{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:31:26Z","timestamp":1783096286250,"version":"3.54.6"},"reference-count":105,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2024YFB4505603"],"award-info":[{"award-number":["2024YFB4505603"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Jiangsu Provincial Key R&D Program","award":["BG2024028"],"award-info":[{"award-number":["BG2024028"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U23B2020, 62090024, 62302479, and 62232015"],"award-info":[{"award-number":["U23B2020, 62090024, 62302479, and 62232015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>Compiler backends are tasked with generating executable machine code for various processors. As the diversity of processors continues to grow, it is imperative for programmers to tailor specific compiler backends to accommodate each one. However, compiler backend development remains a labor-intensive and time-consuming process, with limited automation tools available. Although large language models (LLMs) have demonstrated strong abilities in code completion and code generation tasks, the lack of appropriate datasets for compiler backend development limits the application of LLMs in this field.<\/jats:p>\n                  <jats:p>\n                    In this article, we introduce ComBack++, a multilingual dataset covering C\/C++, machine description, and TableGen, with 184 backends from GCC and LLVM, four backend-specific tasks. Based on ComBack++, we present BePilot, a compiler backend-specific LLM available in two sizes: BePilot-1.5B and BePilot-7B. We also introduce\n                    <jats:sc>CB-Retriever<\/jats:sc>\n                    , a retriever that constructs few-shot prompts via in-context learning to improve vanilla LLM performance in resource-constrained settings. Experimental results show that BePilot-1.5B and BePilot-7B achieve significantly higher accuracy across four tasks in ComBack++ compared to 12 baseline LLMs (125M\u201334B parameters). In addition,\n                    <jats:sc>CB-Retriever<\/jats:sc>\n                    consistently boosts the accuracy of six mainstream LLMs. Both BePilot-1.5B and BePilot-7B, as well as vanilla LLMs augmented with\n                    <jats:sc>CB-Retriever<\/jats:sc>\n                    , outperform the traditional manual compiler backend development approach (Fork-Flow) in efficiency across all four tasks in ComBack++. Furthermore, human evaluation by four experienced compiler backend developers confirms that BePilot not only improves development efficiency over Fork-Flow but also surpasses commercial AI programming assistants such as GPT-4o-mini and Gemini2-Flash in terms of code quality. These findings confirm that BePilot and\n                    <jats:sc>CB-Retriever<\/jats:sc>\n                    can substantially enhance compiler backend development efficiency.\n                  <\/jats:p>","DOI":"10.1145\/3764585","type":"journal-article","created":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T14:57:43Z","timestamp":1756393063000},"page":"1-45","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["BePilot: An AI Programming Assistant for Compiler Backend Development"],"prefix":"10.1145","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7814-7523","authenticated-orcid":false,"given":"Ming","family":"Zhong","sequence":"first","affiliation":[{"name":"SKLP, Institute of Computing Technology, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8263-7876","authenticated-orcid":false,"given":"Xin","family":"Sun","sequence":"additional","affiliation":[{"name":"SKLP, Institute of Computing Technology, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9723-9410","authenticated-orcid":false,"given":"Fang","family":"Lv","sequence":"additional","affiliation":[{"name":"SKLP, Institute of Computing Technology, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6497-221X","authenticated-orcid":false,"given":"Lulin","family":"Wang","sequence":"additional","affiliation":[{"name":"SKLP, Institute of Computing Technology, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0972-4549","authenticated-orcid":false,"given":"Hongna","family":"Geng","sequence":"additional","affiliation":[{"name":"Hygon Information Technology