{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:09:24Z","timestamp":1776888564440,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,2,22]],"date-time":"2020-02-22T00:00:00Z","timestamp":1582329600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1518703"],"award-info":[{"award-number":["CCF-1518703"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,2,22]]},"DOI":"10.1145\/3368826.3377912","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T21:49:28Z","timestamp":1582321768000},"page":"305-316","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":33,"title":["Automatic generation of high-performance quantized machine learning kernels"],"prefix":"10.1145","author":[{"given":"Meghan","family":"Cowan","sequence":"first","affiliation":[{"name":"University of Washington, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thierry","family":"Moreau","sequence":"additional","affiliation":[{"name":"University of Washington, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianqi","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Washington, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Bornholt","sequence":"additional","affiliation":[{"name":"University of Texas at Austin, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis","family":"Ceze","sequence":"additional","affiliation":[{"name":"University of Washington, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,2,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Mart\u00edn Abadi Paul Barham Jianmin Chen Zhifeng Chen Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Geoffrey Irving Michael Isard Manjunath Kudlur Josh Levenberg Rajat Monga Sherry Moore Derek G. Murray Benoit Steiner Paul Tucker Vijay Vasudevan Pete Warden Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2016. TensorFlow: A system for large-scale machine learning. In OSDI."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"James Bornholt Emina Torlak Dan Grossman and Luis Ceze. 2016. Optimizing synthesis with metasketches. In POPL.","DOI":"10.1145\/2914770.2837666"},{"key":"e_1_3_2_1_3_1","unstructured":"Zhaowei Cai Xiaodong He Jian Sun and Nuno Vasconcelos. 2017. Deep learning with low precision by half-wave gaussian quantization. In CVPR."},{"key":"e_1_3_2_1_4_1","volume-title":"TVM: An automated end-to-end optimizing compiler for deep learning. In OSDI.","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Meghan Cowan, Haichen Shen, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM: An automated end-to-end optimizing compiler for deep learning. In OSDI."},{"key":"e_1_3_2_1_5_1","unstructured":"Tianqi Chen Lianmin Zheng Eddie Yan Ziheng Jiang Thierry Moreau Luis Ceze Carlos Guestrin and Arvind Krishnamurthy. 2018. Learning to optimize tensor programs. In NeurIPS."},{"key":"e_1_3_2_1_6_1","volume-title":"Dadiannao: A machine-learning supercomputer. In MICRO.","author":"Chen Yunji","year":"2014","unstructured":"Yunji Chen, Tao Luo, Shaoli Liu, Shijin Zhang, Liqiang He, Jia Wang, Ling Li, Tianshi Chen, Zhiwei Xu, Ninghui Sun, et al. 2014. Dadiannao: A machine-learning supercomputer. In MICRO."},{"key":"e_1_3_2_1_7_1","volume-title":"Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks. JSSC","author":"Chen Yu-Hsin","year":"2017","unstructured":"Yu-Hsin Chen, Tushar Krishna, Joel S Emer, and Vivienne Sze. 2017. Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks. JSSC (2017)."},{"key":"e_1_3_2_1_8_1","volume-title":"cuDNN: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759","author":"Chetlur Sharan","year":"2014","unstructured":"Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, Bryan Catanzaro, and Evan Shelhamer. 2014. cuDNN: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014)."},{"key":"e_1_3_2_1_9_1","volume-title":"SysML conference.","author":"Choi Jungwook","year":"2019","unstructured":"Jungwook Choi, Swagath Venkataramani, Vijayalakshmi Srinivasan, Kailash Gopalakrishnan, Zhuo Wang, and Pierce Chuang. 2019. Accurate and efficient 2-bit quantized neural networks. In SysML conference."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Eric Chung Jeremy Fowers Kalin Ovtcharov Michael Papamichael Adrian Caulfield Todd Massengill Ming Liu Daniel Lo Shlomi Alkalay Michael Haselman et al. 2018. Serving DNNs in real time at datacenter scale with project brainwave. IEEE Micro (2018).","DOI":"10.1109\/MM.2018.022071131"},{"key":"e_1_3_2_1_11_1","unstructured":"Intel Corporation. 2009. Intel Math Kernel Library reference manual."},{"key":"e_1_3_2_1_12_1","volume-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1. arXiv preprint arXiv:1602.02830","author":"Courbariaux Matthieu","year":"2016","unstructured":"Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1. arXiv preprint arXiv:1602.02830 (2016)."