapping and code optimization for OpenCL kernels on FT-matrix architecture (WIP paper)","display_name":"Automatic mapping and code optimization for OpenCL kernels on FT-matrix architecture (WIP paper)","publication_year":2021,"publication_date":"2021-06-18","ids":{"openalex":"https://openalex.org/W3176001158","doi":"https://doi.org/10.1145/3461648.3463845","mag":"3176001158"},"language":"en","primary_location":{"id":"doi:10.1145/3461648.3463845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461648.3463845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems","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/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":false,"raw_author_name":"Xiaolei Zhao","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-5414-1162","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, 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, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, 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, China"],"raw_orcid":"https://orcid.org/0000-0003-1552-8396","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, 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, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100710936","display_name":"Chunyuan Zhang","orcid":"https://orcid.org/0000-0002-0944-2708"},"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":"Chunyuan Zhang","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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":0.9976999759674072,"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":0.8667576313018799},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.8005673885345459},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7311811447143555},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6860162019729614},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.484479159116745},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4637008607387543},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4357476830482483},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.38497719168663025},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3407503664493561},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22565481066703796}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8667576313018799},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8005673885345459},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7311811447143555},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6860162019729614},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.484479159116745},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4637008607387543},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4357476830482483},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.38497719168663025},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3407503664493561},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22565481066703796},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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:10.1145/3461648.3463845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461648.3463845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W206408101","https://openalex.org/W2031781358","https://openalex.org/W2066862978","https://openalex.org/W2079436606","https://openalex.org/W2954586490","https://openalex.org/W3002400545","https://openalex.org/W3030475914","https://openalex.org/W3033144124"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2076165488","https://openalex.org/W3189307731","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1428699136","https://openalex.org/W1998560227","https://openalex.org/W2019451907"],"abstract_inverted_index":{"FT-Matrix":[0,32,83],"is":[1,17,57],"a":[2],"typical":[3],"vector-SIMD":[4],"architecture":[5],"that":[6,107],"refines":[7],"the":[8,39,44,125],"cooperation":[9],"between":[10],"scalar":[11],"and":[12,26,75,98,100,114],"vector":[13,36,52],"units.":[14],"This":[15,69],"approach":[16,87],"widely":[18],"used":[19],"in":[20],"digital":[21],"signal":[22],"processing,":[23],"high-performance":[24],"computing,":[25],"artificial":[27],"intelligence,":[28],"among":[29],"other":[30],"fields.":[31],"currently":[33],"adopts":[34],"C":[35],"extension":[37,53],"as":[38,121,123],"main":[40],"programming":[41,126],"model,":[42],"improving":[43],"utilization":[45,117],"efficiency":[46],"of":[47,93],"SIMD":[48],"by":[49,67,91],"providing":[50],"explicit":[51],"API.":[54],"Moreover,":[55],"it":[56],"difficult":[58],"to":[59],"efficiently":[60],"transplant":[61],"parallel":[62],"programs":[63],"(OpenCL,":[64],"CUDA)":[65],"adopted":[66],"users.":[68],"paper":[70],"proposes":[71],"an":[72],"automatic":[73],"mapping":[74],"code":[76,102],"optimization":[77],"method":[78,109],"for":[79,118],"OpenCL":[80,119],"kernels":[81],"on":[82,128],"architecture.":[84],"The":[85],"proposed":[86],"solves":[88],"these":[89],"challenges":[90],"means":[92],"work":[94],"item":[95],"coalescing,":[96],"slicing":[97],"rotation,":[99],"instruction-level":[101],"optimization.":[103],"Preliminary":[104],"results":[105],"show":[106],"our":[108],"can":[110],"achieve":[111],"high":[112],"performance":[113],"good":[115],"hardware":[116],"kernels,":[120],"well":[122],"decreasing":[124],"difficulty":[127],"FT-Matrix.":[129]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}