{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T03:32:57Z","timestamp":1784431977758,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T00:00:00Z","timestamp":1714176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China (NSFC)","award":["U21B2017"],"award-info":[{"award-number":["U21B2017"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,27]]},"DOI":"10.1145\/3620666.3651330","type":"proceedings-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T12:08:21Z","timestamp":1713960501000},"page":"607-621","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5938-7965","authenticated-orcid":false,"given":"Renze","family":"Chen","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4555-2077","authenticated-orcid":false,"given":"Zijian","family":"Ding","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9471-1780","authenticated-orcid":false,"given":"Size","family":"Zheng","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5424-4898","authenticated-orcid":false,"given":"Chengrui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5660-5493","authenticated-orcid":false,"given":"Jingwen","family":"Leng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7908-8484","authenticated-orcid":false,"given":"Xuanzhe","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9076-7998","authenticated-orcid":false,"given":"Yun","family":"Liang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"A fast, scalable and easy-to-use deep learning framework. https:\/\/github.com\/MegEngine\/MegEngine","author":"Megengine","year":"2020","unstructured":"Megengine: A fast, scalable and easy-to-use deep learning framework. https:\/\/github.com\/MegEngine\/MegEngine, 2020."},{"key":"e_1_3_2_1_2_1","volume-title":"https:\/\/pytorch.org\/docs\/2.1\/torch.compiler","author":"PyTorch","year":"2023","unstructured":"torch.compiler - PyTorch 2.1 documentation. https:\/\/pytorch.org\/docs\/2.1\/torch.compiler, 2023."},{"key":"e_1_3_2_1_3_1","first-page":"44","article-title":"Memory-Aware Scheduling of Irregularly Wired Neural Networks for Edge Devices","volume":"2","author":"Ahn Byung Hoon","year":"2020","unstructured":"Byung Hoon Ahn, Jinwon Lee, Jamie Menjay Lin, Hsin-Pai Cheng, Jilei Hou, and Hadi Esmaeilzadeh. Ordering Chaos: Memory-Aware Scheduling of Irregularly Wired Neural Networks for Edge Devices. MLSys, 2:44--57, 2020.","journal-title":"MLSys"},{"key":"e_1_3_2_1_4_1","volume-title":"Techniques & Tools. pearson Education","author":"Alfred V Aho","year":"2007","unstructured":"V Aho Alfred, S Lam Monica, and D Ullman Jeffrey. Compilers Principles, Techniques & Tools. pearson Education, 2007."},{"key":"e_1_3_2_1_5_1","first-page":"23844","volume-title":"NIPS","volume":"34","author":"Beaumont Olivier","year":"2021","unstructured":"Olivier Beaumont, Lionel Eyraud-Dubois, and Alena Shilova. Efficient Combination of Rematerialization and Offloading for Training DNNs. In NIPS, volume 34, pages 23844--23857, 2021."},{"key":"e_1_3_2_1_6_1","volume-title":"GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow","author":"Black Sid","year":"2021","unstructured":"Sid Black, Leo Gao, Phil Wang, Connor Leahy, and Stella Biderman. GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow, 2021."},{"key":"e_1_3_2_1_7_1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","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, and Amanda Askell. Language models are few-shot learners. NIPS, 33:1877--1901, 2020.","journal-title":"NIPS"},{"key":"e_1_3_2_1_8_1","first-page":"1","volume-title":"ISCA","author":"Cai Jingwei","year":"2023","unstructured":"Jingwei Cai, Yuchen Wei, Zuotong Wu, Sen Peng, and Kaisheng Ma. Inter-layer Scheduling Space Definition and Exploration for Tiled Accelerators. In ISCA, pages 1--17, 2023."},{"key":"e_1_3_2_1_9_1","first-page":"578","volume-title":"OSDI","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. Tvm: An Automated End-to-End Optimizing Compiler for Deep Learning. In OSDI, pages 578--594, 2018."},{"key":"e_1_3_2_1_10_1","volume-title":"Training deep nets with sublinear memory cost","author":"Chen Tianqi","year":"2016","unstructured":"Tianqi Chen, Bing Xu, Chiyuan Zhang, and Carlos Guestrin. Training deep nets with sublinear memory cost, 2016."