},{"key":"e_1_3_2_1_13_1","unstructured":"Meghan Cowan Thierry Moreau Tianqi Chen and Luis Ceze. 2018. Towards automating generation of low precision deep learning operators. In MLPCD. arXiv preprint arXiv:1810.11066."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Sumit Gulwani Susmit Jha Ashish Tiwari and Ramarathnam Venkatesan. 2011. Synthesis of loop-free programs. In PLDI.","DOI":"10.1145\/1993498.1993506"},{"key":"e_1_3_2_1_15_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR."},{"key":"e_1_3_2_1_16_1","unstructured":"Yuwei Hu Jidong Zhai Dinghua Li Yifan Gong Yuhao Zhu Wei Liu Lei Su and Jiangming Jin. 2018. BitFlow: Exploiting vector parallelism for binary neural networks on CPU. In IPDPS."},{"key":"e_1_3_2_1_17_1","volume-title":"Quantized neural networks: Training neural networks with low precision weights and activations. JMLR 18","author":"Hubara Itay","year":"2017","unstructured":"Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2017. Quantized neural networks: Training neural networks with low precision weights and activations. JMLR 18 (2017)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Benoit Jacob Skirmantas Kligys Bo Chen Menglong Zhu Matthew Tang Andrew Howard Hartwig Adam and Dmitry Kalenichenko. 2018. Quantization and training of neural networks for efficient integerarithmetic-only inference. In CVPR.","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_2_1_19_1","unstructured":"Norman P Jouppi Cliff Young Nishant Patil David Patterson Gaurav Agrawal Raminder Bajwa Sarah Bates Suresh Bhatia Nan Boden Al Borchers et al. 2017. In-datacenter performance analysis of a tensor processing unit. In ISCA."},{"key":"e_1_3_2_1_20_1","volume-title":"Stripes: Bit-serial deep neural network computing. In MICRO.","author":"Judd Patrick","year":"2016","unstructured":"Patrick Judd, Jorge Albericio, Tayler Hetherington, Tor M Aamodt, and Andreas Moshovos. 2016. Stripes: Bit-serial deep neural network computing. In MICRO."},{"key":"e_1_3_2_1_21_1","volume-title":"Amarasinghe","author":"Kjolstad Fredrik","year":"2017","unstructured":"Fredrik Kjolstad, Shoaib Kamil, Stephen Chou, David Lugato, and Saman P. Amarasinghe. 2017. The tensor algebra compiler. In OOPSLA."},{"key":"e_1_3_2_1_22_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey Hinton. 2012. ImageNet classification with deep convolutional neural networks. In NeurIPS."},{"key":"e_1_3_2_1_23_1","volume-title":"Superoptimizer: A look at the smallest program. In ASPLOS.","author":"Massalin Henry","year":"1987","unstructured":"Henry Massalin. 1987. Superoptimizer: A look at the smallest program. In ASPLOS."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Amrita Mazumdar Thierry Moreau Sung Kim Meghan Cowan Armin Alaghi Luis Ceze Mark Oskin and Visvesh Sathe. 2017. Exploring computation-communication tradeoffs in camera systems. In IISWC.","DOI":"10.1109\/IISWC.2017.8167775"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2019.2928962"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Omkar M Parkhi Andrea Vedaldi Andrew Zisserman et al. 2015. Deep face recognition. In BMVC.","DOI":"10.5244\/C.29.41"},{"key":"e_1_3_2_1_27_1","volume-title":"Chlorophyll: Synthesisaided compiler for low-power spatial architectures. In PLDI.","author":"Phothilimthana Phitchaya Mangpo","year":"2014","unstructured":"Phitchaya Mangpo Phothilimthana, Tikhon Jelvis, Rohin Shah, Nishant Totla, Sarah Chasins, and Rastislav Bodik. 2014. Chlorophyll: Synthesisaided compiler for low-power spatial architectures. In PLDI."},{"key":"e_1_3_2_1_28_1","volume-title":"SPIRAL: Code generation for DSP transforms. Proc","author":"Puschel M.","year":"2005","unstructured":"M. Puschel, J. M. F. Moura, J. R. Johnson, D. Padua, M. M. Veloso, B. W. Singer, Jianxin Xiong, F. Franchetti, A. Gacic, Y. Voronenko, K. Chen, R. W. Johnson, and N. Rizzolo. 2005. SPIRAL: Code generation for DSP transforms. Proc. IEEE (2005)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"e_1_3_2_1_30_1","volume-title":"Xnor-net: Imagenet classification using binary convolutional neural networks. In ECCV.","author":"Rastegari Mohammad","year":"2016","unstructured":"Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, and Ali Farhadi. 2016. Xnor-net: Imagenet classification using binary convolutional neural networks. In ECCV."