{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:05:30Z","timestamp":1784199930597,"version":"3.55.0"},"reference-count":42,"publisher":"Association for Computing Machinery (ACM)","issue":"PLDI","license":[{"start":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T00:00:00Z","timestamp":1749772800000},"content-version":"vor","delay-in-days":3,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CNS-2312207, OAC-2417850"],"award-info":[{"award-number":["CNS-2312207, OAC-2417850"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["1R01HD108473-01"],"award-info":[{"award-number":["1R01HD108473-01"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020664","name":"USDA Rural Development","doi-asserted-by":"publisher","award":["P24-001771"],"award-info":[{"award-number":["P24-001771"]}],"id":[{"id":"10.13039\/100020664","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC52-07NA27344, ASCR SC-21"],"award-info":[{"award-number":["DE-AC52-07NA27344, ASCR SC-21"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Program. Lang."],"published-print":{"date-parts":[[2025,6,10]]},"abstract":"<jats:p>\n                    Input-centric program optimization aims to optimize code by considering the relations between program inputs and program behaviors. Despite its promise, a long-standing barrier for its adoption is the difficulty of automatically identifying critical features of complex inputs. This paper introduces a novel technique,\n                    <jats:italic toggle=\"yes\">reductive analysis through compiler-guided Large Language Models (LLMs)<\/jats:italic>\n                    , to solve the problem through a synergy between compilers and LLMs. It uses a reductive approach to overcome the scalability and other limitations of LLMs in program code analysis. The solution, for the first time, automates the identification of critical input features without heavy instrumentation or profiling, cutting the time needed for input identification by 44\u00d7 (or 450\u00d7 for local LLMs), reduced from 9.6 hours to 13 minutes (with remote LLMs) or 77 seconds (with local LLMs) on average, making input characterization possible to be integrated into the workflow of program compilations. Optimizations on those identified input features show similar or even better results than those identified by previous profiling-based methods, leading to optimizations that yield 92.6% accuracy in selecting the appropriate adaptive OpenMP parallelization decisions, and 20-30% performance improvement of serverless computing while reducing resource usage by 50-60%.\n                  <\/jats:p>","DOI":"10.1145\/3729282","type":"journal-article","created":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T16:02:27Z","timestamp":1749830547000},"page":"797-821","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Reductive Analysis with Compiler-Guided Large Language Models for Input-Centric Code Optimizations"],"prefix":"10.1145","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3649-0852","authenticated-orcid":false,"given":"Xiangwei","family":"Wang","sequence":"first","affiliation":[{"name":"North Carolina State University, Raleigh, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7078-5454","authenticated-orcid":false,"given":"Xinning","family":"Hui","sequence":"additional","affiliation":[{"name":"North Carolina State University, Raleigh, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6477-0547","authenticated-orcid":false,"given":"Chunhua","family":"Liao","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3599-8010","authenticated-orcid":false,"given":"Xipeng","family":"Shen","sequence":"additional","affiliation":[{"name":"North Carolina State University, Raleigh, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,13]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"David H Bailey Eric Barszcz John T Barton David S Browning Robert L Carter Leonardo Dagum Rod A Fatoohi Paul O Frederickson Thomas A Lasinski Rob S Schreiber et al. 1991. The NAS parallel benchmarks\u2014summary and preliminary results. In Proceedings of the 1991 ACM\/IEEE Conference on Supercomputing. 158\u2013165.","DOI":"10.1145\/125826.125925"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","unstructured":"Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 785\u2013794. doi:10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","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 preprint arXiv:2309.07062 (2023). doi:10.48550\/arXiv.2309.07062","DOI":"10.48550\/arXiv.2309.07062"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/99.660313"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_7_2","unstructured":"Daniel Sleator Davy Temperley and John Lafferty. 