Co., Ltd, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5130-924X","authenticated-orcid":false,"given":"Lei","family":"Qiu","sequence":"additional","affiliation":[{"name":"SKLP, Institute of Computing Technology, CAS, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2491-7679","authenticated-orcid":false,"given":"Huimin","family":"Cui","sequence":"additional","affiliation":[{"name":"SKLP, Institute of Computing Technology, CAS, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2909-7750","authenticated-orcid":false,"given":"Xiaobing","family":"Feng","sequence":"additional","affiliation":[{"name":"SKLP, Institute of Computing Technology, CAS, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,13]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"01-ai. 2024. Meet Yi-Coder: A Small But Mighty LLM for Code. Retrieved from https:\/\/github.com\/01-ai\/Yi-Coder"},{"key":"e_1_3_2_3_2","unstructured":"Alibaba. 2025. XuanTie. Retrieved from https:\/\/www.xrvm.com"},{"key":"e_1_3_2_4_2","unstructured":"Jordi Armengol-Estap\u00e9 and Michael F. P. O\u2019Boyle. 2021. Learning C to x86 translation: An experiment in neural compilation. arXiv:2108.07639. Retrieved from https:\/\/arxiv.org\/abs\/2108.07639"},{"key":"e_1_3_2_5_2","unstructured":"Jordi Armengol-Estap\u00e9 Jackson Woodruff Chris Cummins and Michael F. P. O\u2019Boyle. 2023. SLaDe: A portable small language model decompiler for optimized assembler. arXiv:2305.12520. Retrieved from https:\/\/arxiv.org\/abs\/2305.12520"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1002\/spe.2106"},{"key":"e_1_3_2_7_2","unstructured":"Alexander Brauckmann Andr\u00e9s Goens and Jer\u00f3nimo Castrill\u00f3n. 2021. A reinforcement learning environment for polyhedral optimizations. arXiv:2104.13732. Retrieved from https:\/\/arxiv.org\/abs\/2104.13732"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/996566.996763"},{"key":"e_1_3_2_9_2","first-page":"1877","volume-title":"Advances in Neural Information Processing Systems","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. In Advances in Neural Information Processing Systems. H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877\u20131901. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00110"},{"key":"e_1_3_2_11_2","unstructured":"Liguo Chen Qi Guo Hongrui Jia Zhengran Zeng Xin Wang Yijiang Xu Jian Wu Yidong Wang Qing Gao Jindong Wang et al. 2025. A survey on evaluating large language models in code generation tasks. arXiv:2408.16498. Retrieved from https:\/\/arxiv.org\/abs\/2408.16498"},{"key":"e_1_3_2_12_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde de Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman et al. 2021. Evaluating large language models trained on code. arXiv:2107.03374. Retrieved from https:\/\/arxiv.org\/abs\/2107.03374"},{"key":"e_1_3_2_13_2","unstructured":"Chen Chung-Shu. 2025. Tutorial: Creating an LLVM Backend for the Cpu0 Architecture. Retrieved from https:\/\/jonathan2251.github.io\/lbd\/llvmstructure.html"},{"key":"e_1_3_2_14_2","unstructured":"Visual Studio Code. 2024. Visual Studio Code. Retrieved from https:\/\/code.visualstudio.com\/"},{"key":"e_1_3_2_15_2","unstructured":"Continue. 2024. Continue. Retrieved from https:\/\/docs.continue.dev\/"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2017.24"},{"key":"e_1_3_2_17_2","unstructured":"Chris Cummins Volker Seeker Dejan Grubisic Mostafa Elhoushi Youwei Liang Baptiste Roziere Jonas Gehring Fabian Gloeckle Kim Hazelwood Gabriel Synnaeve et al. 2023. Large language models for compiler optimization. arXiv:2309.07062. Retrieved from https:\/\/arxiv.org\/abs\/2309.07062"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708493.3712691"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370322"},{"key":"e_1_3_2_20_2","unstructured":"Google Deepmind. 2025. Google Gemini. Retrieved from https:\/\/gemini.google.com\/app"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639219"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/1134650.1134671"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1136800"},{"issue":"4","key":"e_1_3_2_26_2","article-title":"Collective optimization: A practical collaborative approach","volume":"7","author":"Fursin Grigori","year":"2011","unstructured":"Grigori Fursin and Olivier Temam. 