{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T03:23:32Z","timestamp":1781234612888,"version":"3.54.1"},"reference-count":33,"publisher":"World Scientific Pub Co Pte Ltd","issue":"01","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61101225"],"award-info":[{"award-number":["61101225"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Tianjin, China","award":["23JCZDJC00020"],"award-info":[{"award-number":["23JCZDJC00020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J CIRCUIT SYST COMP"],"published-print":{"date-parts":[[2025,1,15]]},"abstract":"<jats:p> In contemporary compilers, the determination of the loop unrolling factor is traditionally based on manually crafted heuristic rules. This approach heavily relies on human intuition, which limits its ability to achieve optimized performance across diverse architectures and can sometimes even lead to performance declines. Additionally, developers face challenges in achieving cross-platform compatibility, often necessitating extensive redesign efforts. In response, this study introduces a method leveraging the XGBoost algorithm to predict the optimal loop unrolling factor for compiler optimization, thereby aiming to replace human thinking with machine learning methods and standardize development processes. Initially, the study gathers data on the loop unrolling factors as determined by profile guided optimization technology, analyzes program-specific loop feature vectors and employs cross-validation, including the Pearson correlation coefficient and feature importance ranking, to construct a dataset. Subsequent use of XGBoost to train this dataset models the decision-making process for selecting the most effective loop unrolling factor. The final step involves integrating XGBoost\u2019s trained decision tree model into GCC to calculate the optimal loop unrolling factor during actual compilation. Empirical results on the RISC-V platform indicate that this new method, when tested against the SPEC CPU 2006 benchmark suite, offers up to 6.18% improvement in performance over the existing heuristic approach. It provides a new method for loop unrolling in compilers, and provides an innovative guide for the application of machine learning in compilers. <\/jats:p>","DOI":"10.1142\/s0218126625500355","type":"journal-article","created":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T03:45:57Z","timestamp":1723347957000},"source":"Crossref","is-referenced-by-count":1,"title":["Machine Learning-Driven GCC Loop Unrolling Optimization: Compiler Performance Enhancement Strategy Based on XGBoost"],"prefix":"10.1142","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7308-5113","authenticated-orcid":false,"given":"Zhaoyi","family":"Shi","sequence":"first","affiliation":[{"name":"School of Microelectronics, Tianjin University, Tianjin 300072, P. R. China"},{"name":"Processor Core Research and Development Department, Phytium Technology Co., Ltd, Changsha, Hunan 410073, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Gao","sequence":"additional","affiliation":[{"name":"Processor Core Research and Development Department, Phytium Technology Co., Ltd, Changsha, Hunan 410073, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Guan","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Tianjin University, Tianjin 300072, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"219","published-online":{"date-parts":[[2024,9,23]]},"reference":[{"key":"S0218126625500355BIB001","doi-asserted-by":"publisher","DOI":"10.1109\/CSAE.2011.5953295"},{"key":"S0218126625500355BIB002","doi-asserted-by":"publisher","DOI":"10.1145\/3237009.3237013"},{"key":"S0218126625500355BIB003","doi-asserted-by":"publisher","DOI":"10.1145\/3446804.3446849"},{"key":"S0218126625500355BIB004","doi-asserted-by":"publisher","DOI":"10.1109\/MIPRO.2014.6859582"},{"key":"S0218126625500355BIB005","doi-asserted-by":"publisher","DOI":"10.1145\/2931037.2931074"},{"key":"S0218126625500355BIB006","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71528-3_10"},{"key":"S0218126625500355BIB007","doi-asserted-by":"publisher","DOI":"10.1145\/1186736.1186737"},{"key":"S0218126625500355BIB008","first-page":"1","volume-title":"Workshop on Computer Architecture Research with RISC-V (CARRV 2020)","author":"Perotti M.","year":"2020"},{"key":"S0218126625500355BIB009","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"S0218126625500355BIB010","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2013.6494997"},{"key":"S0218126625500355BIB011","doi-asserted-by":"publisher","DOI":"10.1145\/335231.335246"},{"key":"S0218126625500355BIB012","first-page":"43","volume":"24","author":"Kisuki T.","year":"2000","journal-title":"J. Supercomput."},{"key":"S0218126625500355BIB013","author":"Wang X.","year":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"key":"S0218126625500355BIB014","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-46148-5_5"},{"key":"S0218126625500355BIB015","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11152452"},{"key":"S0218126625500355BIB016","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS.2018.00030"},{"key":"S0218126625500355BIB017","doi-asserted-by":"publisher","DOI":"10.1109\/APCSAC.2008.4625471"},{"key":"S0218126625500355BIB018","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-018-5479-x"},{"key":"S0218126625500355BIB019","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624233"},{"key":"S0218126625500355BIB020","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1984.1676404"},{"key":"S0218126625500355BIB021","first-page":"18087","volume":"33","author":"Gupta P.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0218126625500355BIB022","doi-asserted-by":"publisher","DOI":"10.1213\/ANE.0000000000002864"},{"key":"S0218126625500355BIB023","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5895"},{"key":"S0218126625500355BIB024","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2021.108276"},{"key":"S0218126625500355BIB025","author":"Yu K.","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"S0218126625500355BIB026","doi-asserted-by":"publisher","DOI":"10.1109\/SSDBM.2007.27"},{"key":"S0218126625500355BIB027","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3278668"},{"key":"S0218126625500355BIB028","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2912815"},{"key":"S0218126625500355BIB029","author":"He Q.","journal-title":"IEEE Trans. Serv. Comput."},{"key":"S0218126625500355BIB030","doi-asserted-by":"publisher","DOI":"10.1145\/349299.349314"},{"key":"S0218126625500355BIB031","doi-asserted-by":"publisher","DOI":"10.1145\/197320.197366"},{"key":"S0218126625500355BIB032","doi-asserted-by":"publisher","DOI":"10.1145\/48012.48037"},{"key":"S0218126625500355BIB033","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3387293"}],"container-title":["Journal of Circuits, Systems and Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218126625500355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T02:47:11Z","timestamp":1737514031000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0218126625500355"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,23]]},"references-count":33,"journal-issue":{"issue":"01","published-print":{"date-parts":[[2025,1,15]]}},"alternative-id":["10.1142\/S0218126625500355"],"URL":"https:\/\/doi.org\/10.1142\/s0218126625500355","relation":{},"ISSN":["0218-1266","1793-6454"],"issn-type":[{"value":"0218-1266","type":"print"},{"value":"1793-6454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,23]]},"article-number":"2550035"}}