2016. Link Grammar. https:\/\/www.link.cs.cmu.edu\/link\/."},{"key":"e_1_3_2_8_2","unstructured":"RFV Der Wijngaart and H Jin. 2003. Nas parallel benchmarks multi-zone versions. NASA Advanced Supercomputing Division Ames Research Center USA (2003) 94035\u20131000."},{"key":"e_1_3_2_9_2","unstructured":"Dimitri van Heesch. 1997. Doxygen. https:\/\/www.doxygen.nl\/."},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Sidong Feng and Chunyang Chen. 2024. Prompting Is All You Need: Automated Android Bug Replay with Large Language Models. In Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering. 1\u201313. doi:10.1145\/3597503.3608137","DOI":"10.1145\/3597503.3608137"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Zhangyin Feng Daya Guo Duyu Tang Nan Duan Xiaocheng Feng Ming Gong Linjun Shou Bing Qin Ting Liu Daxin Jiang et al. 2020. Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155 (2020). doi:10.48550\/arXiv.2002.08155","DOI":"10.48550\/arXiv.2002.08155"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao Kangxiang Jia Jinliu Pan Yuxi Bi Yi Dai Jiawei Sun and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997 (2023). doi:10.48550\/arXiv.2312.10997","DOI":"10.48550\/arXiv.2312.10997"},{"key":"e_1_3_2_13_2","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Xinning Hui Yuanchao Xu Zhishan Guo and Xipeng Shen. 2024. ESG: Pipeline-Conscious Efficient Scheduling of DNN Workflows on Serverless Platforms with Shareable GPUs. In Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing. 42\u201355. doi:10.1145\/3625549.3658657","DOI":"10.1145\/3625549.3658657"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Yunlian Jiang Eddy Z Zhang Kai Tian Feng Mao Malcom Gethers Xipeng Shen and Yaoqing Gao. 2010. Exploiting statistical correlations for proactive prediction of program behaviors. In Proceedings of the 8th annual IEEE\/ACM international symposium on Code generation and optimization. 248\u2013256. doi:10.1145\/1772954.1772989","DOI":"10.1145\/1772954.1772989"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-40744-4_1"},{"key":"e_1_3_2_17_2","unstructured":"LangChain Inc. 2024. Map-Reduce: summarize long texts via parallelization. https:\/\/python.langchain.com\/docs\/tutorials\/summarization\/."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/FDL50818.2020.9232934"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-97759-7_3"},{"key":"e_1_3_2_20_2","unstructured":"Andreas L\u00f6bel. 1997. Optimal vehicle scheduling in public transit. Ph.D. Dissertation."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2021.07.021"},{"key":"e_1_3_2_22_2","unstructured":"Wei Ma Shangqing Liu Wenhan Wang Qiang Hu Ye Liu Cen Zhang Liming Nie and Yang Liu. 2023. The scope of chatgpt in software engineering: A thorough investigation. arXiv preprint arXiv:2305.12138 (2023)."},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Feng Mao Eddy Z Zhang and Xipeng Shen. 2009. Influence of program inputs on the selection of garbage collectors. In Proceedings of the 2009 ACM SIGPLAN\/SIGOPS international conference on Virtual execution environments. 91\u2013100. doi:10.1145\/1508293.1508307","DOI":"10.1145\/1508293.1508307"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Gleison Souza Diniz Mendon\u00e7a Chunhua Liao and Fernando Magno Quint\u00e3o Pereira. 2020. AutoParBench: a unified test framework for OpenMP-based parallelizers. In Proceedings of the 34th ACM International Conference on Supercomputing. 1\u201310. doi:10.1145\/3392717.3392744","DOI":"10.1145\/3392717.3392744"},{"key":"e_1_3_2_25_2","unstructured":"NASA Advanced Supercomputing (NAS) Division. 2024. NAS Parallel Benchmarks. https:\/\/www.nas.nasa.gov\/software\/npb.html."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","unstructured":"Erik Nijkamp Bo Pang Hiroaki Hayashi Lifu Tu Huan Wang Yingbo Zhou Silvio Savarese and Caiming Xiong. 2022. Codegen: An open large language model for code with multi-turn program synthesis. arXiv preprint arXiv:2203.13474 (2022). doi:10.48550\/arXiv.2203.13474","DOI":"10.48550\/arXiv.2203.13474"},{"key":"e_1_3_2_27_2","unstructured":"OpenWhisk. 2017. Open Source Serverless Cloud Platform. https:\/\/openwhisk.apache.org\/."},{"key":"e_1_3_2_28_2","unstructured":"Apache OpenWhisk. 2017. How OpenWhisk works. https:\/\/github.com\/apache\/openwhisk\/blob\/master\/docs\/about.md#how-openWhisk-works."