2011. Collective optimization: A practical collaborative approach. ACM Transactions on Architecture and Code Optimization 7, 4, Article 20 (Dec. 2011), 29 pages. Retrieved from https:\/\/doi.org\/10.1145\/1880043.1880047","journal-title":"ACM Transactions on Architecture and Code Optimization"},{"key":"e_1_3_2_27_2","unstructured":"GCC. 2024. GNU Compiler Collection. Retrieved from https:\/\/gcc.gnu.org"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3608134"},{"key":"e_1_3_2_29_2","unstructured":"Aiden Grossman Ludger Paehler Konstantinos Parasyris Tal Ben-Nun Jacob Hegna William Moses Jose M. Monsalve Diaz Trofin Mircea and Doerfert Johannes. 2023. ComPile: A Large IR dataset from production sources. arXiv:2309.15432. Retrieved from https:\/\/arxiv.org\/abs\/2309.15432"},{"key":"e_1_3_2_30_2","unstructured":"Dejan Grubisic Chris Cummins Volker Seeker and Hugh Leather. 2024. Compiler generated feedback for large language models. arXiv:2403.14714. Retrieved from https:\/\/arxiv.org\/abs\/2403.14714"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3642970.3655831"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"e_1_3_2_33_2","volume-title":"Proceedings of the Ninth International Conference on Learning Representations (ICLR \u201921)","author":"Guo Daya","year":"2021","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, et al. 2021. GraphCodeBERT: Pre-training code representations with data flow. In Proceedings of the Ninth International Conference on Learning Representations (ICLR \u201921), OpenReview.net, 18 pages. Retrieved from https:\/\/openreview.net\/forum?id=jLoC4ez43PZ"},{"key":"e_1_3_2_34_2","unstructured":"Daya Guo Qihao Zhu Dejian Yang Zhenda Xie Kai Dong Wentao Zhang Guanting Chen Xiao Bi Y. Wu Y. K. Li et al. 2024. DeepSeek-Coder: When the large language model meets programming \u2013 The rise of code intelligence. arXiv:2401.14196. Retrieved from https:\/\/arxiv.org\/abs\/2401.14196"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368826.3377928"},{"key":"e_1_3_2_36_2","first-page":"70","volume-title":"Proceedings of Machine Learning and Systems","volume":"2","author":"Haj-Ali Ameer","year":"2020","unstructured":"Ameer Haj-Ali, Qijing (Jenny) Huang, John Xiang, William Moses, Krste Asanovic, John Wawrzynek, and Ion Stoica. 2020. AutoPhase: Juggling HLS phase orderings in random forests with deep reinforcement learning. In Proceedings of Machine Learning and Systems. I. Dhillon, D. Papailiopoulos, and V. Sze (Eds.), Vol. 2, mlsys.org, 70\u201381. Retrieved from https:\/\/proceedings.mlsys.org\/paper\/2020\/file\/4e732ced3463d06de0ca9a15b6153677-Paper.pdf"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/307418.307549"},{"key":"e_1_3_2_38_2","unstructured":"Yiyang Hao Ge Li Yongqiang Liu Xiaowei Miao He Zong Siyuan Jiang Yang Liu and He Wei. 2022. AixBench: A code generation benchmark dataset. arXiv:220613179. Retrieved from https:\/\/arxiv.org\/abs\/2206.13179"},{"issue":"1","key":"e_1_3_2_39_2","article-title":"A SIMD optimization framework for retargetable compilers","volume":"6","author":"Hohenauer Manuel","year":"2009","unstructured":"Manuel Hohenauer, Felix Engel, Rainer Leupers, Gerd Ascheid, and Heinrich Meyr. 2009. A SIMD optimization framework for retargetable compilers. ACM Transactions on Architecture and Code Optimization 6, 1, Article 2 (Apr. 2009), 27 pages. Retrieved from https:\/\/doi.org\/10.1145\/1509864.1509866","journal-title":"ACM Transactions on Architecture and Code Optimization"},{"key":"e_1_3_2_40_2","volume-title":"Proceedings of the International Conference on Learning Representations. OpenReview.net","author":"Hu Edward J.","year":"2022","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In Proceedings of the International Conference on Learning Representations. OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_41_2","unstructured":"Dong Huang Jie M. Zhang Michael Luck Qingwen Bu Yuhao Qing and Heming Cui. 2024. AgentCoder: Multi-agent-based code generation with iterative testing and optimisation. arXiv:2312.13010. Retrieved from https:\/\/arxiv.org\/abs\/2312.13010"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00181"},{"key":"e_1_3_2_43_2","unstructured":"Binyuan Hui Jian Yang Zeyu Cui Jiaxi Yang Dayiheng Liu Lei Zhang Tianyu Liu Jiajun Zhang Bowen Yu Kai Dang et al. 2024. Qwen2.5-Coder technical report. arXiv:2409.12186. Retrieved from https:\/\/arxiv.org\/abs\/2409.12186"},{"key":"e_1_3_2_44_2","unstructured":"Hamel Husain Ho-Hsiang Wu Tiferet Gazit Miltiadis Allamanis and Marc Brockschmidt. 