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Alastair Reid. 2017. Who guards the guards? Formal validation of the Arm V8-m architecture specification. In OOPSLA.","DOI":"10.1145\/3133912"},{"key":"e_1_3_2_1_32_1","volume-title":"Glow: Graph lowering compiler techniques for neural networks. arXiv preprint arXiv:1805.00907","author":"Rotem Nadav","year":"2018","unstructured":"Nadav Rotem, Jordan Fix, Saleem Abdulrasool, Garret Catron, Summer Deng, Roman Dzhabarov, Nick Gibson, James Hegeman, Meghan Lele, Roman Levenstein, et al. 2018. Glow: Graph lowering compiler techniques for neural networks. arXiv preprint arXiv:1805.00907 (2018)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. IJCV 115 (2015).","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_34_1","volume-title":"Bit Fusion: Bitlevel dynamically composable architecture for accelerating deep neural networks. In ISCA.","author":"Sharma Hardik","year":"2018","unstructured":"Hardik Sharma, Jongse Park, Naveen Suda, Liangzhen Lai, Benson Chau, Vikas Chandra, and Hadi Esmaeilzadeh. 2018. Bit Fusion: Bitlevel dynamically composable architecture for accelerating deep neural networks. In ISCA."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Armando Solar-Lezama Liviu Tancau Rastislav Bodik Vijay Saraswat and Sanjit Seshia. 2006. Combinatorial sketching for finite programs. In ASPLOS.","DOI":"10.1145\/1168857.1168907"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Emina Torlak and Rastislav Bodik. 2013. Growing solver-aided languages with Rosette. In Onward!","DOI":"10.1145\/2509578.2509586"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Emina Torlak and Rastislav Bodik. 2014. A lightweight symbolic virtual machine for solver-aided host languages. In PLDI.","DOI":"10.1145\/2594291.2594340"},{"key":"e_1_3_2_1_38_1","unstructured":"Andrew Tulloch. 2019. Private communication. (2019)."},{"key":"e_1_3_2_1_39_1","volume-title":"High performance ultralow-precision convolutions on mobile devices. arXiv preprint arXiv:1712.02427","author":"Tulloch Andrew","year":"2017","unstructured":"Andrew Tulloch and Yangqing Jia. 2017. High performance ultralow-precision convolutions on mobile devices. arXiv preprint arXiv:1712.02427 (2017)."},{"key":"e_1_3_2_1_40_1","unstructured":"Yaman Umuroglu. 2018. Private communication. (2018)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021744"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Yaman Umuroglu and Magnus Jahre. 2017. Towards efficient quantized neural network inference on mobile devices. In CASES.","DOI":"10.1145\/3125501.3125528"},{"key":"e_1_3_2_1_43_1","volume-title":"Bismo: A scalable bit-serial matrix multiplication overlay for reconfigurable computing. In FPL.","author":"Umuroglu Yaman","year":"2018","unstructured":"Yaman Umuroglu, Lahiru Rasnayake, and Magnus Sj\u00e4lander. 2018. Bismo: A scalable bit-serial matrix multiplication overlay for reconfigurable computing. In FPL."},{"key":"e_1_3_2_1_44_1","volume-title":"Tensor Comprehensions: Frameworkagnostic high-performance machine learning abstractions. arXiv preprint arXiv:1802.04730","author":"Vasilache Nicolas","year":"2018","unstructured":"Nicolas Vasilache, Oleksandr Zinenko, Theodoros Theodoridis, Priya Goyal, Zachary DeVito, William S Moses, Sven Verdoolaege, Andrew Adams, and Albert Cohen. 2018. Tensor Comprehensions: Frameworkagnostic high-performance machine learning abstractions. arXiv preprint arXiv:1802.04730 (2018)."},{"key":"e_1_3_2_1_45_1","volume-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160","author":"Zhou Shuchang","year":"2016","unstructured":"Shuchang Zhou, Yuxin Wu, Zekun Ni, Xinyu Zhou, He Wen, and Yuheng Zou. 2016. DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160 (2016)."}],"event":{"name":"CGO '20: 18th ACM\/IEEE International Symposium on Code Generation and Optimization","location":"San Diego CA USA","acronym":"CGO '20","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing","IEEE-CS Computer Society"]},"container-title":["Proceedings of the 18th ACM\/IEEE International Symposium on Code Generation and Optimization"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3368826.3377912","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3368826.3377912","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3368826.3377912","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:28Z","timestamp":1750202608000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3368826.3377912"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,22]]},"references-count":45,"alternative-id":["10.1145\/3368826.3377912","10.1145\/3368826"],"URL":"https:\/\/doi.org\/10.1145\/3368826.3377912","relation":{},"subject":[],"published":{"date-parts":[[2020,2,22]]},"assertion":[{"value":"2020-02-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}