},{"key":"e_1_3_2_1_11_1","first-page":"31","article-title":"Learning to optimize tensor programs","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Lianmin Zheng, Eddie Yan, Ziheng Jiang, Thierry Moreau, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. Learning to optimize tensor programs. NIPS, 31, 2018.","journal-title":"NIPS"},{"key":"e_1_3_2_1_12_1","first-page":"4171","volume-title":"NAACL","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. NAACL, pages 4171--4186, 2019."},{"key":"e_1_3_2_1_13_1","volume-title":"Natalia Vassilieva, Marvin Tom, and Joel Hestness. Btlm-3b-8k: 7b parameter performance in a 3b parameter model","author":"Dey Nolan","year":"2023","unstructured":"Nolan Dey, Daria Soboleva, Faisal Al-Khateeb, Bowen Yang, Ribhu Pathria, Hemant Khachane, Shaheer Muhammad, Zhiming, Chen, Robert Myers, Jacob Robert Steeves, Natalia Vassilieva, Marvin Tom, and Joel Hestness. Btlm-3b-8k: 7b parameter performance in a 3b parameter model, 2023."},{"key":"e_1_3_2_1_14_1","first-page":"167","article-title":"Inter-operator scheduler for cnn acceleration","volume":"3","author":"Ding Yaoyao","year":"2021","unstructured":"Yaoyao Ding, Ligeng Zhu, Zhihao Jia, Gennady Pekhimenko, and Song Han. Ios: Inter-operator scheduler for cnn acceleration. MLSys, 3:167--180, 2021.","journal-title":"MLSys"},{"key":"e_1_3_2_1_15_1","volume-title":"ICLR","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, and Sylvain Gelly. An image is worth 16\u00d716 words: Transformers for image recognition at scale. ICLR, 2020."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3576933"},{"key":"e_1_3_2_1_17_1","volume-title":"Algorithm 799: revolve: an implementation of checkpointing for the reverse or adjoint mode of computational differentiation. TOMS, 26(1):19--45","author":"Griewank Andreas","year":"2000","unstructured":"Andreas Griewank and Andrea Walther. Algorithm 799: revolve: an implementation of checkpointing for the reverse or adjoint mode of computational differentiation. TOMS, 26(1):19--45, 2000."},{"key":"e_1_3_2_1_18_1","first-page":"29","article-title":"Memory-efficient backpropagation through time","author":"Gruslys Audrunas","year":"2016","unstructured":"Audrunas Gruslys, R\u00e9mi Munos, Ivo Danihelka, Marc Lanctot, and Alex Graves. Memory-efficient backpropagation through time. NIPS, 29, 2016.","journal-title":"NIPS"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378465"},{"key":"e_1_3_2_1_21_1","first-page":"6840","volume-title":"NIPS","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. Denoising Diffusion Probabilistic Models. In NIPS, volume 33, pages 6840--6851. Curran Associates, Inc., 2020."},{"key":"e_1_3_2_1_22_1","first-page":"1341","volume-title":"ASPLOS","author":"Huang Chien-Chin","year":"2020","unstructured":"Chien-Chin Huang, Gu Jin, and Jinyang Li. Swapadvisor: Pushing deep learning beyond the gpu memory limit via smart swapping. In ASPLOS, pages 1341--1355, 2020."},{"key":"e_1_3_2_1_23_1","volume-title":"Weinberger. Densely Connected Convolutional Networks. In CVPR","author":"Huang Gao","year":"2018","unstructured":"Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger. Densely Connected Convolutional Networks. In CVPR, 2018."},{"key":"e_1_3_2_1_24_1","volume-title":"Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization. MLSys","author":"Jain Paras","year":"2020","unstructured":"Paras Jain, Ajay Jain, Aniruddha Nrusimha, Amir Gholami, Pieter Abbeel, Kurt Keutzer, Ion Stoica, and Joseph E. Gonzalez. Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization. MLSys, 2020."},{"key":"e_1_3_2_1_25_1","first-page":"47","volume-title":"SOSP","author":"Jia Zhihao","year":"2019","unstructured":"Zhihao Jia, Oded Padon, James Thomas, Todd Warszawski, Matei Zaharia, and Alex Aiken. TASO: optimizing deep learning computation with automatic generation of graph substitutions. In SOSP, pages 47--62, 2019."