{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:22:42Z","timestamp":1781972562756,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":73,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,3,25]],"date-time":"2023-03-25T00:00:00Z","timestamp":1679702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"CAS Project for Young Scientists in Basic Research","award":["YSBR-029"],"award-info":[{"award-number":["YSBR-029"]}]},{"name":"Youth Innovation Promotion Association CAS","award":[""],"award-info":[{"award-number":[""]}]},{"name":"Beijing Academy of Artificial Intelligence","award":[""],"award-info":[{"award-number":[""]}]},{"name":"the NSF of China","award":["U22A2028, 61925208, 62102398, 62222214, 62002338, U19B2019, U20A20227"],"award-info":[{"award-number":["U22A2028, 61925208, 62102398, 62222214, 62002338, U19B2019, U20A20227"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,3,25]]},"DOI":"10.1145\/3582016.3582061","type":"proceedings-article","created":{"date-parts":[[2023,3,20]],"date-time":"2023-03-20T16:59:03Z","timestamp":1679331543000},"page":"314-328","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["Heron: Automatically Constrained High-Performance Library Generation for Deep Learning Accelerators"],"prefix":"10.1145","author":[{"given":"Jun","family":"Bi","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, China \/ Institute of Computing Technology at Chinese Academy of Sciences, China \/ Cambricon Technologies, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology at Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaqing","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology at Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongwei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology at Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanbo","family":"Wen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology at Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, China \/ Institute of Computing Technology at Chinese Academy of Sciences, China \/ Cambricon Technologies, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enshuai","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, China \/ Institute of Computing Technology at Chinese Academy of Sciences, China \/ Cambricon Technologies, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology at Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zidong","family":"Du","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology at Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Software at Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaping","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianshi","family":"Chen","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,3,25]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d]. Accelerate Fast Math with Intel\u00ae oneAPI Math Kernel Library.  http:\/\/software.intel.com\/en-us\/intel-mkl \t\t\t\t  [n.d]. Accelerate Fast Math with Intel\u00ae oneAPI Math Kernel Library.  http:\/\/software.intel.com\/en-us\/intel-mkl"},{"key":"e_1_3_2_1_2_1","unstructured":"[n.d]. Basic Linear Algebra on NVIDIA GPUs.  https:\/\/developer.nvidia.com\/cublas \t\t\t\t  [n.d]. Basic Linear Algebra on NVIDIA GPUs.  https:\/\/developer.nvidia.com\/cublas"},{"key":"e_1_3_2_1_3_1","unstructured":"[n.d]. Cambricon MLU.  https:\/\/www.cambricon.com\/ \t\t\t\t  [n.d]. Cambricon MLU.  https:\/\/www.cambricon.com\/"},{"key":"e_1_3_2_1_4_1","unstructured":"[n.d]. Googles Operations Research Tools.  https:\/\/github.com\/google\/or-tools \t\t\t\t  [n.d]. Googles Operations Research Tools.  https:\/\/github.com\/google\/or-tools"},{"key":"e_1_3_2_1_5_1","unstructured":"[n.d]. GOYA INFERENCE PRODUCTS.  https:\/\/habana.ai\/inference\/ \t\t\t\t  [n.d]. GOYA INFERENCE PRODUCTS.  https:\/\/habana.ai\/inference\/"},{"key":"e_1_3_2_1_6_1","unstructured":"[n.d]. Inside Apple\u2019s new A11 Bionic processor.  https:\/\/www.zdnet.com\/article\/inside-apples-new-a11-bionic-processor\/ \t\t\t\t  [n.d]. Inside Apple\u2019s new A11 Bionic processor.  https:\/\/www.zdnet.com\/article\/inside-apples-new-a11-bionic-processor\/"},{"key":"e_1_3_2_1_7_1","unstructured":"[n.d]. Intel Deep Learning Boost - Intel AI.  https:\/\/www.intel.com\/content\/www\/us\/en\/artificial-intelligence\/deep-learning-boost.html \t\t\t\t  [n.d]. Intel Deep Learning Boost - Intel AI.  https:\/\/www.intel.com\/content\/www\/us\/en\/artificial-intelligence\/deep-learning-boost.html"},{"key":"e_1_3_2_1_8_1","unstructured":"[n.d]. NVIDIA A100 TENSOR CORE GPU.  https:\/\/www.nvidia.com\/en-us\/data-center\/a100\/ \t\t\t\t  [n.d]. NVIDIA A100 TENSOR CORE GPU.  https:\/\/www.nvidia.com\/en-us\/data-center\/a100\/"},{"key":"e_1_3_2_1_9_1","unstructured":"[n.d]. NVIDIA cuDNN.  