2019. CodeSearchNet challenge: Evaluating the state of semantic code search. arXiv:1909.09436. Retrieved from https:\/\/arxiv.org\/abs\/1909.09436"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1192"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454038"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037698"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00179"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3671016.3674819"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3691620.3695331"},{"issue":"12","key":"e_1_3_2_51_2","doi-asserted-by":"crossref","first-page":"3369","DOI":"10.1109\/TSE.2024.3486195","article-title":"\\(\\mathbf{A^{3}}\\) A3-CodGen: A repository-level code generation framework for code reuse with local-aware, global-aware, and third-party-library-aware","volume":"50","author":"Liao Dianshu","year":"2024","unstructured":"Dianshu Liao, Shidong Pan, Xiaoyu Sun, Xiaoxue Ren, Qing Huang, Zhenchang Xing, Huan Jin, and Qinying Li. 2024. \\(\\mathbf{A^{3}}\\) A3-CodGen: A repository-level code generation framework for code reuse with local-aware, global-aware, and third-party-library-aware. IEEE Transactions on Software Engineering 50, 12 (Dec. 2024), 3369\u20133384. Retrieved from https:\/\/doi.org\/10.1109\/TSE.2024.3486195","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_2_52_2","first-page":"74","volume-title":"Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out. Association for Computational Linguistics, 74\u201381. Retrieved from https:\/\/aclanthology.org\/W04-1013"},{"issue":"1","key":"e_1_3_2_53_2","article-title":"Iterative compilation optimization based on metric learning and collaborative filtering","volume":"19","author":"Liu Hongzhi","year":"2021","unstructured":"Hongzhi Liu, Jie Luo, Ying Li, and Zhonghai Wu. 2021. Iterative compilation optimization based on metric learning and collaborative filtering. ACM Transactions on Architecture and Code Optimization 19, 1, Article 2 (Dec. 2021), 25 pages. Retrieved from https:\/\/doi.org\/10.1145\/3480250","journal-title":"ACM Transactions on Architecture and Code Optimization"},{"key":"e_1_3_2_54_2","unstructured":"LLVM. 2024. The LLVM Compiler Infrastructure Project. Retrieved from http:\/\/llvm.org\/"},{"key":"e_1_3_2_55_2","unstructured":"LLVM. 2024. The LLVM Target-Independent Code Generator. Retrieved from https:\/\/llvm.org\/docs\/CodeGenerator.html"},{"key":"e_1_3_2_56_2","unstructured":"LLVM. 2024. Writing an LLVM Backend. Retrieved from https:\/\/llvm.org\/docs\/WritingAnLLVMBackend.html"},{"key":"e_1_3_2_57_2","unstructured":"Shuai Lu Daya Guo Shuo Ren Junjie Huang Alexey Svyatkovskiy Ambrosio Blanco Colin B. Clement Dawn Drain Daxin Jiang Duyu Tang et al. 2021. CodeXGLUE: A machine learning benchmark dataset for code understanding and generation. arXiv:2102.04664. Retrieved from https:\/\/arxiv.org\/abs\/2102.04664"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639213"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378525"},{"key":"e_1_3_2_60_2","unstructured":"Rahim Mammadli Ali Jannesari and Felix Wolf. 2020. Static Neural Compiler Optimization via Deep Reinforcement Learning. Retrieved from https:\/\/arxiv.org\/abs\/2008.08951"},{"key":"e_1_3_2_61_2","first-page":"587","volume-title":"Proceedings of the 21st Design Automation Conference Proceedings","author":"Marwedel P.","year":"1984","unstructured":"P. Marwedel. 1984. The MIMOLA design system: Tools for the design of digital processors. In Proceedings of the 21st Design Automation Conference Proceedings. IEEE Computer Society, 587\u2013593. DOI: https:\/\/doi.org\/10.1109\/DAC.1984.1585857"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3183297"},{"key":"e_1_3_2_63_2","first-page":"7908","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML \u201919)","author":"Mendis Charith","year":"2019","unstructured":"Charith Mendis, Alex Renda, Saman Amarasinghe, and Michael Carbin. 2019. IThemal: Accurate, portable and fast basic block throughput estimation using deep neural networks. In Proceedings of the 36th International Conference on Machine Learning (ICML \u201919). International Machine Learning Society (IMLS), 7908\u20137918."