},{"key":"e_1_3_2_1_26_1","first-page":"27","article-title":"Optimizing DNN Computation with Relaxed Graph Substitutions","volume":"1","author":"Jia Zhihao","year":"2019","unstructured":"Zhihao Jia, James Thomas, Todd Warszawski, Mingyu Gao, Matei Zaharia, and Alex Aiken. Optimizing DNN Computation with Relaxed Graph Substitutions. MLSys, 1:27--39, 2019.","journal-title":"MLSys"},{"key":"e_1_3_2_1_27_1","volume-title":"ICLR","author":"Kirisame Marisa","year":"2021","unstructured":"Marisa Kirisame, Steven Lyubomirsky, Altan Haan, Jennifer Brennan, Mike He, Jared Roesch, Tianqi Chen, and Zachary Tatlock. Dynamic Tensor Rematerialization. ICLR, 2021."},{"key":"e_1_3_2_1_28_1","first-page":"32","article-title":"Efficient Rematerialization for Deep Networks","author":"Kumar Ravi","year":"2019","unstructured":"Ravi Kumar, Manish Purohit, Zoya Svitkina, Erik Vee, and Joshua Wang. Efficient Rematerialization for Deep Networks. NIPS, 32, 2019.","journal-title":"NIPS"},{"key":"e_1_3_2_1_29_1","volume-title":"NIPS","volume":"32","author":"Kusumoto Mitsuru","year":"2019","unstructured":"Mitsuru Kusumoto, Takuya Inoue, Gentaro Watanabe, Takuya Akiba, and Masanori Koyama. A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation. In NIPS, volume 32, 2019."},{"key":"e_1_3_2_1_30_1","volume-title":"Tflms: Large model support in tensorflow by graph rewriting","author":"Le Tung D.","year":"2019","unstructured":"Tung D. Le, Haruki Imai, Yasushi Negishi, and Kiyokuni Kawachiya. Tflms: Large model support in tensorflow by graph rewriting, 2019."},{"key":"e_1_3_2_1_31_1","volume-title":"CGO","author":"Li Ao","year":"2020","unstructured":"Ao Li, Bojian Zheng, Gennady Pekhimenko, and Fan Long. Automatic Horizontal Fusion for GPU Kernels. In CGO, 2020."},{"key":"e_1_3_2_1_32_1","first-page":"161","volume-title":"ATC","author":"Lim Gangmuk","year":"2021","unstructured":"Gangmuk Lim, Jeongseob Ahn, Wencong Xiao, Youngjin Kwon, and Myeongjae Jeon. Zico: Efficient {GPU} memory sharing for concurrent {DNN} training. In ATC, pages 161--175, 2021."},{"key":"e_1_3_2_1_33_1","first-page":"881","volume-title":"OSDI","author":"Ma Lingxiao","year":"2020","unstructured":"Lingxiao Ma, Zhiqiang Xie, Zhi Yang, Jilong Xue, Youshan Miao, Wei Cui, Wenxiang Hu, Fan Yang, Lintao Zhang, and Lidong Zhou. Rammer: Enabling Holistic Deep Learning Compiler Optimizations with {rTasks}. In OSDI, pages 881--897, 2020."},{"issue":"5","key":"e_1_3_2_1_34_1","first-page":"122","article-title":"a look at the smallest program","volume":"15","author":"Massalin Henry","year":"1987","unstructured":"Henry Massalin. Superoptimizer: a look at the smallest program. ASPLOS, 15(5):122--126, 1987.","journal-title":"ASPLOS"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454083"},{"key":"e_1_3_2_1_36_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, Soumith Chintala, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9 Buc, E. Fox, and R. Garnett. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In NIPS, 2019."},{"key":"e_1_3_2_1_37_1","volume-title":"POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging. In ICML","author":"Patil Shishir G.","year":"2022","unstructured":"Shishir G. Patil, Paras Jain, Prabal Dutta, Ion Stoica, and Joseph E. Gonzalez. POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging. In ICML, 2022."},{"key":"e_1_3_2_1_38_1","first-page":"891","volume-title":"ASPLOS","author":"Peng Xuan","year":"2020","unstructured":"Xuan Peng, Xuanhua Shi, Hulin Dai, Hai Jin, Weiliang Ma, Qian Xiong, Fan Yang, and Xuehai Qian. Capuchin: Tensor-based gpu memory management for deep learning. In ASPLOS, pages 891--905, 2020."},{"key":"e_1_3_2_1_39_1","first-page":"1","volume-title":"SC","author":"Rajbhandari Samyam","year":"2021","unstructured":"Samyam Rajbhandari, Olatunji Ruwase, Jeff Rasley, Shaden Smith, and Yuxiong He. Zero-infinity: Breaking the gpu memory wall for extreme scale deep learning. In SC, pages 1--14, 2021."},{"key":"e_1_3_2_1_40_1","volume-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. Hierarchical text-conditional image generation with clip latents, 2022."},{"key":"e_1_3_2_1_41_1","first-page":"551","volume-title":"ATC","author":"Ren Jie","year":"2021","unstructured":"Jie Ren, Samyam Rajbhandari, Reza Yazdani Aminabadi, Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, and Yuxiong He. ZeRO-Offload: Democratizing Billion-Scale Model Training. In ATC, pages 551--564, 2021."