{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:58:55Z","timestamp":1750309135228,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T00:00:00Z","timestamp":1726012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Amazon Research Award","award":[""],"award-info":[{"award-number":[""]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,9,11]]},"DOI":"10.1145\/3650212.3652143","type":"proceedings-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T11:44:25Z","timestamp":1726055065000},"page":"479-490","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated Deep Learning Optimization via DSL-Based Source Code Transformation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9298-0925","authenticated-orcid":false,"given":"Ruixin","family":"Wang","sequence":"first","affiliation":[{"name":"Purdue University, West Lafayette, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0136-3204","authenticated-orcid":false,"given":"Minghai","family":"Lu","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9298-6254","authenticated-orcid":false,"given":"Cody Hao","family":"Yu","sequence":"additional","affiliation":[{"name":"BosonAI, Santa Clara, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2358-805X","authenticated-orcid":false,"given":"Yi-Hsiang","family":"Lai","sequence":"additional","affiliation":[{"name":"Amazon Web Services, Seattle, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5468-9347","authenticated-orcid":false,"given":"Tianyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. Apex (A PyTorch Extension) \u2014 Apex 0.1.0 documentation. https:\/\/nvidia.github.io\/apex\/"},{"key":"e_1_3_2_1_2_1","unstructured":"2023. comaniac\/epoi: Benchmark PyTorch Custom Operators. https:\/\/github.com\/comaniac\/epoi"},{"key":"e_1_3_2_1_3_1","unstructured":"2023. comby-tools\/comby: A code rewrite tool for structural search and replace that supports ~ every language.. https:\/\/github.com\/comby-tools\/comby"},{"key":"e_1_3_2_1_4_1","unstructured":"2023. Deepspeed. https:\/\/www.deepspeed.ai\/"},{"key":"e_1_3_2_1_5_1","unstructured":"2023. google-research\/python-graphs: A static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.. https:\/\/github.com\/google-research\/python-graphs"},{"key":"e_1_3_2_1_6_1","unstructured":"2023. Hugging Face \u2013 The AI community building the future.. https:\/\/huggingface.co\/"},{"key":"e_1_3_2_1_7_1","unstructured":"2023. huggingface\/transformers: Transformers: State-of-the-art Machine Learning for Pytorch TensorFlow and JAX.. https:\/\/github.com\/huggingface\/transformers"},{"key":"e_1_3_2_1_8_1","unstructured":"2023. PyTorch. https:\/\/www.pytorch.org"},{"key":"e_1_3_2_1_9_1","unstructured":"2023. Slapo: A Schedule Language for Large Model Training. https:\/\/github.com\/awslabs\/slapo original-date: 2023-01-12T00:31:57Z"},{"key":"e_1_3_2_1_10_1","unstructured":"2023. Triton. https:\/\/github.com\/openai\/triton original-date: 2014-08-30T17:07:16Z"},{"key":"e_1_3_2_1_11_1","unstructured":"2023. What is xFormers? | xFormers 0.0.23 documentation. https:\/\/facebookresearch.github.io\/xformerswhat_is_xformers.html"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"2024. Adopter: Automated Deep Learning Optimization via DSL-based Source Code Transformation. Zenodo. https:\/\/doi.org\/10.5281\/zenodo.10901816 10.5281\/zenodo.10901816","DOI":"10.5281\/zenodo.10901816"},{"key":"e_1_3_2_1_13_1","volume-title":"Cheng Li, Du Li, Elton Zheng, Jeff Rasley, Shaden Smith, Olatunji Ruwase, and Yuxiong He.","author":"Aminabadi Reza Yazdani","year":"2022","unstructured":"Reza Yazdani Aminabadi, Samyam Rajbhandari, Minjia Zhang, Ammar Ahmad Awan, Cheng Li, Du Li, Elton Zheng, Jeff Rasley, Shaden Smith, Olatunji Ruwase, and Yuxiong He. 2022. DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale. arxiv:2207.00032."},{"key":"e_1_3_2_1_14_1","unstructured":"Davide Bacciu Paulo J. G. Lisboa Jos\u00e9 D. Mart\u00edn Ruxandra Stoean and Alfredo Vellido. 2018. Bioinformatics and Medicine in the Era of Deep Learning. arxiv:1802.09791 arXiv:1802.09791 [cs q-bio stat]"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"J. Cohen. 