{"id":"https://openalex.org/W3080542861","doi":"https://doi.org/10.1145/3409963.3410488","title":"AVX overhead profiling","display_name":"AVX overhead profiling","publication_year":2020,"publication_date":"2020-08-19","ids":{"openalex":"https://openalex.org/W3080542861","doi":"https://doi.org/10.1145/3409963.3410488","mag":"3080542861"},"language":"en","primary_location":{"id":"doi:10.1145/3409963.3410488","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3409963.3410488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM SIGOPS Asia-Pacific Workshop on 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/A5055183849","display_name":"Mathias Gottschlag","orcid":"https://orcid.org/0000-0001-8330-8059"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mathias Gottschlag","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000501317","display_name":"Tim Schmidt","orcid":"https://orcid.org/0009-0001-1383-2899"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Schmidt","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055263070","display_name":"Frank Bellosa","orcid":"https://orcid.org/0000-0002-0806-3191"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank Bellosa","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":1.1269,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.75186178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"59","last_page":"66"},"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/T10904","display_name":"Embedded Systems Design 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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9975000023841858,"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/overhead","display_name":"Overhead (engineering)","score":0.6887732744216919},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.652014434337616},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.596412718296051},{"id":"https://openalex.org/keywords/power-consumption","display_name":"Power consumption","score":0.5384213328361511},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4925597310066223},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4715542793273926},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.32000064849853516},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.19208118319511414},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.1541573703289032}],"concepts":[{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6887732744216919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.652014434337616},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.596412718296051},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.5384213328361511},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4925597310066223},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4715542793273926},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.32000064849853516},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.19208118319511414},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.1541573703289032},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3409963.3410488","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3409963.3410488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM SIGOPS Asia-Pacific Workshop on Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W35708471","https://openalex.org/W1598892388","https://openalex.org/W1628605343","https://openalex.org/W2002991280","https://openalex.org/W2050974892","https://openalex.org/W2734941459","https://openalex.org/W2838294110","https://openalex.org/W2928756332","https://openalex.org/W3011239373","https://openalex.org/W3021580169","https://openalex.org/W3031369767","https://openalex.org/W3103905023"],"related_works":["https://openalex.org/W986318368","https://openalex.org/W2000785801","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2990194547","https://openalex.org/W2004734601","https://openalex.org/W2611230223","https://openalex.org/W1468792037","https://openalex.org/W2611621114","https://openalex.org/W4300588659"],"abstract_inverted_index":{"The":[0],"AVX2":[1,44],"and":[2,19,77],"AVX-512":[3],"instructions":[4],"found":[5],"in":[6],"recent":[7],"Intel":[8],"CPUs":[9],"can":[10,34],"increase":[11],"the":[12,25,38,83,88],"performance":[13],"of":[14,37,54],"vectorized":[15],"code.":[16],"Their":[17],"complexity":[18],"increased":[20],"power":[21],"consumption,":[22],"however,":[23],"causes":[24],"CPU":[26],"to":[27],"reduce":[28],"its":[29],"frequency.":[30],"This":[31],"frequency":[32,68],"reduction":[33,69],"affect":[35],"parts":[36],"workload":[39],"which":[40],"do":[41],"not":[42],"use":[43],"or":[45],"AVX-512,":[46],"with":[47,61],"previous":[48],"work":[49],"reporting":[50],"an":[51],"overall":[52],"slowdown":[53],"more":[55],"than":[56,87],"10%":[57],"for":[58],"various":[59],"workloads":[60],"AVX-512-enabled":[62],"parts.":[63],"Although":[64],"countermeasures":[65],"against":[66],"this":[67],"overhead":[70,76],"exist,":[71],"they":[72],"themselves":[73],"cause":[74],"additional":[75,89],"are":[78,85],"therefore":[79],"only":[80],"viable":[81],"if":[82],"gains":[84],"larger":[86],"overhead.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
