{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:48:52Z","timestamp":1755794932194,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62021002"],"award-info":[{"award-number":["62021002"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3736887","type":"proceedings-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T13:32:14Z","timestamp":1754055134000},"page":"486-497","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CompilerDream: Learning a Compiler World Model for General Code Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0635-2568","authenticated-orcid":false,"given":"Chaoyi","family":"Deng","sequence":"first","affiliation":[{"name":"School of Software, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7846-053X","authenticated-orcid":false,"given":"Jialong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Software, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8448-2570","authenticated-orcid":false,"given":"Ningya","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Software, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6841-7943","authenticated-orcid":false,"given":"Jianmin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5412-9120","authenticated-orcid":false,"given":"Mingsheng","family":"Long","sequence":"additional","affiliation":[{"name":"School of Software, BNRist, Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","first-page":"265","volume-title":"TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al., 2016. TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16). USENIX Association, Savannah, GA, 265-283."},{"key":"e_1_3_2_2_2_1","volume-title":"Proceedings of the 10th International Conference on Learning Representations (ICLR '22)","author":"Anand Ankesh","year":"2022","unstructured":"Ankesh Anand, Jacob C Walker, Yazhe Li, Eszter V\u00e9rtes, Julian Schrittwieser, Sherjil Ozair, Theophane Weber, and Jessica B Hamrick. 2022. Procedural generalization by planning with self-supervised world models. In Proceedings of the 10th International Conference on Learning Representations (ICLR '22)."},{"key":"e_1_3_2_2_3_1","volume-title":"Alex Woo, and Maurice Yarrow.","author":"Bailey David","year":"1995","unstructured":"David Bailey, Tim Harris, William Saphir, Rob Van Der Wijngaart, Alex Woo, and Maurice Yarrow. 1995. The NAS parallel benchmarks 2.0. Technical Report. Technical Report NAS-95-020, NASA Ames Research Center."},{"key":"e_1_3_2_2_4_1","first-page":"3589","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems(NeurIPS '18)","author":"Ben-Nun Tal","year":"2018","unstructured":"Tal Ben-Nun, Alice Shoshana Jakobovits, and Torsten Hoefler. 2018. Neural code comprehension: a learnable representation of code semantics. In Proceedings of the 32nd International Conference on Neural Information Processing Systems(NeurIPS '18). 3589-3601."},{"key":"e_1_3_2_2_5_1","volume-title":"Workshop on Profile and Feedback-Directed Compilation","author":"Bodin Franc","year":"1998","unstructured":"Franc cois Bodin, Toru Kisuki, Peter Knijnenburg, Mike O' Boyle, and Erven Rohou. 1998. Iterative compilation in a non-linear optimisation space. In Workshop on Profile and Feedback-Directed Compilation, Paris, France."},{"key":"e_1_3_2_2_6_1","first-page":"17","volume-title":"Proceedings of the 30th International Conference on Parallel Architectures and Compilation Techniques","author":"Brauckmann Alexander","year":"2024","unstructured":"Alexander Brauckmann, Andr\u00e9s Goens, and Jeronimo Castrillon. 2024. PolyGym: Polyhedral Optimizations as an Environment for Reinforcement Learning. In Proceedings of the 30th International Conference on Parallel Architectures and Compilation Techniques(Atlanta, GA, USA) (PACT '21). IEEE Press, 17-29."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3495883"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/239912.239923"},{"key":"e_1_3_2_2_9_1","first-page":"1725","volume-title":"2012 Proceedings of the 35th International Convention MIPRO(MIPRO '12)","author":"Culjak Ivan","year":"2012","unstructured":"Ivan Culjak, David Abram, Tomislav Pribanic, Hrvoje Dzapo, and Mario Cifrek. 