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"e_1_3_2_1_43_1","volume-title":"Relay: A high-level compiler for deep learning","author":"Roesch Jared","year":"2019","unstructured":"Jared Roesch, Steven Lyubomirsky, Marisa Kirisame, Logan Weber, Josh Pollock, Luis Vega, Ziheng Jiang, Tianqi Chen, Thierry Moreau, and Zachary Tatlock. Relay: A high-level compiler for deep learning, 2019."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_46_1","volume-title":"Xla: Compiling machine learning for peak performance","author":"Sabne Amit","year":"2020","unstructured":"Amit Sabne. Xla: Compiling machine learning for peak performance. 2020."},{"key":"e_1_3_2_1_47_1","volume-title":"ICLR","author":"Shah Aashaka","year":"2022","unstructured":"Aashaka Shah, Chao-Yuan Wu, Jayashree Mohan, Vijay Chidambaram, and Philipp Kraehenbuehl. Memory Optimization for Deep Networks. In ICLR, 2022."},{"key":"e_1_3_2_1_48_1","volume-title":"Kurt Mehlhorn, and Karsten M. Borgwardt. Weisfeiler-lehman graph kernels. JMLR, 12(9)","author":"Shervashidze Nino","year":"2011","unstructured":"Nino Shervashidze, Pascal Schweitzer, Erik Jan Van Leeuwen, Kurt Mehlhorn, and Karsten M. Borgwardt. Weisfeiler-lehman graph kernels. JMLR, 12(9), 2011."},{"key":"e_1_3_2_1_49_1","volume-title":"OSDI","author":"Shi Yining","year":"2023","unstructured":"Yining Shi, Zhi Yang, Jilong Xue, Lingxiao Ma, Yuqing Xia, Ziming Miao, Yuxiao Guo, Fan Yang, and Lidong Zhou. Welder: Scheduling Deep Learning Memory Access via Tile-graph. In OSDI, 2023."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"e_1_3_2_1_51_1","volume-title":"Llama: Open and efficient foundation language models","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. Llama: Open and efficient foundation language models, 2023."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03968"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446753"},{"key":"e_1_3_2_1_54_1","first-page":"267","volume-title":"OSDI","author":"Unger Colin","year":"2022","unstructured":"Colin Unger, Zhihao Jia, Wei Wu, Sina Lin, Mandeep Baines, Carlos Efrain Quintero Narvaez, Vinay Ramakrishnaiah, Nirmal Prajapati, Pat McCormick, and Jamaludin Mohd-Yusof. Unity: Accelerating DNN Training Through Joint Optimization of Algebraic Transformations and Parallelization. In OSDI, pages 267--284, 2022."},{"key":"e_1_3_2_1_55_1","first-page":"5998","volume-title":"NIPS","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NIPS, pages 5998--6008, 2017."},{"key":"e_1_3_2_1_56_1","first-page":"37","volume-title":"OSDI","author":"Wang Haojie","year":"2021","unstructured":"Haojie Wang, Jidong Zhai, Mingyu Gao, Zixuan Ma, Shizhi Tang, Liyan Zheng, Yuanzhi Li, Kaiyuan Rong, Yuanyong Chen, and Zhihao Jia. PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections. In OSDI, pages 37--54, 2021."},{"key":"e_1_3_2_1_57_1","first-page":"41","volume-title":"PPoPP","author":"Wang Linnan","year":"2018","unstructured":"Linnan Wang, Jinmian Ye, Yiyang Zhao, Wei Wu, Ang Li, Shuaiwen Leon Song, Zenglin Xu, and Tim Kraska. Superneurons: dynamic GPU memory management for training deep neural networks. In PPoPP, pages 41--53, 2018."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530472"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370330"},{"key":"e_1_3_2_1_60_1","first-page":"1","article-title":"Fast and Extensible Equality Saturation","volume":"5","author":"Willsey Max","year":"2021","unstructured":"Max Willsey, Chandrakana Nandi, Yisu Remy Wang, Oliver Flatt, Zachary Tatlock, and Pavel Panchekha. egg: Fast and Extensible Equality Saturation. POPL, 5:1--29, 2021.","journal-title":"POPL"},{"key":"e_1_3_2_1_61_1","volume-title":"MLSys","author":"Xing Jiarong","year":"2022","unstructured":"Jiarong Xing, Leyuan Wang, Shang Zhang, Jack Chen, Ang Chen, and Yibo Zhu. Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance. MLSys, 4, April 2022."