1960. A Coefficient of Agreement for Nominal Scales. Educational and Psychological Measurement. http:\/\/dx.doi.org\/10.1177\/001316446002000104 10.1177\/001316446002000104","DOI":"10.1177\/001316446002000104"},{"volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"de Moura Leonardo","key":"e_1_3_2_1_16_1","unstructured":"Leonardo de Moura and Nikolaj Bj\u00f8rner. 2008. Z3: An Efficient SMT Solver. In Tools and Algorithms for the Construction and Analysis of Systems, C. R. Ramakrishnan and Jakob Rehof (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg. 337\u2013340. isbn:978-3-540-78800-3"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3473493"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00091"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. https:\/\/doi.org\/10.48550\/arXiv.2010.11929 arXiv:2010.11929 [cs] 10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485538"},{"key":"e_1_3_2_1_21_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. arxiv:1512.03385 arXiv:1512.03385 [cs]"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510115"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510115"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Sulabh Kumra and Christopher Kanan. 2017. Robotic Grasp Detection using Deep Convolutional Neural Networks. arxiv:1611.08036 arXiv:1611.08036 [cs]","DOI":"10.1109\/IROS.2017.8202237"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-018-1003-9"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.09312"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1993316.1993537"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2013.6606596"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Seonwoo Min Byunghan Lee and Sungroh Yoon. 2016. Deep learning in bioinformatics. Brief Bioinform July bbw068. issn:1467-5463 1477-4054 https:\/\/doi.org\/10.1093\/bib\/bbw068 10.1093\/bib\/bbw068","DOI":"10.1093\/bib"},{"key":"e_1_3_2_1_31_1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21, 1 (2020), Jan., 140:5485\u2013140:5551. issn:1532-4435","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884808"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Samyam Rajbhandari Jeff Rasley Olatunji Ruwase and Yuxiong He. 2020. ZeRO: Memory Optimizations Toward Training Trillion Parameter Models. arxiv:1910.02054.","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_34_1","unstructured":"James K. Reed Zachary DeVito Horace He Ansley Ussery and Jason Ansel. 2022. Torch.fx: Practical Program Capture and Transformation for Deep Learning in Python. arxiv:2112.08429."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2017.44"},{"key":"e_1_3_2_1_36_1","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2020. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arxiv:1909.08053."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2023. Attention Is All You Need. https:\/\/doi.org\/10.48550\/arXiv.1706.03762 arXiv:1706.03762 [cs] 10.48550\/arXiv.1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"e_1_3_2_1_38_1","volume-title":"Xformer: Hybrid X-Shaped Transformer for Image Denoising. arxiv:2303.06440 arXiv:2303.06440 [cs]","author":"Zhang Jiale","year":"2023","unstructured":"Jiale Zhang, Yulun Zhang, Jinjin Gu, Jiahua Dong, Linghe Kong, and Xiaokang Yang. 2023. Xformer: Hybrid X-Shaped Transformer for Image Denoising. arxiv:2303.06440 arXiv:2303.06440 [cs]"},{"key":"e_1_3_2_1_39_1","volume-title":"2017 IEEE\/ACM 39th International Conference on Software Engineering (ICSE). 665\u2013676","author":"Zhang Tianyi","year":"2017","unstructured":"Tianyi Zhang and Miryung Kim. 2017. Automated transplantation and differential testing for clones. In 2017 IEEE\/ACM 39th International Conference on Software Engineering (ICSE). 665\u2013676."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180260"}],"event":{"name":"ISSTA '24: 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","AITO"],"location":"Vienna Austria","acronym":"ISSTA '24"},"container-title":["Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650212.3652143","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3650212.3652143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:06Z","timestamp":1750287006000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650212.3652143"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,11]]},"references-count":40,"alternative-id":["10.1145\/3650212.3652143","10.1145\/3650212"],"URL":"https:\/\/doi.org\/10.1145\/3650212.3652143","relation":{},"subject":[],"published":{"date-parts":[[2024,9,11]]},"assertion":[{"value":"2024-09-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}