{"id":"https://openalex.org/W4413146180","doi":"https://doi.org/10.1109/ipdpsw66978.2025.00222","title":"Towards Efficient Instruction Stream Scheduling for Stencil Computation on ARM Processors","display_name":"Towards Efficient Instruction Stream Scheduling for Stencil Computation on ARM Processors","publication_year":2025,"publication_date":"2025-06-03","ids":{"openalex":"https://openalex.org/W4413146180","doi":"https://doi.org/10.1109/ipdpsw66978.2025.00222"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw66978.2025.00222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw66978.2025.00222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","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/A5074346821","display_name":"Shanghao Liu","orcid":"https://orcid.org/0009-0007-2651-9651"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shanghao Liu","raw_affiliation_strings":["Beihang University,School of Computer Science and Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018705589","display_name":"Hailong Yang","orcid":"https://orcid.org/0000-0003-1101-7927"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Yang","raw_affiliation_strings":["Beihang University,School of Computer Science and Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683034","display_name":"Xin You","orcid":"https://orcid.org/0000-0002-9181-8646"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin You","raw_affiliation_strings":["Beihang University,School of Computer Science and Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074183877","display_name":"Zhongzhi Luan","orcid":"https://orcid.org/0000-0002-7186-0556"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongzhi Luan","raw_affiliation_strings":["Beihang University,School of Computer Science and Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110369968","display_name":"Yi Liu","orcid":"https://orcid.org/0009-0008-3024-5806"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Beihang University,School of Computer Science and Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101941938","display_name":"Depei Qian","orcid":"https://orcid.org/0000-0002-9301-8394"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Depei Qian","raw_affiliation_strings":["Beihang University,School of Computer Science and Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5074346821"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26593011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1307","last_page":"1310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9939000010490417,"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":0.9939000010490417,"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":0.9822999835014343,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.972100019454956,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.8613808155059814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8150889277458191},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7780112028121948},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6239111423492432},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5502994060516357},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.41374731063842773},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3685213327407837},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23682478070259094},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.20433443784713745},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14579421281814575},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.07858020067214966}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8613808155059814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8150889277458191},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7780112028121948},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6239111423492432},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5502994060516357},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.41374731063842773},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3685213327407837},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23682478070259094},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.20433443784713745},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14579421281814575},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.07858020067214966},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw66978.2025.00222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw66978.2025.00222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2039378765","https://openalex.org/W2003798513","https://openalex.org/W2151764765","https://openalex.org/W2890431355","https://openalex.org/W4376875029","https://openalex.org/W3149084271","https://openalex.org/W4247008888","https://openalex.org/W2150319905","https://openalex.org/W2962978274","https://openalex.org/W4298291099"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3,32,63],"propose":[4,33],"independent":[5,24],"instruction":[6,25],"stream":[7],"scheduling":[8,37],"with":[9,79],"the":[10,19,46,60],"Serial-FMA":[11],"to":[12,17,44,69],"Tree-Based":[13],"Reduction":[14],"(SFTBR)":[15],"technique":[16,38],"decompose":[18],"stencil":[20,73],"computation":[21],"into":[22],"multiple":[23],"streams":[26],"for":[27,39],"improved":[28],"instruction-level":[29],"parallelism.":[30],"Furthermore,":[31],"a":[34,65],"locality-aware":[35,40],"block":[36],"multi-level":[41],"thread":[42],"parallelism":[43],"address":[45],"complexities":[47],"of":[48],"cache":[49],"and":[50],"memory":[51],"hierarchies":[52],"on":[53,59,75],"modern":[54],"ARM":[55,76],"many-core":[56,77],"processors.":[57],"Based":[58],"above":[61],"techniques,":[62],"implement":[64],"domain-specific":[66],"compiler,":[67],"AOStencil,":[68],"automatically":[70],"generate":[71],"optimized":[72],"codes":[74],"processors":[78],"genetic-algorithm-driven":[80],"parameter":[81],"tuning.":[82]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}