{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:14Z","timestamp":1750309514608,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T00:00:00Z","timestamp":1719100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3649329.3658483","type":"proceedings-article","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:27:22Z","timestamp":1731007642000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Holistic Functionalization Approach to Optimizing Imperative Tensor Programs in Deep Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1351-1377","authenticated-orcid":false,"given":"Jinming","family":"Ma","sequence":"first","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4896-121X","authenticated-orcid":false,"given":"Xiuhong","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7118-0131","authenticated-orcid":false,"given":"Zihan","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8525-0608","authenticated-orcid":false,"given":"Xingcheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"SenseTime, Beijing, Beijing, China"},{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3858-7972","authenticated-orcid":false,"given":"Shengen","family":"Yan","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analysis and Applications, Peking University, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4128-8966","authenticated-orcid":false,"given":"Yuting","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9206-4630","authenticated-orcid":false,"given":"Yueqian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6649-2445","authenticated-orcid":false,"given":"Minxi","family":"Jin","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0250-5590","authenticated-orcid":false,"given":"Lijuan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9076-7998","authenticated-orcid":false,"given":"Yun (Eric)","family":"Liang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7426-6248","authenticated-orcid":false,"given":"Chao","family":"Yang","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analysis and Applications, Peking University, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8865-7896","authenticated-orcid":false,"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong, Hong Kong"},{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Andrew W. Appel. 1998. SSA is Functional Programming. SIGPLAN Not. (1998).","DOI":"10.1145\/278283.278285"},{"key":"e_1_3_2_1_2_1","unstructured":"The IREE Authors. 2019. IREE. https:\/\/openxla.github.io\/iree\/"},{"key":"e_1_3_2_1_3_1","volume-title":"YOLACT: Real-Time Instance Segmentation. In ICCV.","author":"Daniel Bolya","year":"2019","unstructured":"Daniel Bolya et al. 2019. YOLACT: Real-Time Instance Segmentation. In ICCV."},{"key":"e_1_3_2_1_4_1","volume-title":"TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In OSDI.","author":"Tianqi Chen","year":"2018","unstructured":"Tianqi Chen et al. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In OSDI."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Fred Chow et al. 1996. Effective representation of aliases and indirect memory operations in SSA form. In CC.","DOI":"10.1007\/3-540-61053-7_66"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Ron Cytron et al. 1991. Efficiently Computing Static Single Assignment Form and the Control Dependence Graph. ACM Trans. Program. Lang. Syst. (1991).","DOI":"10.1145\/115372.115320"},{"key":"e_1_3_2_1_7_1","unstructured":"Zachary DeVito. 2022. TorchScript: Optimized execution of PyTorch programs. https:\/\/program-transformations.github.io\/slides\/pytorch_neurips.pdf"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Sepp Hochreiter et al. 1997. Long Short-Term Memory. Neural Computation (1997).","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_9_1","unstructured":"Richard Zou Horace He. 2021. functorch: JAX-like composable function transforms for PyTorch. https:\/\/github.com\/pytorch\/functorch."},{"key":"e_1_3_2_1_10_1","volume-title":"TASO: Optimizing Deep Learning Computation with Automatic Generation of Graph Substitutions. In SOSP.","author":"Zhihao Jia","year":"2019","unstructured":"Zhihao Jia et al. 2019. TASO: Optimizing Deep Learning Computation with Automatic Generation of Graph Substitutions. In SOSP."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Lijuan Jiang et al. 2023. EasyView: Enabling and Scheduling Tensor Views in Deep Learning Compilers. In ICPP.","DOI":"10.1145\/3545008.3545037"},{"key":"e_1_3_2_1_12_1","volume-title":"MLIR: Scaling compiler infrastructure for domain specific computation. In CGO.","author":"Chris Lattner","year":"2021","unstructured":"Chris Lattner et al. 2021. MLIR: Scaling compiler infrastructure for domain specific computation. In CGO."