{"id":"https://openalex.org/W4414198759","doi":"https://doi.org/10.1109/dac63849.2025.11133291","title":"Late Breaking Results: Statistical Timing Graph Scheduling Algorithm for GPU Computation","display_name":"Late Breaking Results: Statistical Timing Graph Scheduling Algorithm for GPU Computation","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414198759","doi":"https://doi.org/10.1109/dac63849.2025.11133291"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11133291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","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/A5052559632","display_name":"Chih\u2010Chun Chang","orcid":"https://orcid.org/0000-0002-4377-7026"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chih-Chun Chang","raw_affiliation_strings":["University of Wisconsin-Madison,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison,USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088685794","display_name":"Tsung\u2010Wei Huang","orcid":"https://orcid.org/0000-0001-9768-3378"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsung-Wei Huang","raw_affiliation_strings":["University of Wisconsin-Madison,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison,USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":4.2409,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94987684,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.904699981212616,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.904699981212616,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6187000274658203},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5425000190734863},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4851999878883362},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44510000944137573},{"id":"https://openalex.org/keywords/static-timing-analysis","display_name":"Static timing analysis","score":0.4020000100135803},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.38269999623298645},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.36160001158714294},{"id":"https://openalex.org/keywords/digital-electronics","display_name":"Digital electronics","score":0.33480000495910645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8361999988555908},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6973999738693237},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6187000274658203},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4851999878883362},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.475600004196167},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C93682380","wikidata":"https://www.wikidata.org/wiki/Q2025226","display_name":"Static timing analysis","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3411000072956085},{"id":"https://openalex.org/C81843906","wikidata":"https://www.wikidata.org/wiki/Q173156","display_name":"Digital electronics","level":3,"score":0.33480000495910645},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.3188999891281128},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.27959999442100525},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.26109999418258667},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11133291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","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":6,"referenced_works":["https://openalex.org/W1967709031","https://openalex.org/W3041526861","https://openalex.org/W3141440412","https://openalex.org/W3149402879","https://openalex.org/W3198396679","https://openalex.org/W4230035938"],"related_works":[],"abstract_inverted_index":{"Statistical":[0],"Static":[1],"Timing":[2],"Analysis":[3],"(SSTA)":[4],"is":[5],"a":[6,64,73,87,95],"crucial":[7],"technique":[8],"in":[9],"digital":[10],"circuit":[11],"design":[12],"because":[13],"it":[14,51],"addresses":[15],"on-chip":[16],"variations":[17],"(OCV)":[18],"by":[19],"propagating":[20],"timing":[21,66],"distributions":[22],"instead":[23],"of":[24,31],"fixed":[25],"delays.":[26],"However,":[27],"the":[28],"computational":[29],"complexity":[30],"SSTA":[32,56],"demands":[33],"significant":[34],"memory":[35,48,75,92],"and":[36],"long":[37],"runtimes.":[38],"While":[39],"GPUs":[40],"offer":[41],"opportunities":[42],"to":[43,53,82,94],"accelerate":[44],"SSTA,":[45],"their":[46],"limited":[47],"capacity":[49],"makes":[50],"challenging":[52],"handle":[54],"large-scale":[55],"workloads.":[57],"To":[58],"address":[59],"this":[60],"challenge,":[61],"we":[62],"propose":[63],"statistical":[65],"graph":[67],"(STG)":[68],"scheduling":[69],"algorithm":[70],"combined":[71],"with":[72,89],"GPU":[74,88],"management":[76],"strategy.":[77],"We":[78],"have":[79],"shown":[80],"up":[81],"$4.9":[83],"\\times$":[84],"speedup":[85],"on":[86],"16":[90],"GB":[91,103],"compared":[93],"20-thread":[96],"CPU":[97],"baseline":[98],"when":[99],"solving":[100],"an":[101],"18.2":[102],"STG.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}