{"id":"https://openalex.org/W2946829662","doi":"https://doi.org/10.23919/date.2019.8714861","title":"Cache-Aware Kernel Tiling: An Approach for System-Level Performance Optimization of GPU-Based Applications","display_name":"Cache-Aware Kernel Tiling: An Approach for System-Level Performance Optimization of GPU-Based Applications","publication_year":2019,"publication_date":"2019-03-01","ids":{"openalex":"https://openalex.org/W2946829662","doi":"https://doi.org/10.23919/date.2019.8714861","mag":"2946829662"},"language":"en","primary_location":{"id":"doi:10.23919/date.2019.8714861","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2019.8714861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Design, Automation &amp; Test in Europe Conference &amp; Exhibition (DATE)","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/A5033993115","display_name":"Arian Maghazeh","orcid":null},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Arian Maghazeh","raw_affiliation_strings":["Department of Computer and Information Science, Link\u00f6ping University, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, Link\u00f6ping University, Sweden","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103205285","display_name":"Sudipta Chattopadhyay","orcid":"https://orcid.org/0000-0001-8935-2990"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Sudipta Chattopadhyay","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001844771","display_name":"Petru Eles","orcid":"https://orcid.org/0000-0001-8621-3346"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Petru Eles","raw_affiliation_strings":["Department of Computer and Information Science, Link\u00f6ping University, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, Link\u00f6ping University, Sweden","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003372884","display_name":"Zebo Peng","orcid":"https://orcid.org/0000-0002-5137-565X"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Zebo Peng","raw_affiliation_strings":["Department of Computer and Information Science, Link\u00f6ping University, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, Link\u00f6ping University, Sweden","institution_ids":["https://openalex.org/I102134673"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3051,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59706804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"570","last_page":"575"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.8835875988006592},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7162498235702515},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7013915777206421},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.603339672088623},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.43051111698150635},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4270389676094055},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3315759301185608}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8835875988006592},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7162498235702515},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7013915777206421},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.603339672088623},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.43051111698150635},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4270389676094055},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3315759301185608},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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:10.23919/date.2019.8714861","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2019.8714861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Design, Automation &amp; Test in Europe Conference &amp; Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1578285471","https://openalex.org/W1984490927","https://openalex.org/W2072912074","https://openalex.org/W2087250219","https://openalex.org/W2098290747","https://openalex.org/W2171888576","https://openalex.org/W2433248078","https://openalex.org/W2512431201","https://openalex.org/W2618092901","https://openalex.org/W2951810231","https://openalex.org/W4235557873"],"related_works":["https://openalex.org/W2167303720","https://openalex.org/W2497617944","https://openalex.org/W1563139915","https://openalex.org/W2109715593","https://openalex.org/W2061075966","https://openalex.org/W3147501184","https://openalex.org/W2268996566","https://openalex.org/W4256652509","https://openalex.org/W2140219379","https://openalex.org/W2129141857"],"abstract_inverted_index":{"We":[0,104],"present":[1],"a":[2,20,109],"software":[3],"approach":[4],"to":[5,43,95],"address":[6],"the":[7,24,31,39,48,61,69,76,116],"data":[8,34],"latency":[9],"issue":[10],"for":[11],"certain":[12],"GPU":[13,28,40],"applications.":[14],"Each":[15],"application":[16,113],"is":[17,53,93],"modeled":[18],"as":[19],"kernel":[21,59,88,96],"graph,":[22],"where":[23],"nodes":[25],"represent":[26],"individual":[27],"kernels":[29],"and":[30,98,114],"edges":[32],"capture":[33],"dependencies.":[35],"Our":[36,90],"technique":[37,92,107],"exploits":[38],"L2":[41],"cache":[42],"accelerate":[44],"parameter":[45],"passing":[46],"between":[47],"kernels.":[49],"The":[50],"key":[51],"idea":[52],"that,":[54],"instead":[55],"of":[56,87],"having":[57],"each":[58,81],"process":[60,80],"entire":[62],"input":[63,70],"in":[64,75,83],"one":[65,84],"invocation,":[66],"we":[67],"subdivide":[68],"into":[71],"fragments":[72],"(which":[73],"fit":[74],"cache)":[77],"and,":[78],"ideally,":[79],"fragment":[82],"continuous":[85],"sequence":[86],"invocations.":[89],"proposed":[91],"oblivious":[94],"functionalities":[97],"requires":[99],"minimal":[100],"source":[101],"code":[102],"modification.":[103],"demonstrate":[105],"our":[106],"on":[108,118],"full-fledged":[110],"image":[111],"processing":[112],"improve":[115],"performance":[117],"average":[119],"by":[120],"30%":[121],"over":[122],"various":[123],"settings.":[124]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
