DNN-Compiler.bib

% =========================================
%         Dataflow Optimization 
% =========================================
@inproceedings{SPEED-MICRO2016-Alwani,
    title     = {Fused-layer {CNN} accelerators},
    author    = {Alwani, Manoj and Chen, Han and Ferdman, Michael and Milder, Peter},
    booktitle = micro,
    pages     = {22:1--22:12},
    year      = {2016},
}
@inproceedings{SPEED-DATE2018-SmartShuttle,
    title     = {{SmartShuttle}: Optimizing off-chip memory accesses for deep learning accelerators},
    author    = {Li, Jiajun and Yan, Guihai and Lu, Wenyan and Jiang, Shuhao and Gong, Shijun and Wu, Jingya and Li, Xiaowei},
    booktitle = date,
    pages     = {343--348},
    year      = {2018},
}
@inproceedings{SPEED-ICCAD2019-Sun,
    title     = {Energy-Driven {DNN} Dataflow Optimization on {FPGA}},
    author    = {Qi Sun and Tinghuan Chen and Jin Miao and Bei Yu},
    booktitle = iccad,
    year      = {2019},
}

% =========================================
%             DNN Compiler 
% =========================================
@inproceedings{Compil-OSDI2018-TVM,
    title     = {{TVM}: An automated end-to-end optimizing compiler for deep learning},
    author    = {Chen, Tianqi and Moreau, Thierry and Jiang, Ziheng and Zheng, Lianmin and Yan, Eddie and Shen, Haichen and Cowan, Meghan and Wang, Leyuan and Hu, Yuwei and Ceze, Luis and others},
    booktitle = osdi,
    pages     = {578--594},
    year      = {2018},
}
@inproceedings{Compil-MAPL2018-Relay,
    title={Relay: A new {IR} for machine learning frameworks},
    author={Roesch, Jared and Lyubomirsky, Steven and Weber, Logan and Pollock, Josh and Kirisame, Marisa and Chen, Tianqi and Tatlock, Zachary},
    booktitle={Proc.~MAPL},
    pages={58--68},
    year={2018}
}
@article{Compil-NeurIPS2018-Chen,
    title={{Learning to Optimize Tensor Programs}},
    author={Chen, Tianqi and Zheng, Lianmin and Yan, Eddie and Jiang, Ziheng and Moreau, Thierry and Ceze, Luis and Guestrin, Carlos and Krishnamurthy, Arvind},
    journal=neurips,
    volume={31},
    pages={3389--3400},
    year={2018}
}
@inproceedings{Compil-SOSP2019-TASO,
    title={{TASO}: optimizing deep learning computation with automatic generation of graph substitutions},
    author={Jia, Zhihao and Padon, Oded and Thomas, James and Warszawski, Todd and Zaharia, Matei and Aiken, Alex},
    booktitle=sosp,
    pages={47--62},
    year={2019}
}
@article{Compil-TOG2019-Halide,
    title={{Learning to Optimize Halide with Tree Search and Random Programs}},
    author={Adams, Andrew and Ma, Karima and Anderson, Luke and Baghdadi, Riyadh and Li, Tzu-Mao and Gharbi, Micha{\"e}l and Steiner, Benoit and Johnson, Steven and Fatahalian, Kayvon and Durand, Fr{\'e}do and others},
    journal=tog,
    volume={38},
    number={4},
    pages={1--12},
    year={2019},
}
@article{Compil-TPDS2020-Li,
    title={The deep learning compiler: A comprehensive survey},
    author={Li, Mingzhen and Liu, Yi and Liu, Xiaoyan and Sun, Qingxiao and You, Xin and Yang, Hailong and Luan, Zhongzhi and Gan, Lin and Yang, Guangwen and Qian, Depei},
    journal=tpds,
    volume={32},
    number={3},
    pages={708--727},
    year={2020},
    publisher={IEEE}
}
@inproceedings{Compil-OSDI2020-Ansor,
    title={Ansor: Generating high-performance tensor programs for deep learning},
    author={Zheng, Lianmin and Jia, Chengfan and Sun, Minmin and Wu, Zhao and Yu, Cody Hao and Haj-Ali, Ameer and Wang, Yida and Yang, Jun and Zhuo, Danyang and Sen, Koushik and others},
    booktitle=osdi,
    pages={863--879},
    year={2020}
}
@inproceedings{Compil-MLSys2021-IOS,
    title={{IOS: Inter-Operator Scheduler for CNN Acceleration}},
    author={Ding, Yaoyao and Zhu, Ligeng and Jia, Zhihao and Pekhimenko, Gennady and Han, Song},
    booktitle=mlsys,
    year={2021}
}
@inproceedings{Compil-DAC2022-GTuner,
    title={{GTuner: tuning DNN computations on GPU via graph attention network}},
    author={Sun, Qi and Zhang, Xinyun and Geng, Hao and Zhao, Yuxuan and Bai, Yang and Zheng, Haisheng and Yu, Bei},
    booktitle=dac,
    pages={1045--1050},
    year={2022}
}
@inproceedings{Compil-ICCV2021-Sun,
    title={{Fast and efficient DNN deployment via deep Gaussian transfer learning}},
    author={Sun, Qi and Bai, Chen and Chen, Tinghuan and Geng, Hao and Zhang, Xinyun and Bai, Yang and Yu, Bei},
    booktitle=iccv,
    pages={5380--5390},
    year={2021}
}
@inproceedings{Compil-ICCAD2021-AutoGTCO,
    title={{AutoGTCO: Graph and Tensor Co-Optimize for Image Recognition with Transformers on GPU}},
    author={Bai, Yang and Yao, Xufeng and Sun, Qi and Yu, Bei},
    booktitle=iccad,
    pages={1--9},
    year={2021},
}