2012. A brief introduction to OpenCV. In 2012 Proceedings of the 35th International Convention MIPRO(MIPRO '12). 1725-1730."},{"key":"e_1_3_2_2_10_1","first-page":"2244","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML '21)","author":"Cummins Chris","year":"2021","unstructured":"Chris Cummins, Zacharias V. Fisches, Tal Ben-Nun, Torsten Hoefler, Michael F P O'Boyle, and Hugh Leather. 2021. ProGraML: A Graph-based Program Representation for Data Flow Analysis and Compiler Optimizations. In Proceedings of the 38th International Conference on Machine Learning (ICML '21). 2244-2253."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO53902.2022.9741258"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370322"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413375"},{"key":"e_1_3_2_2_14_1","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies(NAACL-HLT '19)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies(NAACL-HLT '19). Association for Computational Linguistics, 4171-4186."},{"key":"e_1_3_2_2_15_1","first-page":"1407","volume-title":"International Conference on Machine Learning (ICML '18)","author":"Espeholt Lasse","year":"2018","unstructured":"Lasse Espeholt, Hubert Soyer, Remi Munos, Karen Simonyan, Vlad Mnih, Tom Ward, Yotam Doron, Vlad Firoiu, Tim Harley, Iain Dunning, et al., 2018. Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures. In International Conference on Machine Learning (ICML '18). 1407-1416."},{"key":"e_1_3_2_2_16_1","unstructured":"Facebook. 2022. CompilerGym Leaderboard. https:\/\/github.com\/facebookresearch\/CompilerGym?tab=readme-ov-file#leaderboards. Accessed: 2024-8-09."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69338-3_17"},{"key":"e_1_3_2_2_18_1","unstructured":"Grigori Fursin Cupertino Miranda Olivier Temam Mircea Namolaru Ayal Zaks Bilha Mendelson Edwin Bonilla John Thomson Hugh Leather Chris Williams et al. 2008. MILEPOST GCC: machine learning based research compiler. In GCC summit. Ottawa Canada."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3207719.3207727"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/WWC.2001.990739"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327144.3327171"},{"key":"e_1_3_2_2_22_1","unstructured":"Tuomas Haarnoja Aurick Zhou Kristian Hartikainen George Tucker Sehoon Ha Jie Tan Vikash Kumar Henry Zhu Abhishek Gupta Pieter Abbeel and Sergey Levine. 2019. Soft Actor-Critic Algorithms and Applications. arXiv:1812.05905 [cs.LG] https:\/\/arxiv.org\/abs\/1812.05905"},{"key":"e_1_3_2_2_23_1","unstructured":"Danijar Hafner Timothy Lillicrap Jimmy Ba and Mohammad Norouzi. 2020. Dream to Control: Learning Behaviors by Latent Imagination. arXiv:1912.01603 [cs.LG] https:\/\/arxiv.org\/abs\/1912.01603"},{"key":"e_1_3_2_2_24_1","volume-title":"Mastering Atari with Discrete World Models. In International Conference on Learning Representations (ICLR '21)","author":"Hafner Danijar","year":"2021","unstructured":"Danijar Hafner, Timothy P Lillicrap, Mohammad Norouzi, and Jimmy Ba. 2021. Mastering Atari with Discrete World Models. In International Conference on Learning Representations (ICLR '21)."},{"key":"e_1_3_2_2_25_1","unstructured":"Danijar Hafner Jurgis Pasukonis Jimmy Ba and Timothy Lillicrap. 2023. Mastering diverse domains through world models. arXiv preprint arXiv:2301.04104(2023)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368826.3377928"},{"key":"e_1_3_2_2_27_1","first-page":"70","volume-title":"Proceedings of Machine Learning and Systems(MLSys '20)","author":"Haj-Ali Ameer","year":"2020","unstructured":"Ameer Haj-Ali, Qijing (Jenny) Huang, William S. Moses, John Xiang, 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(MLSys '20). 70-81."