https:\/\/developer.nvidia.com\/cudnn \t\t\t\t  [n.d]. NVIDIA cuDNN.  https:\/\/developer.nvidia.com\/cudnn"},{"key":"e_1_3_2_1_10_1","unstructured":"[n.d]. NVIDIA T4 Tensor Core GPU for AI inference..  https:\/\/www.nvidia.com\/en-us\/data-center\/tesla-t4\/ \t\t\t\t  [n.d]. NVIDIA T4 Tensor Core GPU for AI inference..  https:\/\/www.nvidia.com\/en-us\/data-center\/tesla-t4\/"},{"key":"e_1_3_2_1_11_1","unstructured":"[n.d]. NVIDIA Tensor Core. https:\/\/www.nvidia.cn\/data-center\/tensor-cores\/ \t\t\t\t  [n.d]. NVIDIA Tensor Core. https:\/\/www.nvidia.cn\/data-center\/tensor-cores\/"},{"key":"e_1_3_2_1_12_1","unstructured":"[n.d]. NVIDIA V100 TENSOR CORE GPU.  https:\/\/www.nvidia.com\/en-us\/data-center\/v100\/ \t\t\t\t  [n.d]. NVIDIA V100 TENSOR CORE GPU.  https:\/\/www.nvidia.com\/en-us\/data-center\/v100\/"},{"key":"e_1_3_2_1_13_1","unstructured":"[n.d]. oneAPI Deep Neural Network Library (oneDNN).  https:\/\/github.com\/intel\/mkl-dnn \t\t\t\t  [n.d]. oneAPI Deep Neural Network Library (oneDNN).  https:\/\/github.com\/intel\/mkl-dnn"},{"key":"e_1_3_2_1_14_1","unstructured":"[n.d]. OpenBLAS: An optimized BLAS library.  https:\/\/www.openblas.net \t\t\t\t  [n.d]. OpenBLAS: An optimized BLAS library.  https:\/\/www.openblas.net"},{"key":"e_1_3_2_1_15_1","unstructured":"[n.d]. Poplar Graph Framework Software.  https:\/\/www.graphcore.ai\/products\/poplar \t\t\t\t  [n.d]. Poplar Graph Framework Software.  https:\/\/www.graphcore.ai\/products\/poplar"},{"key":"e_1_3_2_1_16_1","unstructured":"[n.d]. Programming Tensor Cores in CUDA 9. https:\/\/developer.nvidia.com\/blog\/programming-tensor-cores-cuda-9\/ \t\t\t\t  [n.d]. Programming Tensor Cores in CUDA 9. https:\/\/developer.nvidia.com\/blog\/programming-tensor-cores-cuda-9\/"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322967"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/3314872.3314896"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/2503308.2188395"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.2971677"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 476\u2013488","author":"Cai Ruizhe","year":"2018","unstructured":"Ruizhe Cai , Ao Ren , Ning Liu , Caiwen Ding , Luhao Wang , Xuehai Qian , Massoud Pedram , and Yanzhi Wang . 2018 . VIBNN: Hardware Acceleration of Bayesian Neural Networks . In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 476\u2013488 . Ruizhe Cai, Ao Ren, Ning Liu, Caiwen Ding, Luhao Wang, Xuehai Qian, Massoud Pedram, and Yanzhi Wang. 2018. VIBNN: Hardware Acceleration of Bayesian Neural Networks. In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 476\u2013488."},{"key":"e_1_3_2_1_22_1","volume-title":"Marvel: A Data-centric Compiler for DNN Operators on Spatial Accelerators. arXiv: Distributed, Parallel, and Cluster Computing.","author":"Chatarasi Prasanth","year":"2020","unstructured":"Prasanth Chatarasi , Hyoukjun Kwon , Natesh Raina , Saurabh Malik , Vaisakh Haridas , Angshuman Parashar , Michael Pellauer , Tushar Krishna , and Vivek Sarkar . 2020 . Marvel: A Data-centric Compiler for DNN Operators on Spatial Accelerators. arXiv: Distributed, Parallel, and Cluster Computing. Prasanth Chatarasi, Hyoukjun Kwon, Natesh Raina, Saurabh Malik, Vaisakh Haridas, Angshuman Parashar, Michael Pellauer, Tushar Krishna, and Vivek Sarkar. 2020. Marvel: A Data-centric Compiler for DNN Operators on Spatial Accelerators. arXiv: Distributed, Parallel, and Cluster Computing."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 269\u2013284","author":"Chen Tianshi","year":"2014","unstructured":"Tianshi Chen , Zidong Du , Ninghui Sun , Jia Wang , Chengyong Wu , Yunji Chen , and Olivier Temam . 2014 . DianNao: A Small-Footprint High-Throughput Accelerator for Ubiquitous Machine-Learning . In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 269\u2013284 . Tianshi Chen, Zidong Du, Ninghui Sun, Jia Wang, Chengyong Wu, Yunji Chen, and Olivier Temam. 2014. DianNao: A Small-Footprint High-Throughput Accelerator for Ubiquitous Machine-Learning. In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 269\u2013284."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI). 578\u2013594","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen , Thierry Moreau , Ziheng Jiang , Lianmin Zheng , Eddie Yan , Haichen Shen , Meghan Cowan , Leyuan Wang , Yuwei Hu , and Luis Ceze . 