},{"key":"e_1_3_2_1_62_1","volume-title":"MLSys","author":"Yang Yichen","year":"2021","unstructured":"Yichen Yang, Phitchaya Mangpo Phothilimtha, Yisu Remy Wang, Max Willsey, Sudip Roy, and Jacques Pienaar. Equality Saturation for Tensor Graph Superoptimization. MLSys, 2021."},{"key":"e_1_3_2_1_63_1","first-page":"4","article-title":"Automatic Partition-based Operator fusion through Layer by Layer Optimization","author":"Zhao Jie","year":"2022","unstructured":"Jie Zhao, Xiong Gao, Ruijie Xia, Zhaochuang Zhang, Deshi Chen, Lei Chen, Renwei Zhang, Zhen Geng, Bin Cheng, and Xuefeng Jin. Apollo: Automatic Partition-based Operator fusion through Layer by Layer Optimization. MLSys, 4, 2022.","journal-title":"MLSys"},{"key":"e_1_3_2_1_64_1","first-page":"863","volume-title":"OSDI","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, et al. Ansor: Generating high-performance tensor programs for deep learning. In OSDI, pages 863--879, 2020."},{"issue":"11","key":"e_1_3_2_1_65_1","first-page":"3220","article-title":"A flexible framework for enabling efficient compilation for high performance dnn training","volume":"33","author":"Zheng Size","year":"2021","unstructured":"Size Zheng, Renze Chen, Yicheng Jin, Anjiang Wei, Bingyang Wu, Xiuhong Li, Shengen Yan, and Yun Liang. Neoflow: A flexible framework for enabling efficient compilation for high performance dnn training. TPDS, 33(11):3220--3232, 2021.","journal-title":"TPDS"},{"key":"e_1_3_2_1_66_1","first-page":"874","volume-title":"ISCA","author":"Zheng Size","year":"2022","unstructured":"Size Zheng, Renze Chen, Anjiang Wei, Yicheng Jin, Qin Han, Liqiang Lu, Bingyang Wu, Xiuhong Li, Shengen Yan, and Yun Liang. Amos: Enabling automatic mapping for tensor computations on spatial accelerators with hardware abstraction. In ISCA, pages 874--887, 2022."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623792"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247951"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071018"},{"key":"e_1_3_2_1_70_1","first-page":"859","volume-title":"ASPLOS","author":"Zheng Size","year":"2020","unstructured":"Size Zheng, Yun Liang, Shuo Wang, Renze Chen, and Kaiwen Sheng. Flextensor: An automatic schedule exploration and optimization framework for tensor computation on heterogeneous system. In ASPLOS, pages 859--873, 2020."},{"key":"e_1_3_2_1_71_1","volume-title":"ASPLOS","author":"Zheng Zhen","year":"2022","unstructured":"Zhen Zheng, Xuanda Yang, Pengzhan Zhao, Guoping Long, Kai Zhu, Feiwen Zhu, Wenyi Zhao, Xiaoyong Liu, Jun Yang, Jidong Zhai, Shuaiwen Leon Song, and Wei Lin. AStitch: enabling a new multidimensional optimization space for memory-intensive ML training and inference on modern SIMT architectures. In ASPLOS, 2022."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323998"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"e_1_3_2_1_74_1","first-page":"233","volume-title":"OSDI","author":"Zhu Hongyu","year":"2022","unstructured":"Hongyu Zhu, Ruofan Wu, Yijia Diao, Shanbin Ke, Haoyu Li, Chen Zhang, Jilong Xue, Lingxiao Ma, Yuqing Xia, Wei Cui, Fan Yang, Mao Yang, Lidong Zhou, Asaf Cidon, and Gennady Pekhimenko. {ROLLER}: Fast and Efficient Tensor Compilation for Deep Learning. In OSDI, pages 233--248, 2022."},{"key":"e_1_3_2_1_75_1","volume-title":"Learning Transferable Architectures for Scalable Image Recognition. In CVPR","author":"Zoph Barret","year":"2018","unstructured":"Barret Zoph, Vijay Vasudevan, Jonathon Shlens, and Quoc V. Le. Learning Transferable Architectures for Scalable Image Recognition. In CVPR, 2018."}],"event":{"name":"ASPLOS '24: 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","location":"La Jolla CA USA","acronym":"ASPLOS '24","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620666.3651330","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:42Z","timestamp":1750291422000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620666.3651330"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,27]]},"references-count":75,"alternative-id":["10.1145\/3620666.3651330","10.1145\/3620666"],"URL":"https:\/\/doi.org\/10.1145\/3620666.3651330","relation":{},"subject":[],"published":{"date-parts":[[2024,4,27]]},"assertion":[{"value":"2024-04-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}