{"id":"https://openalex.org/W4399304396","doi":"https://doi.org/10.1145/3650200.3656630","title":"Tile Size and Loop Order Selection using Machine Learning for Multi-/Many-Core Architectures","display_name":"Tile Size and Loop Order Selection using Machine Learning for Multi-/Many-Core Architectures","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399304396","doi":"https://doi.org/10.1145/3650200.3656630"},"language":"en","primary_location":{"id":"doi:10.1145/3650200.3656630","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656630","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656630","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656630","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099001591","display_name":"Shilpa Babalad","orcid":"https://orcid.org/0000-0002-9114-0409"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shilpa Babalad","raw_affiliation_strings":["Indian Institute of Science, India"],"raw_orcid":"https://orcid.org/0000-0002-9114-0409","affiliations":[{"raw_affiliation_string":"Indian Institute of Science, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026126465","display_name":"Shirish Shevade","orcid":"https://orcid.org/0009-0009-7202-6860"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shirish Shevade","raw_affiliation_strings":["Indian Institute of Science, India"],"raw_orcid":"https://orcid.org/0009-0009-7202-6860","affiliations":[{"raw_affiliation_string":"Indian Institute of Science, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027487670","display_name":"Matthew J. Thazhuthaveetil","orcid":"https://orcid.org/0009-0007-1550-8121"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Matthew Jacob Thazhuthaveetil","raw_affiliation_strings":["Indian Institute of Science, India"],"raw_orcid":"https://orcid.org/0009-0007-1550-8121","affiliations":[{"raw_affiliation_string":"Indian Institute of Science, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006412622","display_name":"R Govindarajan","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"R Govindarajan","raw_affiliation_strings":["Indian Institute of Science, India"],"raw_orcid":"https://orcid.org/0000-0003-2517-9994","affiliations":[{"raw_affiliation_string":"Indian Institute of Science, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5099001591"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.9487,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71673927,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"388","last_page":"399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9995999932289124,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9986000061035156,"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/loop-tiling","display_name":"Loop tiling","score":0.8539187908172607},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7826536893844604},{"id":"https://openalex.org/keywords/tile","display_name":"Tile","score":0.728759765625},{"id":"https://openalex.org/keywords/loop-fission","display_name":"Loop fission","score":0.670471727848053},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.6433538198471069},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6207039952278137},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5778285264968872},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.49913811683654785},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.42077067494392395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3732183575630188},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32853174209594727},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32057368755340576},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2831127643585205},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10489386320114136}],"concepts":[{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.8539187908172607},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7826536893844604},{"id":"https://openalex.org/C2780728851","wikidata":"https://www.wikidata.org/wiki/Q468402","display_name":"Tile","level":2,"score":0.728759765625},{"id":"https://openalex.org/C134718785","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fission","level":3,"score":0.670471727848053},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.6433538198471069},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6207039952278137},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5778285264968872},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.49913811683654785},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.42077067494392395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3732183575630188},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32853174209594727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32057368755340576},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2831127643585205},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10489386320114136},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3650200.3656630","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656630","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656630","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai::85619","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.1145/3650200.3656630","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656630","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656630","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399304396.pdf","grobid_xml":"https://content.openalex.org/works/W4399304396.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1967846636","https://openalex.org/W1983545421","https://openalex.org/W1991009705","https://openalex.org/W2034761517","https://openalex.org/W2048430744","https://openalex.org/W2049890071","https://openalex.org/W2064441385","https://openalex.org/W2071110673","https://openalex.org/W2077143534","https://openalex.org/W2100218206","https://openalex.org/W2111726457","https://openalex.org/W2157099283","https://openalex.org/W2157273783","https://openalex.org/W2168155345","https://openalex.org/W2168519934","https://openalex.org/W2169875292","https://openalex.org/W2340076492","https://openalex.org/W2475636809","https://openalex.org/W2751901133","https://openalex.org/W2793666465","https://openalex.org/W2912281309","https://openalex.org/W3008788679","https://openalex.org/W3114760331","https://openalex.org/W3172873298","https://openalex.org/W4214583996","https://openalex.org/W4313419123"],"related_works":["https://openalex.org/W2014071052","https://openalex.org/W2342605656","https://openalex.org/W1596526459","https://openalex.org/W1545258949","https://openalex.org/W4238138329","https://openalex.org/W2124711255","https://openalex.org/W2011263215","https://openalex.org/W2003132503","https://openalex.org/W1488921751","https://openalex.org/W2042531701"],"abstract_inverted_index":{"Loop":[0],"tiling":[1],"and":[2,13,16,31,79,95,110,120,144],"loop":[3,24,32,52,96,101,111,130],"interchange":[4],"(or":[5],"permutation)":[6],"are":[7],"techniques":[8],"that":[9],"can":[10,17],"expose":[11],"task":[12],"data-level":[14],"parallelisms":[15],"exploit":[18],"data":[19],"locality":[20],"available":[21],"in":[22,66,106],"multi-dimensional":[23],"nests.":[25],"Choosing":[26],"the":[27,42,48,51,59,91,123],"appropriate":[28],"tile":[29,93,108],"size":[30,94],"order":[33,97],"is":[34,54,117],"important":[35],"to":[36,58,89,153],"achieve":[37],"significant":[38],"performance":[39,49,125],"improvement.":[40],"However,":[41],"effect":[43],"of":[44,50,62,122,129,151],"these":[45],"transformations":[46],"on":[47,115,132],"nest":[53],"not":[55],"straightforward":[56],"due":[57],"complex":[60],"interplay":[61],"several":[63],"architectural":[64],"features":[65],"multi-/many-core":[67],"architectures.":[68],"In":[69],"this":[70],"work,":[71],"we":[72],"propose":[73],"using":[74],"a":[75,81,99,147],"supervised":[76],"learning":[77],"technique":[78],"develop":[80],"Support":[82],"Vector":[83],"Machine":[84],"(SVM)":[85],"based":[86],"hierarchical":[87],"classifier":[88],"identify":[90],"best-performing":[92],"for":[98,126],"given":[100],"nest.":[102],"Our":[103],"approach":[104],"results":[105],"identifying":[107],"sizes":[109],"orders":[112],"whose":[113],"performance,":[114],"average,":[116],"within":[118],"18%":[119],"9%":[121],"optimal":[124],"two":[127],"sets":[128],"nests":[131],"Intel":[133],"Xeon":[134],"Cascadelake":[135],"architecture.":[136],"Further,":[137],"our":[138],"method":[139],"outperforms":[140],"state-of-the-art":[141],"techniques,":[142],"Pluto":[143],"Polly,":[145],"with":[146],"geometric":[148],"mean":[149],"speedup":[150],"1.35x":[152],"1.58x.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}