2018 . TVM: An Automated End-to-End Optimizing Compiler for Deep Learning . In Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI). 578\u2013594 . Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, and Luis Ceze. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI). 578\u2013594."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems (NeurIPS). 3393\u20133404","author":"Chen Tianqi","year":"2018","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 Proceedings of the 32nd International Conference on Neural Information Processing Systems (NeurIPS). 3393\u20133404 . Tianqi Chen, Lianmin Zheng, Eddie Yan, Ziheng Jiang, Thierry Moreau, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. Learning to optimize tensor programs. In Proceedings of the 32nd International Conference on Neural Information Processing Systems (NeurIPS). 3393\u20133404."},{"key":"e_1_3_2_1_27_1","first-page":"105","article-title":"DianNao Family","volume":"59","author":"Chen Yunji","year":"2016","unstructured":"Yunji Chen , Tianshi Chen , Zhiwei Xu , Ninghui Sun , and Olivier Temam . 2016 . DianNao Family : Energy-Efficient Hardware Accelerators for Machine Learning. Commun. ACM , 59 , 11 (2016), 105 \u2013 112 . Yunji Chen, Tianshi Chen, Zhiwei Xu, Ninghui Sun, and Olivier Temam. 2016. DianNao Family: Energy-Efficient Hardware Accelerators for Machine Learning. Commun. ACM, 59, 11 (2016), 105\u2013112.","journal-title":"Energy-Efficient Hardware Accelerators for Machine Learning. Commun. ACM"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 43rd ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 367\u2013379","author":"Chen Yu-Hsin","year":"2016","unstructured":"Yu-Hsin Chen , Joel Emer , and Vivienne Sze . 2016 . Eyeriss: A Spatial Architecture for Energy-Efficient Dataflow for Convolutional Neural Networks . In Proceedings of the 43rd ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 367\u2013379 . Yu-Hsin Chen, Joel Emer, and Vivienne Sze. 2016. Eyeriss: A Spatial Architecture for Energy-Efficient Dataflow for Convolutional Neural Networks. In Proceedings of the 43rd ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 367\u2013379."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 43rd ACM\/IEEE International Symposium on Computer Architecture (ISCA). 27\u201339","author":"Chi Ping","year":"2016","unstructured":"Ping Chi , Shuangchen Li , Cong Xu , Tao Zhang , Jishen Zhao , Yongpan Liu , Yu Wang , and Yuan Xie . 2016 . PRIME: A Novel Processing-in-Memory Architecture for Neural Network Computation in ReRAM-Based Main Memory . In Proceedings of the 43rd ACM\/IEEE International Symposium on Computer Architecture (ISCA). 27\u201339 . Ping Chi, Shuangchen Li, Cong Xu, Tao Zhang, Jishen Zhao, Yongpan Liu, Yu Wang, and Yuan Xie. 2016. PRIME: A Novel Processing-in-Memory Architecture for Neural Network Computation in ReRAM-Based Main Memory. In Proceedings of the 43rd ACM\/IEEE International Symposium on Computer Architecture (ISCA). 27\u201339."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1080\/02630250008970288"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the Genetic and Evolutionary Computation Conference Companion.","author":"Coello Coello Carlos A.","year":"2022","unstructured":"Carlos A. Coello Coello . 2022 . Constraint-handling techniques used with evolutionary algorithms . Proceedings of the Genetic and Evolutionary Computation Conference Companion. Carlos A. Coello Coello. 2022. Constraint-handling techniques used with evolutionary algorithms. Proceedings of the Genetic and Evolutionary Computation Conference Companion."},{"key":"e_1_3_2_1_33_1","volume-title":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1544\u20131548","author":"Dave Shail","year":"2020","unstructured":"Shail Dave , Aviral Shrivastava , Youngbin Kim , Sasikanth Avancha , and Kyoungwoo Lee . 2020 . dMazeRunner: Optimizing Convolutions on Dataflow Accelerators . ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1544\u20131548 . Shail Dave, Aviral Shrivastava, Youngbin Kim, Sasikanth Avancha, and Kyoungwoo Lee. 2020. dMazeRunner: Optimizing Convolutions on Dataflow Accelerators. ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1544\u20131548."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). 4171\u20134186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2019 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding . In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). 4171\u20134186 . Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). 4171\u20134186."