{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:47:17Z","timestamp":1782546437045,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFB3001804"],"award-info":[{"award-number":["2023YFB3001804"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,19]]},"DOI":"10.1145\/3801487.3801808","type":"proceedings-article","created":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:05:47Z","timestamp":1782543947000},"page":"271-279","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Portable GPU Kernel Performance Modeling Method Based on LLVM IR Dynamic Feature Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9179-6611","authenticated-orcid":false,"given":"Qiang","family":"Wang","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6999-5071","authenticated-orcid":false,"given":"Hao","family":"Zheng","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2630-2431","authenticated-orcid":false,"given":"Yiru","family":"Liu","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1828-9633","authenticated-orcid":false,"given":"Fan","family":"Yang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1611-0608","authenticated-orcid":false,"given":"Jiachen","family":"Liu","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9041-5467","authenticated-orcid":false,"given":"Chaojun","family":"Deng","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5064-2376","authenticated-orcid":false,"given":"Ziheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9003-2625","authenticated-orcid":false,"given":"Xiaoshe","family":"Dong","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,27]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Gargi Alavani Jineet Desai Snehanshu Saha and Santonu Sarkar. 2023. Program analysis and machine learning\u2013based approach to predict power consumption of cuda kernel. ACM Transactions on Modeling and Performance Evaluation of Computing Systems 8 4 (2023) 1\u201324.","DOI":"10.1145\/3603533"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/BDCloud.2018.00139"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Marcos Amaris Raphael Camargo Daniel Cordeiro Alfredo Goldman and Denis Trystram. 2023. Evaluating execution time predictions on gpu kernels using an analytical model and machine learning techniques. J. Parallel and Distrib. Comput. 171 (2023) 66\u201378.","DOI":"10.1016\/j.jpdc.2022.09.002"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Yehia Arafa Abdel-Hameed\u00a0A Badawy Gopinath Chennupati Nandakishore Santhi and Stephan Eidenbenz. 2019. Ppt-gpu: Scalable gpu performance modeling. IEEE Computer Architecture Letters 18 1 (2019) 55\u201358.","DOI":"10.1109\/LCA.2019.2904497"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/1693453.1693470"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS49563.2019.00014"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Lorenz Braun Sotirios Nikas Chen Song Vincent Heuveline and Holger Fr\u00f6ning. 2020. A simple model for portable and fast prediction of execution time and power consumption of GPU kernels. ACM Transactions on Architecture and Code Optimization (TACO) 18 1 (2020) 1\u201325.","DOI":"10.1145\/3431731"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2017.28"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPDS62779.2024.10667546"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3392717.3392737"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"S\u00e9bastien Darche and Michel\u00a0R Dagenais. 2024. Low-overhead trace collection and profiling on GPU compute kernels. ACM Transactions on Parallel Computing 11 2 (2024) 1\u201324.","DOI":"10.1145\/3649510"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337833"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339595"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00072"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Jo\u00e3o Guerreiro Aleksandar Ilic Nuno Roma and Pedro Tom\u00e1s. 2019. GPU static modeling using PTX and deep structured learning. IEEE Access 7 (2019) 159150\u2013159161.","DOI":"10.1109\/ACCESS.2019.2951218"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555775"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS.2018.00095"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.34"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS64422.2024.10786558"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Ali Riahi Abdorreza Savadi and Mahmoud Naghibzadeh. 2024. Many-BSP: an analytical performance model for CUDA kernels. Computing 106 5 (2024) 1519\u20131555.","DOI":"10.1007\/s00607-023-01255-w"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Leslie\u00a0G Valiant. 1990. A bridging model for parallel computation. Commun. ACM 33 8 (1990) 103\u2013111.","DOI":"10.1145\/79173.79181"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-7563-6_53"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Qiang Wang and Xiaowen Chu. 2020. GPGPU performance estimation with core and memory frequency scaling. IEEE Transactions on Parallel and Distributed Systems 31 12 (2020) 2865\u20132881.","DOI":"10.1109\/TPDS.2020.3004623"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00062"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056063"}],"event":{"name":"CF '26: Proceedings of the 23rd ACM International Conference on Computing Frontiers","location":"Catania Italy","acronym":"CF '26","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 23rd ACM International Conference on Computing Frontiers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3801487.3801808","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:13:15Z","timestamp":1782544395000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3801487.3801808"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,19]]},"references-count":26,"alternative-id":["10.1145\/3801487.3801808","10.1145\/3801487"],"URL":"https:\/\/doi.org\/10.1145\/3801487.3801808","relation":{},"subject":[],"published":{"date-parts":[[2026,5,19]]},"assertion":[{"value":"2026-06-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}