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2008.4541637"},{"key":"e_1_3_2_2_29_1","volume-title":"Distributed Prioritized Experience Replay. In International Conference on Learning Representations (ICLR '18)","author":"Horgan Dan","year":"2018","unstructured":"Dan Horgan, John Quan, David Budden, Gabriel Barth-Maron, Matteo Hessel, Hado van Hasselt, and David Silver. 2018. Distributed Prioritized Experience Replay. In International Conference on Learning Representations (ICLR '18)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS55109.2022.00012"},{"key":"e_1_3_2_2_31_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems(NeurIPS '19)","author":"Janner Michael","year":"2019","unstructured":"Michael Janner, Justin Fu, Marvin Zhang, and Sergey Levine. 2019. When to trust your model: Model-based policy optimization. In Proceedings of the 33rd International Conference on Neural Information Processing Systems(NeurIPS '19). Article 1122."},{"key":"e_1_3_2_2_32_1","first-page":"4015","volume-title":"Segment Anything. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV '23)","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollar, and Ross Girshick. 2023. Segment Anything. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV '23). 4015-4026."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2384616.2384628"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"e_1_3_2_2_35_1","first-page":"308","volume-title":"ACM Transactions on Mathematical Software (TOMS '79)","volume":"5","author":"Lawson Chuck L","year":"1979","unstructured":"Chuck L Lawson, Richard J. Hanson, David R Kincaid, and Fred T. Krogh. 1979. Basic linear algebra subprograms for Fortran usage. ACM Transactions on Mathematical Software (TOMS '79), Vol. 5, 3 (1979), 308-323."},{"key":"e_1_3_2_2_36_1","first-page":"1","article-title":"Machine learning in compilers: Past, present and future. In 2020 Forum for Specification and Design Languages (FDL)","author":"Leather Hugh","year":"2020","unstructured":"Hugh Leather and Chris Cummins. 2020. Machine learning in compilers: Past, present and future. In 2020 Forum for Specification and Design Languages (FDL). IEEE, 1-8.","journal-title":"IEEE"},{"key":"e_1_3_2_2_37_1","first-page":"1","article-title":"A path towards autonomous machine intelligence version 0.9. 2, 2022-06-27","volume":"62","author":"LeCun Yann","year":"2022","unstructured":"Yann LeCun. 2022. A path towards autonomous machine intelligence version 0.9. 2, 2022-06-27. Open Review, Vol. 62, 1 (2022), 1-62. https:\/\/openreview.net\/pdf?id=BZ5a1r-kVsf","journal-title":"Open Review"},{"key":"e_1_3_2_2_38_1","volume-title":"International Conference on Learning Representations (ICLR '24)","author":"Lee Vint","year":"2024","unstructured":"Vint Lee, Pieter Abbeel, and Youngwoon Lee. 2024. DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing. In International Conference on Learning Representations (ICLR '24)."},{"key":"e_1_3_2_2_39_1","first-page":"1092","volume-title":"Science","volume":"378","author":"Li Yujia","year":"2022","unstructured":"Yujia Li, David Choi, Junyoung Chung, Nate Kushman, Julian Schrittwieser, R\u00e9mi Leblond, Tom Eccles, James Keeling, Felix Gimeno, Agustin Dal Lago, et al., 2022. Competition-level code generation with alphacode. Science, Vol. 378, 6624 (2022), 1092-1097."},{"key":"e_1_3_2_2_40_1","first-page":"3053","volume-title":"RLlib: Abstractions for Distributed Reinforcement Learning. In International Conference on Machine Learning (ICML '18)","volume":"80","author":"Liang Eric","year":"2018","unstructured":"Eric Liang, Richard Liaw, Robert Nishihara, Philipp Moritz, Roy Fox, Ken Goldberg, Joseph E. Gonzalez, Michael I. Jordan, and Ion Stoica. 2018. RLlib: Abstractions for Distributed Reinforcement Learning. In International Conference on Machine Learning (ICML '18), Vol. 80. 3053-3062."