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1209\/0295-5075\/17\/6\/001"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Baptiste Roziere Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing Ellen Tan Yossi Adi Jingyu Liu Tal Remez J\u00e9r\u00e9my Rapin et al. 2023. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950 (2023). doi:10.48550\/arXiv.2308.12950","DOI":"10.48550\/arXiv.2308.12950"},{"key":"e_1_3_2_31_2","unstructured":"Mohammad Shahrad Rodrigo Fonseca \u00cd\u00f1igo Goiri Gohar Chaudhry Paul Batum Jason Cooke Eduardo Laureano Colby Tresness Mark Russinovich and Ricardo Bianchini. 2020. Serverless in the wild: Characterizing and optimizing the serverless workload at a large cloud provider. In 2020 USENIX Annual Technical Conference (USENIX ATC 20). 205\u2013218."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85261-2_14"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","unstructured":"Haoye Tian Weiqi Lu Tsz On Li Xunzhu Tang Shing-Chi Cheung Jacques Klein and Tegawend\u00e9 F Bissyand\u00e9. 2023. Is ChatGPT the ultimate programming assistant\u2013how far is it? arXiv preprint arXiv:2304.11938 (2023). doi:10.48550\/arXiv.2304.11938","DOI":"10.48550\/arXiv.2304.11938"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","unstructured":"Kai Tian Yunlian Jiang Eddy Z Zhang and Xipeng Shen. 2010. An input-centric paradigm for program dynamic optimizations. In Proceedings of the ACM international conference on Object oriented programming systems languages and applications. 125\u2013139. doi:10.1145\/1869459.1869471","DOI":"10.1145\/1869459.1869471"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","unstructured":"Kai Tian Eddy Zhang and Xipeng Shen. 2011. A step towards transparent integration of input-consciousness into dynamic program optimizations. In Proceedings of the 2011 ACM international conference on Object oriented programming systems languages and applications. 445\u2013462. doi:10.1145\/2048066.2048103","DOI":"10.1145\/2048066.2048103"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","unstructured":"Mircea Trofin Yundi Qian Eugene Brevdo Zinan Lin Krzysztof Choromanski and David Li. 2021. Mlgo: a machine learning guided compiler optimizations framework. arXiv preprint arXiv:2101.04808 (2021). doi:10.48550\/arXiv.2101.04808","DOI":"10.48550\/arXiv.2101.04808"},{"key":"e_1_3_2_37_2","unstructured":"Truefoundry. 2023. Benchmaring Llama2-70B. https:\/\/www.truefoundry.com\/blog\/benchmarking-llama-2-70b\/."},{"key":"e_1_3_2_38_2","unstructured":"VideoLAN. 2013. x264. https:\/\/www.videolan.org\/developers\/x264.html."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","unstructured":"Yue Wang Weishi Wang Shafiq Joty and Steven CH Hoi. 2021. Codet5: Identifier-aware unified pre-trained encoderdecoder models for code understanding and generation. arXiv preprint arXiv:2109.00859 (2021). doi:10.48550\/arXiv.2109.00859","DOI":"10.48550\/arXiv.2109.00859"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2817118"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","unstructured":"Chunqiu Steven Xia Matteo Paltenghi Jia Le Tian Michael Pradel and Lingming Zhang. 2024. Fuzz4all: Universal fuzzing with large language models. Proc. IEEE\/ACM ICSE (2024). doi:10.1145\/3597503.3639121","DOI":"10.1145\/3597503.3639121"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","unstructured":"Eddy Z Zhang Yunlian Jiang Ziyu Guo and Xipeng Shen. 2010. Streamlining GPU applications on the fly: thread divergence elimination through runtime thread-data remapping. In Proceedings of the 24th ACM International Conference on Supercomputing. 115\u2013126. doi:10.1145\/1810085.1810104","DOI":"10.1145\/1810085.1810104"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2932931"}],"container-title":["Proceedings of the ACM on Programming Languages"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3729282","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3729282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T10:06:28Z","timestamp":1784196388000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3729282"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,10]]},"references-count":42,"journal-issue":{"issue":"PLDI","published-print":{"date-parts":[[2025,6,10]]}},"alternative-id":["10.1145\/3729282"],"URL":"https:\/\/doi.org\/10.1145\/3729282","relation":{},"ISSN":["2475-1421"],"issn-type":[{"value":"2475-1421","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,10]]},"assertion":[{"value":"2024-11-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}