{"id":"https://openalex.org/W7166354018","doi":"https://doi.org/10.1145/3801487.3801808","title":"A Portable GPU Kernel Performance Modeling Method Based on LLVM IR Dynamic Feature Prediction","display_name":"A Portable GPU Kernel Performance Modeling Method Based on LLVM IR Dynamic Feature Prediction","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7166354018","doi":"https://doi.org/10.1145/3801487.3801808"},"language":null,"primary_location":{"id":"doi:10.1145/3801487.3801808","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3801808","pdf_url":null,"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 23rd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3801487.3801808","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109103720","display_name":"Qiang Wang","orcid":"https://orcid.org/0000-0001-9179-6611"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-9179-6611","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101521156","display_name":"Hao Zheng","orcid":"https://orcid.org/0000-0001-8381-0049"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zheng","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0005-6999-5071","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139475476","display_name":"Yiru Liu","orcid":"https://orcid.org/0009-0005-2630-2431"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiru Liu","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0005-2630-2431","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139510591","display_name":"Fan Yang","orcid":"https://orcid.org/0009-0006-1828-9633"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0006-1828-9633","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139503899","display_name":"Jiachen Liu","orcid":"https://orcid.org/0009-0000-1611-0608"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiachen Liu","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0000-1611-0608","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139497223","display_name":"Chaojun Deng","orcid":"https://orcid.org/0009-0008-9041-5467"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaojun Deng","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0008-9041-5467","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100717657","display_name":"Ziheng Wang","orcid":"https://orcid.org/0000-0001-5064-2376"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziheng Wang","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-5064-2376","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100332436","display_name":"Xiaoshe Dong","orcid":"https://orcid.org/0000-0002-9003-2625"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshe Dong","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-9003-2625","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.95683203,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"271","last_page":"279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9429000020027161,"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":0.9429000020027161,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.01489999983459711,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.006099999882280827,"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/profiling","display_name":"Profiling (computer programming)","score":0.6133000254631042},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5443999767303467},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5354999899864197},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5134999752044678},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4178999960422516},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.3912000060081482},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3774999976158142},{"id":"https://openalex.org/keywords/rootkit","display_name":"Rootkit","score":0.37380000948905945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8963000178337097},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6133000254631042},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5443999767303467},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5354999899864197},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3912999927997589},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C10144332","wikidata":"https://www.wikidata.org/wiki/Q14645","display_name":"Rootkit","level":3,"score":0.37380000948905945},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.3019999861717224},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25609999895095825},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3801487.3801808","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3801808","pdf_url":null,"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 23rd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3801487.3801808","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3801808","pdf_url":null,"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 23rd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.415502667427063,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G3637710088","display_name":null,"funder_award_id":"2023YFB3001804","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2038666141","https://openalex.org/W2045271686","https://openalex.org/W2080592089","https://openalex.org/W2113282196","https://openalex.org/W2128120785","https://openalex.org/W2167334577","https://openalex.org/W2611990469","https://openalex.org/W2751871758","https://openalex.org/W2794513473","https://openalex.org/W2796878504","https://openalex.org/W2899387410","https://openalex.org/W2921788688","https://openalex.org/W2923029190","https://openalex.org/W2930604630","https://openalex.org/W2962843187","https://openalex.org/W2984189761","https://openalex.org/W3015338905","https://openalex.org/W3037110041","https://openalex.org/W3039595577","https://openalex.org/W3115175310","https://openalex.org/W4297569227","https://openalex.org/W4379388541","https://openalex.org/W4392167388","https://openalex.org/W4392240387","https://openalex.org/W4402474531","https://openalex.org/W4405362884"],"related_works":[],"abstract_inverted_index":{"Performance":[0,114],"modeling":[1],"of":[2,198],"GPU":[3,61],"kernels":[4,180],"is":[5,162],"essential":[6],"for":[7,53,171],"compiler":[8],"optimizations,":[9],"runtime":[10,122,161],"scheduling,":[11],"and":[12,38,111,143,149,183,204,217],"auto-tuning":[13],"systems.":[14],"However,":[15],"existing":[16,211],"approaches":[17],"often":[18],"rely":[19],"on":[20,131,178,200,206],"hardware-specific":[21],"metrics":[22],"or":[23,141],"require":[24],"online":[25,54,172],"kernel":[26,165],"execution":[27,82],"to":[28,90,120],"collect":[29],"dynamic":[30,74],"features":[31],"during":[32],"prediction,":[33],"which":[34],"incurs":[35],"significant":[36],"overhead":[37,151],"limits":[39],"their":[40],"deployment":[41],"in":[42,213],"latency-sensitive":[43],"scenarios":[44],"while":[45,56],"hindering":[46],"cross-platform":[47],"generalization.":[48],"To":[49],"eliminate":[50],"the":[51,169],"need":[52,170],"profiling":[55,129,148],"maintaining":[57],"prediction":[58,215],"accuracy":[59,216],"across":[60,154,185],"platforms,":[62,209],"we":[63],"propose":[64],"a":[65,92,132],"specialized":[66],"two-stage":[67],"performance":[68],"model":[69,97],"mehod":[70],"that":[71,98,191],"leverages":[72],"platform-independent":[73,79],"features.":[75,125],"Our":[76],"method":[77,177],"uses":[78],"basic":[80],"block":[81],"counts":[83],"(BBC)":[84],"derived":[85],"from":[86,101,123,181],"instrumented":[87],"LLVM":[88],"IR":[89],"train":[91],"shared":[93],"Feature":[94],"Prediction":[95,115],"(FP)":[96],"predicts":[99],"BBC":[100],"static":[102],"launch":[103,109],"configurations":[104],"(e.g.,":[105,139],"problem":[106],"size,":[107],"thread":[108],"configuration),":[110],"lightweight":[112],"platform-specific":[113],"(PP)":[116],"models":[117],"are":[118],"trained":[119],"estimate":[121],"these":[124],"This":[126],"design":[127],"requires":[128],"only":[130],"single":[133],"reference":[134],"device":[135],"per":[136],"compilation":[137,187],"ecosystem":[138],"CUDA":[140,208],"ROCm)":[142],"enables":[144],"intra-ecosystem":[145,218],"portability,":[146],"reducing":[147],"retraining":[150],"when":[152],"deploying":[153],"multiple":[155],"GPUs.":[156],"Moreover,":[157],"at":[158],"inference":[159],"time,":[160],"estimated":[163],"without":[164],"execution,":[166],"thereby":[167],"eliminating":[168],"profiling.":[173],"We":[174],"evaluate":[175],"our":[176,192],"34":[179],"PolyBench":[182],"Rodinia":[184],"two":[186],"ecosystems.":[188],"Experiments":[189],"show":[190],"approach":[193],"achieves":[194],"an":[195],"average":[196],"MAPE":[197],"8.3%":[199],"three":[201,207],"ROCm":[202],"platforms":[203],"4.96%":[205],"outperforming":[210],"methods":[212],"both":[214],"portability.":[219]},"counts_by_year":[],"updated_date":"2026-06-28T06:20:29.262167","created_date":"2026-06-28T00:00:00"}