},{"key":"e_1_3_2_1_13_1","volume-title":"SSD: Single Shot MultiBox Detector. In ECCV.","author":"Wei Liu","year":"2016","unstructured":"Wei Liu et al. 2016. SSD: Single Shot MultiBox Detector. In ECCV."},{"key":"e_1_3_2_1_14_1","volume-title":"Rammer: Enabling Holistic Deep Learning Compiler Optimizations with rTasks. In OSDI.","author":"Lingxiao Ma","year":"2020","unstructured":"Lingxiao Ma et al. 2020. Rammer: Enabling Holistic Deep Learning Compiler Optimizations with rTasks. In OSDI."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Wei Niu et al. 2021. DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion. In PLDI.","DOI":"10.1145\/3453483.3454083"},{"key":"e_1_3_2_1_16_1","unstructured":"Adam Paszke et al. 2019. PyTorch: An Imperative Style High-Performance Deep Learning Library. In NeurIPS."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"e_1_3_2_1_18_1","unstructured":"Joseph Redmon et al. 2018. YOLOv3: An Incremental Improvement. CoRR (2018)."},{"key":"e_1_3_2_1_19_1","unstructured":"James Reed et al. 2022. torch.fx: Practical Program Capture and Transformation for Deep Learning in Python. In MLSys."},{"key":"e_1_3_2_1_20_1","unstructured":"Christian Sarofeen et al. 2022. Introducing nvFuser a deep learning compiler for PyTorch. https:\/\/pytorch.org\/blog\/introducing-nvfuser-a-deep-learning-compiler-for-pytorch\/"},{"key":"e_1_3_2_1_21_1","unstructured":"Ilya Sutskever et al. 2014. Sequence to Sequence Learning with Neural Networks. In NeurIPS."},{"key":"e_1_3_2_1_22_1","volume-title":"FCOS: Fully Convolutional One-Stage Object Detection. In ICCV.","author":"Zhi Tian","year":"2019","unstructured":"Zhi Tian et al. 2019. FCOS: Fully Convolutional One-Stage Object Detection. In ICCV."},{"key":"e_1_3_2_1_23_1","unstructured":"Ashish Vaswani et al. 2017. Attention is all you need. NeurIPS (2017)."},{"key":"e_1_3_2_1_24_1","volume-title":"PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections. In OSDI.","author":"Haojie Wang","year":"2021","unstructured":"Haojie Wang et al. 2021. PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections. In OSDI."},{"key":"e_1_3_2_1_25_1","unstructured":"Peng Wu. 2023. PyTorch 2.0: The Journey to Bringing Compiler Technologies to the Core of PyTorch (Keynote). In CGO."},{"key":"e_1_3_2_1_26_1","volume-title":"Cocktailer: Analyzing and Optimizing Dynamic Control Flow in Deep Learning. In OSDI.","author":"Chen Zhang","year":"2023","unstructured":"Chen Zhang et al. 2023. Cocktailer: Analyzing and Optimizing Dynamic Control Flow in Deep Learning. In OSDI."},{"key":"e_1_3_2_1_27_1","volume-title":"Ansor: Generating High-Performance Tensor Programs for Deep Learning. In OSDI.","author":"Lianmin Zheng","year":"2020","unstructured":"Lianmin Zheng et al. 2020. Ansor: Generating High-Performance Tensor Programs for Deep Learning. In OSDI."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Zhen Zheng et al. 2022. AStitch: Enabling a New Multi-Dimensional Optimization Space for Memory-Intensive ML Training and Inference on Modern SIMT Architectures. In ASPLOS.","DOI":"10.1145\/3503222.3507723"},{"key":"e_1_3_2_1_29_1","unstructured":"Mikhail Zolotukhin. 2021. NNC walkthrough: how PyTorch ops get fused. https:\/\/dev-discuss.pytorch.org\/t\/nnc-walkthrough-how-pytorch-ops-get-fused\/125"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Barret Zoph et al. 2018. Learning transferable architectures for scalable image recognition. In CVPR.","DOI":"10.1109\/CVPR.2018.00907"}],"event":{"name":"DAC '24: 61st ACM\/IEEE Design Automation Conference","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE-CEDA","SIGBED ACM Special Interest Group on Embedded Systems"],"location":"San Francisco CA USA","acronym":"DAC '24"},"container-title":["Proceedings of the 61st ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3658483","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649329.3658483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:01Z","timestamp":1750295881000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3658483"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":30,"alternative-id":["10.1145\/3649329.3658483","10.1145\/3649329"],"URL":"https:\/\/doi.org\/10.1145\/3649329.3658483","relation":{},"subject":[],"published":{"date-parts":[[2024,6,23]]},"assertion":[{"value":"2024-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}