{"id":"https://openalex.org/W4412046573","doi":"https://doi.org/10.1145/3747183","title":"Register Blocking: A Source-to-Source Analytical Modelling Approach for Affine Loop Kernels","display_name":"Register Blocking: A Source-to-Source Analytical Modelling Approach for Affine Loop Kernels","publication_year":2025,"publication_date":"2025-07-05","ids":{"openalex":"https://openalex.org/W4412046573","doi":"https://doi.org/10.1145/3747183"},"language":"en","primary_location":{"id":"doi:10.1145/3747183","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3747183","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3747183","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099870925","display_name":"Theologos Anthimopoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Theologos Anthimopoulos","raw_affiliation_strings":["School of Informatics, Aristotle University of Thessaloniki"],"raw_orcid":"https://orcid.org/0009-0007-3620-4637","affiliations":[{"raw_affiliation_string":"School of Informatics, Aristotle University of Thessaloniki","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074371053","display_name":"\u0393\u03b5\u03ce\u03c1\u03b3\u03b9\u03bf\u03c2 \u039a\u03b5\u03c1\u03b1\u03bc\u03af\u03b4\u03b1\u03c2","orcid":"https://orcid.org/0000-0003-0460-6061"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Keramidas","raw_affiliation_strings":["School of Informatics, Aristotle University of Thessaloniki"],"raw_orcid":"https://orcid.org/0000-0003-0460-6061","affiliations":[{"raw_affiliation_string":"School of Informatics, Aristotle University of Thessaloniki","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090157400","display_name":"Vasilios Kelefouras","orcid":"https://orcid.org/0000-0001-9591-913X"},"institutions":[{"id":"https://openalex.org/I897542642","display_name":"University of Plymouth","ror":"https://ror.org/008n7pv89","country_code":"GB","type":"education","lineage":["https://openalex.org/I897542642"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vasilios Kelefouras","raw_affiliation_strings":["School of Engineering, Computing and Mathematics, University of Plymouth"],"raw_orcid":"https://orcid.org/0000-0001-9591-913X","affiliations":[{"raw_affiliation_string":"School of Engineering, Computing and Mathematics, University of Plymouth","institution_ids":["https://openalex.org/I897542642"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036388687","display_name":"Iakovos Stamoulis","orcid":"https://orcid.org/0009-0004-4624-6089"},"institutions":[{"id":"https://openalex.org/I4210165146","display_name":"Applied Materials (Germany)","ror":"https://ror.org/05ejpyv46","country_code":"DE","type":"company","lineage":["https://openalex.org/I193427800","https://openalex.org/I4210165146"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Iakovos Stamoulis","raw_affiliation_strings":["Think Silicon S.A., An Applied Materials Company"],"raw_orcid":"https://orcid.org/0009-0004-4624-6089","affiliations":[{"raw_affiliation_string":"Think Silicon S.A., An Applied Materials Company","institution_ids":["https://openalex.org/I4210165146"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64676453,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"24","issue":"5","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.9958000183105469,"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"}},"topics":[{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.9958000183105469,"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"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9934999942779541,"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/blocking","display_name":"Blocking (statistics)","score":0.7721977829933167},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.5761798620223999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5742805004119873},{"id":"https://openalex.org/keywords/register","display_name":"Register (sociolinguistics)","score":0.5498377084732056},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.521914005279541},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.498960018157959},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40085357427597046},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30247557163238525},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.13909417390823364},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.12810984253883362},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1024715006351471}],"concepts":[{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7721977829933167},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.5761798620223999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5742805004119873},{"id":"https://openalex.org/C2779235478","wikidata":"https://www.wikidata.org/wiki/Q286576","display_name":"Register (sociolinguistics)","level":2,"score":0.5498377084732056},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.521914005279541},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.498960018157959},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40085357427597046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30247557163238525},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.13909417390823364},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.12810984253883362},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1024715006351471},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3747183","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3747183","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3747183","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3747183","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W125869453","https://openalex.org/W288065879","https://openalex.org/W1564285798","https://openalex.org/W2007451249","https://openalex.org/W2034761517","https://openalex.org/W2098891450","https://openalex.org/W2112796928","https://openalex.org/W2138007781","https://openalex.org/W2398692629","https://openalex.org/W2788464413","https://openalex.org/W2901114907","https://openalex.org/W2946042477","https://openalex.org/W2955053021","https://openalex.org/W3004913014","https://openalex.org/W3091055609","https://openalex.org/W4308596141","https://openalex.org/W4379518528","https://openalex.org/W4387350719","https://openalex.org/W4400224472","https://openalex.org/W6600234944","https://openalex.org/W6603799187","https://openalex.org/W6629577186","https://openalex.org/W6683589413","https://openalex.org/W7002000011"],"related_works":["https://openalex.org/W4312941541","https://openalex.org/W2361019053","https://openalex.org/W2071125430","https://openalex.org/W624979004","https://openalex.org/W4238987864","https://openalex.org/W2392835431","https://openalex.org/W4232669059","https://openalex.org/W2064119831","https://openalex.org/W1606827233","https://openalex.org/W2224948060"],"abstract_inverted_index":{"Register":[0],"Blocking":[1],"(RB),":[2],"also":[3],"known":[4],"as":[5],"\u2018Register-level":[6],"Tiling\u2019":[7],"or":[8],"\u2018unroll-and-jam,\u2019":[9],"is":[10,23,39,63,87,103],"a":[11,24,79,98],"key":[12],"compiler":[13],"optimization":[14],"for":[15,89],"developing":[16],"efficient":[17,92],"micro-kernels.":[18],"However,":[19],"applying":[20],"RB":[21,37,42,62,106],"effectively":[22],"complex":[25],"task":[26],"due":[27],"to":[28,110],"several":[29],"challenges.":[30],"First,":[31],"the":[32,55,59,67,72,108,113,122,132,169,172],"exploration":[33,56],"space":[34],"of":[35,61,115],"possible":[36],"configurations":[38],"vast.":[40],"Second,":[41],"and":[43,71,83,121,137,150,158,175],"loop":[44,74,138,156],"permutation":[45],"are":[46,125],"interdependent;":[47],"therefore,":[48],"addressing":[49],"both":[50,148],"optimizations":[51],"simultaneously":[52],"further":[53],"inflates":[54],"space.":[57],"Third,":[58],"effectiveness":[60],"highly":[64],"dependent":[65],"on":[66,147],"target":[68,133],"hardware":[69,134],"platform":[70],"specific":[73],"kernel":[75,139],"being":[76],"optimized.":[77],"As":[78],"result,":[80],"an":[81,91,128],"extensive":[82],"time-consuming":[84],"fine-tuning":[85],"process":[86],"necessary":[88],"achieving":[90],"implementation.":[93],"To":[94],"address":[95],"these":[96],"challenges,":[97],"source-to-source":[99],"analytical":[100,129],"modelling":[101],"approach":[102],"proposed.":[104],"The":[105,141,163],"factors,":[107],"loops":[109],"apply":[111],"RB,":[112],"number":[114],"allocated":[116],"variables/registers":[117],"per":[118],"array":[119],"reference,":[120],"loops\u2019":[123],"ordering":[124],"generated":[126],"by":[127],"model,":[130],"leveraging":[131],"architecture":[135],"details":[136],"characteristics.":[140],"proposed":[142],"methodology":[143],"has":[144],"been":[145],"evaluated":[146],"embedded":[149],"general-purpose":[151],"CPUs,":[152],"using":[153],"seven":[154],"well-known":[155],"kernels":[157],"three":[159],"machine":[160],"learning":[161],"applications.":[162],"results":[164],"show":[165],"significant":[166],"speedups":[167],"over":[168],"GCC":[170],"compiler,":[171],"Pluto":[173],"tool,":[174],"related":[176],"work.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