},{"key":"e_1_3_2_64_2","first-page":"4505","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Mendis Charith","year":"2019","unstructured":"Charith Mendis, Alex Renda, Saman Amarasinghe, and Michael Carbin. 2019. Ithemal: Accurate, portable and fast basic block throughput estimation using deep neural networks. In Proceedings of the International Conference on Machine Learning. PMLR, 4505\u20134515."},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00072"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00084"},{"key":"e_1_3_2_67_2","unstructured":"Nvidia. 2024. NVIDIA NGC. Retrieved from https:\/\/www.nvidia.com\/en-us\/gpu-cloud\/"},{"key":"e_1_3_2_68_2","unstructured":"Ollama. 2024. Ollama: Get Up and Running with Large Language Models. Retrieved from https:\/\/github.com\/ollama\/ollama"},{"key":"e_1_3_2_69_2","unstructured":"OpenAI. 2022. ChatGPT: Optimizing Language Models for Dialogue. Retrieved from https:\/\/openai.com\/blog\/chatgpt\/"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO53902.2022.9741263"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/309847.310101"},{"key":"e_1_3_2_72_2","doi-asserted-by":"crossref","unstructured":"Qiwei Peng Yekun Chai and Xuhong Li. 2024. HumanEval-XL: A multilingual code generation benchmark for cross-lingual natural language generalization. arXiv:2402.16694. Retrieved from https:\/\/arxiv.org\/abs\/2402.16694","DOI":"10.63317\/2zjsm6sdd5yo"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643991.3644878"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3660793"},{"issue":"10","key":"e_1_3_2_75_2","first-page":"1691","article-title":"Neural network-based performance prediction for task migration on S-NUCA many-cores","volume":"70","author":"Rapp Martin","year":"2021","unstructured":"Martin Rapp, Anuj Pathania, Tulika Mitra, and J\u00f6rg Henkel. 2021. Neural network-based performance prediction for task migration on S-NUCA many-cores. IEEE Transactions on Computers 70, 10 (2021), 1691\u20131704. Retrieved from https:\/\/doi.org\/10.1109\/TC.2020.3023022","journal-title":"IEEE Transactions on Computers"},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2016.27"},{"key":"e_1_3_2_77_2","unstructured":"Shuo Ren Daya Guo Shuai Lu Long Zhou Shujie Liu Duyu Tang Neel Sundaresan Ming Zhou Ambrosio Blanco and Shuai Ma. 2020. CodeBLEU: A method for automatic evaluation of code synthesis. arXiv:200910297. Retrieved from https:\/\/arxiv.org\/abs\/2009.10297"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3385412.3385995"},{"key":"e_1_3_2_79_2","unstructured":"Baptiste Rozi\u00e8re Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing Ellen Tan Yossi Adi Jingyu Liu Romain Sauvestre Tal Remez et al. 2024. Code Llama: Open foundation models for code. arXiv:2308.12950. Retrieved from https:\/\/arxiv.org\/abs\/2308.12950"},{"key":"e_1_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.143"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696443.3708929"},{"key":"e_1_3_2_82_2","unstructured":"CppCheck Team. 2024. CppCheck: A Tool for Static C\/C++ Code Analysis. Retrieved from https:\/\/cppcheck.sourceforge.io\/"},{"key":"e_1_3_2_83_2","unstructured":"CodeGemma Team Heri Zhao Jeffrey Hui Joshua Howland Nam Nguyen Siqi Zuo Andrea Hu Christopher A. Choquette-Choo Jingyue Shen Joe Kelley et al. 2024. CodeGemma: Open code models based on gemma. arXiv:2406.11409. Retrieved from https:\/\/arxiv.org\/abs\/2406.11409"},{"key":"e_1_3_2_84_2","unstructured":"Tree-Sitter. 2024. Tree-Sitter Introduction. Retrieved from https:\/\/tree-sitter.github.io\/tree-sitter"},{"key":"e_1_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446753"},{"key":"e_1_3_2_86_2","doi-asserted-by":"publisher","DOI":"10.1145\/3640537.3641580"},{"key":"e_1_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.1145\/3578360.3580273"},{"key":"e_1_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549113"},{"key":"e_1_3_2_89_2","doi-asserted-by":"crossref","unstructured":"Yue Wang Hung Le Akhilesh Deepak Gotmare Nghi D. Q. Bui Junnan Li and Steven C. H. Hoi. 2023. CodeT5+: Open code large language models for code understanding and generation. arXiv:2305.07922. Retrieved from https:\/\/arxiv.org\/abs\/2305.07922","DOI":"10.18653\/v1\/2023.emnlp-main.68"},{"key":"e_1_3_2_90_2","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Wang Yue","year":"2021","unstructured":"Yue Wang, Weishi Wang, Shafiq Joty, and Steven C. H. Hoi. 2021. CodeT5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics."},{"key":"e_1_3_2_91_2","first-page":"165","volume-title":"Proceedings of the 2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE)","author":"Wang Yanlin","year":"2025","unstructured":"Yanlin Wang, Yanli Wang, Daya Guo, Jiachi Chen, Ruikai Zhang, Yuchi Ma, and Zibin Zheng. 2025. RLCoder: Reinforcement learning for repository-level code completion. In Proceedings of the 2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE). IEEE Computer Society, 165\u2013177. Retrieved from https:\/\/doi.ieeecomputersociety.org\/10.1109\/ICSE55347.2025.00014"},{"issue":"4","key":"e_1_3_2_92_2","article-title":"Automatic and portable mapping of data parallel programs to OpenCL for GPU-based heterogeneous systems","volume":"11","author":"Wang Zheng","year":"2014","unstructured":"Zheng Wang, Dominik Grewe, and Michael F. P. O\u2019boyle. 2014. Automatic and portable mapping of data parallel programs to OpenCL for GPU-based heterogeneous systems. ACM Transactions on Architecture and Code Optimization 11, 4, Article 42 (Dec. 2014), 26 pages. Retrieved from https:\/\/doi.org\/10.1145\/2677036","journal-title":"ACM Transactions on Architecture and Code Optimization"},{"key":"e_1_3_2_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00191"},{"key":"e_1_3_2_94_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575742"},{"key":"e_1_3_2_95_2","volume-title":"Proceedings of the 41st International Conference on Machine Learning (ICML \u201924)","author":"Wu Di","year":"2024","unstructured":"Di Wu, Wasi Uddin Ahmad, Dejiao Zhang, Murali Krishna Ramanathan, and Xiaofei Ma. 2024. REPOFORMER: Selective retrieval for repository-level code completion. In Proceedings of the 41st International Conference on Machine Learning (ICML \u201924). JMLR.org, Article 2183, 21 pages."},{"key":"e_1_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663815"},{"key":"e_1_3_2_97_2","doi-asserted-by":"publisher","DOI":"10.1145\/3717061"},{"key":"e_1_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623316"},{"key":"e_1_3_2_99_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575737"},{"key":"e_1_3_2_100_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.151"},{"key":"e_1_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.737"},{"key":"e_1_3_2_102_2","unstructured":"Jiasheng Zheng Boxi Cao Zhengzhao Ma Ruotong Pan Hongyu Lin Yaojie Lu Xianpei Han and Le Sun. 2024. Beyond correctness: Benchmarking multi-dimensional code generation for large language models. arXiv:2407.11470. Retrieved from https:\/\/arxiv.org\/abs\/2407.11470"},{"key":"e_1_3_2_103_2","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","volume":"1","author":"Zheng Lianmin","year":"2021","unstructured":"Lianmin Zheng, Ruochen Liu, Junru Shao, Tianqi Chen, Joseph Gonzalez, Ion Stoica, and Ameer Haj-Ali. 2021. TenSet: A large-scale program performance dataset for learned tensor compilers. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks. J. Vanschoren and S. Yeung (Eds.), Vol. 1, Curran. Retrieved from https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/a684eceee76fc522773286a895bc8436-Paper-round1.pdf"},{"key":"e_1_3_2_104_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER64311.2025.00037"},{"key":"e_1_3_2_105_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696443.3708931"},{"key":"e_1_3_2_106_2","unstructured":"Xin Zhou Kisub Kim Ting Zhang Martin Weyssow Luis F. Gomes Guang Yang and David Lo. 2025. An LLM-as-judge metric for bridging the gap with human evaluation in SE tasks. arXiv:250520854. Retrieved from https:\/\/arxiv.org\/abs\/2505.20854"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3764585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:28:00Z","timestamp":1778693280000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3764585"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,13]]},"references-count":105,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3764585"],"URL":"https:\/\/doi.org\/10.1145\/3764585","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,13]]},"assertion":[{"value":"2025-03-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}