{"id":"https://openalex.org/W4401568304","doi":"https://doi.org/10.23919/date58400.2024.10546600","title":"A Compiler Phase to Optimally Split GPU Wavefronts for Safety-Critical Systems","display_name":"A Compiler Phase to Optimally Split GPU Wavefronts for Safety-Critical Systems","publication_year":2024,"publication_date":"2024-03-25","ids":{"openalex":"https://openalex.org/W4401568304","doi":"https://doi.org/10.23919/date58400.2024.10546600"},"language":"en","primary_location":{"id":"doi:10.23919/date58400.2024.10546600","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/date58400.2024.10546600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)","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/A5092831742","display_name":"Artem Klashtorny","orcid":"https://orcid.org/0009-0001-8458-8512"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Artem Klashtorny","raw_affiliation_strings":["University of Waterloo,Electrical and Computer Engineering,Waterloo,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Electrical and Computer Engineering,Waterloo,Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081788400","display_name":"Mahesh Tripunitara","orcid":"https://orcid.org/0000-0002-3615-9393"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mahesh Tripunitara","raw_affiliation_strings":["University of Waterloo,Electrical and Computer Engineering,Waterloo,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Electrical and Computer Engineering,Waterloo,Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042701714","display_name":"Hiren Patel","orcid":"https://orcid.org/0000-0003-1128-8110"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hiren Patel","raw_affiliation_strings":["University of Waterloo,Electrical and Computer Engineering,Waterloo,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Electrical and Computer Engineering,Waterloo,Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9944000244140625,"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":0.9944000244140625,"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":0.991599977016449,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.991599977016449,"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/compiler","display_name":"Compiler","score":0.7899004220962524},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7608643770217896},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5787983536720276},{"id":"https://openalex.org/keywords/wavefront","display_name":"Wavefront","score":0.4804651141166687},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.42575934529304504},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1901915967464447},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.11094531416893005},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10815593600273132}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7899004220962524},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7608643770217896},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5787983536720276},{"id":"https://openalex.org/C165699331","wikidata":"https://www.wikidata.org/wiki/Q461533","display_name":"Wavefront","level":2,"score":0.4804651141166687},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.42575934529304504},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1901915967464447},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.11094531416893005},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10815593600273132},{"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:10.23919/date58400.2024.10546600","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/date58400.2024.10546600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4240253816","https://openalex.org/W2108497790","https://openalex.org/W3096456556","https://openalex.org/W2047489700","https://openalex.org/W2169584677","https://openalex.org/W2979513934","https://openalex.org/W4232954277","https://openalex.org/W2053110192"],"abstract_inverted_index":{"We":[0,46,74],"present":[1],"a":[2,51,65],"compiler":[3,52],"phase":[4],"for":[5,43,54],"GPUs":[6],"enabled":[7],"with":[8],"predictable":[9],"wavefront":[10],"splitting":[11],"(PWSG)":[12],"that":[13,35,88],"implements":[14],"an":[15,55,79],"optimal":[16],"algorithm":[17,28,49],"to":[18,97,103,110,114],"split":[19,98],"diverging":[20],"GPU":[21,33,95],"wavefronts":[22],"into":[23],"separate":[24],"scheduleable":[25],"entities.":[26],"This":[27],"selects":[29],"branches":[30],"in":[31,50,93],"the":[32,37,44,61,70,94,105],"kernel":[34,96],"guarantee":[36],"lowest":[38],"worst-case":[39],"execution":[40],"time":[41],"(WCET)":[42],"kernel.":[45],"implement":[47],"our":[48,76],"flow":[53],"AMD":[56,71],"GPU,":[57],"and":[58],"we":[59,100],"deploy":[60],"resulting":[62],"binary":[63],"on":[64,78],"gem5":[66],"micro-architectural":[67],"implementation":[68,77],"of":[69,82],"GCN3":[72],"GPU.":[73],"evaluate":[75],"extensive":[80],"set":[81],"synthetic":[83],"benchmarks.":[84],"Our":[85],"experiments":[86],"show":[87],"by":[89],"automatically":[90],"selecting":[91],"points":[92],"wavefronts,":[99],"are":[101],"able":[102],"reduce":[104],"WCET":[106],"ranging":[107],"from":[108],"34%":[109],"52%":[111],"reduction":[112],"compared":[113],"five":[115],"alternative":[116],"approaches.":[117]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}