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3619263"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669121"},{"key":"e_1_3_2_2_43_1","volume-title":"HarmonyDream: Task Harmonization Inside World Models. In International Conference on Machine Learning (ICML '24)","author":"Ma Haoyu","year":"2024","unstructured":"Haoyu Ma, Jialong Wu, Ningya Feng, Chenjun Xiao, Dong Li, HAO Jianye, Jianmin Wang, and Mingsheng Long. 2024. HarmonyDream: Task Harmonization Inside World Models. In International Conference on Machine Learning (ICML '24)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/LLVMHPCHiPar51896.2020.00006"},{"key":"e_1_3_2_2_45_1","volume-title":"Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL. In International Conference on Learning Representations (ICLR '22)","author":"Mazoure Bogdan","year":"2022","unstructured":"Bogdan Mazoure, Ahmed M Ahmed, R Devon Hjelm, Andrey Kolobov, and Patrick MacAlpine. 2022. Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL. In International Conference on Learning Representations (ICLR '22)."},{"key":"e_1_3_2_2_46_1","first-page":"2430","volume-title":"International Conference on Machine Learning (ICML '17)","author":"Mirhoseini Azalia","year":"2017","unstructured":"Azalia Mirhoseini, Hieu Pham, Quoc V Le, Benoit Steiner, Rasmus Larsen, Yuefeng Zhou, Naveen Kumar, Mohammad Norouzi, Samy Bengio, and Jeff Dean. 2017. Device placement optimization with reinforcement learning. In International Conference on Machine Learning (ICML '17). 2430-2439."},{"key":"e_1_3_2_2_47_1","volume-title":"International Conference on Machine Learning (ICML '16)","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous methods for deep reinforcement learning. In International Conference on Machine Learning (ICML '16). 1928-1937."},{"key":"e_1_3_2_2_48_1","first-page":"529","volume-title":"Nature","volume":"518","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al., 2015. Human-level control through deep reinforcement learning. Nature, Vol. 518, 7540 (2015), 529-533."},{"key":"e_1_3_2_2_49_1","first-page":"8748","volume-title":"International Conference on Machine Learning (ICML '21)","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning (ICML '21). 8748-8763."},{"key":"e_1_3_2_2_50_1","first-page":"604","volume-title":"Nature","volume":"588","author":"Schrittwieser Julian","year":"2020","unstructured":"Julian Schrittwieser, Ioannis Antonoglou, Thomas Hubert, Karen Simonyan, Laurent Sifre, Simon Schmitt, Arthur Guez, Edward Lockhart, Demis Hassabis, Thore Graepel, et al., 2020. Mastering atari, go, chess and shogi by planning with a learned model. Nature, Vol. 588, 7839 (2020), 604-609."},{"key":"e_1_3_2_2_51_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arXiv:1707.06347 [cs.LG] https:\/\/arxiv.org\/abs\/1707.06347"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/LLVM-HPC56686.2022.00007"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781141"},{"volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","key":"e_1_3_2_2_54_1","unstructured":"Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3617555.3617874"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2003.1191546"},{"key":"e_1_3_2_2_57_1","unstructured":"Mircea Trofin Yundi Qian Eugene Brevdo Zinan Lin Krzysztof Choromanski and David Li. 2021. MLGO: a Machine Learning Guided Compiler Optimizations Framework. arXiv:2101.04808 [cs.PL] https:\/\/arxiv.org\/abs\/2101.04808"},{"key":"e_1_3_2_2_58_1","volume-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning","author":"Williams Ronald J","year":"1992","unstructured":"Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, Vol. 8 (1992), 229-256."},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/1993498.1993532"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Toronto ON Canada","acronym":"KDD '25"},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3736887","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T14:35:44Z","timestamp":1755354944000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3736887"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":59,"alternative-id":["10.1145\/3711896.3736887","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3736887","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}