{"id":"https://openalex.org/W4400224480","doi":"https://doi.org/10.1145/3649153.3649196","title":"DNNOPT: A Framework for Efficiently Selecting On-chip Memory Loop Optimizations of DNN Accelerators","display_name":"DNNOPT: A Framework for Efficiently Selecting On-chip Memory Loop Optimizations of DNN Accelerators","publication_year":2024,"publication_date":"2024-05-07","ids":{"openalex":"https://openalex.org/W4400224480","doi":"https://doi.org/10.1145/3649153.3649196"},"language":"en","primary_location":{"id":"doi:10.1145/3649153.3649196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649153.3649196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM International Conference on Computing Frontiers","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/A5086797997","display_name":"Piyumal Ranawaka","orcid":"https://orcid.org/0000-0002-7006-2376"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Piyumal Ranawaka","raw_affiliation_strings":["Chalmers University of Technology, Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology, Gothenburg, Sweden","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008522376","display_name":"Muhammad Waqar Azhar","orcid":"https://orcid.org/0000-0003-0477-4540"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Muhammad Waqar Azhar","raw_affiliation_strings":["Chalmers University of Technology, Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology, Gothenburg, Sweden","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091704449","display_name":"Per Stenstr\u00f6m","orcid":"https://orcid.org/0000-0002-7441-8245"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Per Stenstrom","raw_affiliation_strings":["Chalmers University of Technology, Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology, Gothenburg, Sweden","institution_ids":["https://openalex.org/I66862912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5086797997"],"corresponding_institution_ids":["https://openalex.org/I66862912"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08575804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9988999962806702,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9987999796867371,"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":0.7541581392288208},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6150237321853638},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5838432312011719},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.5342440009117126},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.5217729210853577},{"id":"https://openalex.org/keywords/system-on-a-chip","display_name":"System on a chip","score":0.5199462175369263},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.40080755949020386},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07358774542808533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541581392288208},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6150237321853638},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5838432312011719},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.5342440009117126},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.5217729210853577},{"id":"https://openalex.org/C118021083","wikidata":"https://www.wikidata.org/wiki/Q610398","display_name":"System on a chip","level":2,"score":0.5199462175369263},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.40080755949020386},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07358774542808533},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3649153.3649196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649153.3649196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},{"id":"pmh:oai:research.chalmers.se:542156","is_oa":false,"landing_page_url":"https://research.chalmers.se/en/publication/542156","pdf_url":null,"source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2034761517","https://openalex.org/W2049890071","https://openalex.org/W2094756095","https://openalex.org/W2100218206","https://openalex.org/W2318529993","https://openalex.org/W2442974303","https://openalex.org/W2464177207","https://openalex.org/W2471164860","https://openalex.org/W2584311934","https://openalex.org/W2612090114","https://openalex.org/W2780077279","https://openalex.org/W2884700152","https://openalex.org/W2899367379","https://openalex.org/W2905135312","https://openalex.org/W2921953552","https://openalex.org/W2940862705","https://openalex.org/W2945146780","https://openalex.org/W2954698171","https://openalex.org/W2961619211","https://openalex.org/W2963495494","https://openalex.org/W2979644612","https://openalex.org/W2997929983","https://openalex.org/W2998732502","https://openalex.org/W3004659153","https://openalex.org/W3017521908","https://openalex.org/W3037847693","https://openalex.org/W3049586678","https://openalex.org/W3097528158","https://openalex.org/W3103034165","https://openalex.org/W3112293503","https://openalex.org/W3123054690","https://openalex.org/W3132942233","https://openalex.org/W3135765046","https://openalex.org/W3137875211","https://openalex.org/W3156745629","https://openalex.org/W3192336523","https://openalex.org/W3206210071","https://openalex.org/W4200566604","https://openalex.org/W4205762292","https://openalex.org/W4238109388","https://openalex.org/W4256622436","https://openalex.org/W4283643682","https://openalex.org/W4288083528","https://openalex.org/W4312225933","https://openalex.org/W4321184926","https://openalex.org/W6719768283"],"related_works":["https://openalex.org/W2065289416","https://openalex.org/W2502691491","https://openalex.org/W2017236304","https://openalex.org/W3142211975","https://openalex.org/W1879443270","https://openalex.org/W2018912978","https://openalex.org/W2136854845","https://openalex.org/W2130914040","https://openalex.org/W2119122672","https://openalex.org/W4292904049"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"(DNN)":[3],"accelerators":[4],"suffer":[5],"from":[6],"poor":[7],"utilization":[8,29],"of":[9,46,58],"on-chip":[10,27],"memory":[11,28],"which":[12],"potentially":[13],"reduces":[14],"performance":[15],"and":[16,21],"energy":[17],"efficiency.":[18],"Loop":[19],"reordering":[20],"blocking":[22],"are":[23,37],"used":[24],"to":[25,40,54],"improve":[26],"in":[30],"DNN":[31],"accelerators.":[32],"However,":[33],"existing":[34],"optimization":[35],"frameworks":[36],"inefficient":[38],"due":[39,53],"either":[41],"a":[42,55],"prohibitive":[43],"time":[44],"complexity":[45],"searching":[47],"the":[48],"entire":[49],"search":[50],"space":[51],"or":[52],"sub-optimal":[56],"choice":[57],"optimizations.":[59]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