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 751\u2013764","author":"Gao Mingyu","year":"2017","unstructured":"Mingyu Gao , Jing Pu , Xuan Yang , Mark Horowitz , and Christos Kozyrakis . 2017 . TETRIS: Scalable and Efficient Neural Network Acceleration with 3D Memory . In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 751\u2013764 . Mingyu Gao, Jing Pu, Xuan Yang, Mark Horowitz, and Christos Kozyrakis. 2017. TETRIS: Scalable and Efficient Neural Network Acceleration with 3D Memory. In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 751\u2013764."},{"key":"e_1_3_2_1_37_1","first-page":"36","article-title":"Genetic algorithms in search, optimization, and machine learning","volume":"1989","author":"Golberg David E","year":"1989","unstructured":"David E Golberg . 1989 . Genetic algorithms in search, optimization, and machine learning . Addion Wesley , 1989 , 102 (1989), 36 . David E Golberg. 1989. Genetic algorithms in search, optimization, and machine learning. Addion Wesley, 1989, 102 (1989), 36.","journal-title":"Addion Wesley"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems.","author":"Hegde Kartik","unstructured":"Kartik Hegde , Po-An Tsai , Sitao Huang , Vikas Chandra , Angshuman Parashar , and Christopher W. Fletcher . 2021. Mind mappings: enabling efficient algorithm-accelerator mapping space search . Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems. Kartik Hegde, Po-An Tsai, Sitao Huang, Vikas Chandra, Angshuman Parashar, and Christopher W. Fletcher. 2021. Mind mappings: enabling efficient algorithm-accelerator mapping space search. Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems."},{"key":"e_1_3_2_1_40_1","volume-title":"Intel Nervana Neural Network Processor-T (NNP-T) Fused Floating Point Many-Term Dot Product. In 2020 IEEE 27th Symposium on Computer Arithmetic (ARITH). 133\u2013136","author":"Hickmann Brian","year":"2020","unstructured":"Brian Hickmann , Jieasheng Chen , Michael Rotzin , Andrew Yang , Maciej Urbanski , and Sasikanth Avancha . 2020 . Intel Nervana Neural Network Processor-T (NNP-T) Fused Floating Point Many-Term Dot Product. In 2020 IEEE 27th Symposium on Computer Arithmetic (ARITH). 133\u2013136 . Brian Hickmann, Jieasheng Chen, Michael Rotzin, Andrew Yang, Maciej Urbanski, and Sasikanth Avancha. 2020. Intel Nervana Neural Network Processor-T (NNP-T) Fused Floating Point Many-Term Dot Product. In 2020 IEEE 27th Symposium on Computer Arithmetic (ARITH). 133\u2013136."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1177\/003754979406200405"},{"key":"e_1_3_2_1_42_1","unstructured":"Zhe Jia Blake Tillman Marco Maggioni and Daniele Paolo Scarpazza. 2019. Dissecting the graphcore ipu architecture via microbenchmarking. arXiv preprint arXiv:1912.03413. \t\t\t\t  Zhe Jia Blake Tillman Marco Maggioni and Daniele Paolo Scarpazza. 2019. Dissecting the graphcore ipu architecture via microbenchmarking. arXiv preprint arXiv:1912.03413."},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence, 579\u2013584","volume":"2","author":"Jeffrey","unstructured":"Jeffrey A. Joines and Christopher R. Houck. 1994. On the use of non-stationary penalty functions to solve nonlinear constrained optimization problems with GA\u2019s . Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence, 579\u2013584 vol. 2 . Jeffrey A. Joines and Christopher R. Houck. 1994. On the use of non-stationary penalty functions to solve nonlinear constrained optimization problems with GA\u2019s. Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence, 579\u2013584 vol.2."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1162\/evco.1999.7.1.19"},{"key":"e_1_3_2_1_46_1","first-page":"2010","volume-title":"Appl. Comput. Intell. Soft Comput.","author":"Kramer Oliver","year":"2010","unstructured":"Oliver Kramer . 2010 . A Review of Constraint-Handling Techniques for Evolution Strategies . Appl. Comput. Intell. Soft Comput. , 2010 (2010), 185063:1\u2013185063:11. Oliver Kramer. 2010. A Review of Constraint-Handling Techniques for Evolution Strategies. Appl. Comput. Intell. Soft Comput., 2010 (2010), 185063:1\u2013185063:11."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275055"},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 369\u2013381","author":"Liu Daofu","year":"2015","unstructured":"Daofu Liu , Tianshi Chen , Shaoli Liu , Jinhong Zhou , Shengyuan Zhou , Olivier Teman , Xiaobing Feng , Xuehai Zhou , and Yunji Chen . 2015 . PuDianNao : A Polyvalent Machine Learning Accelerator . In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 369\u2013381 . Daofu Liu, Tianshi Chen, Shaoli Liu, Jinhong Zhou, Shengyuan Zhou, Olivier Teman, Xiaobing Feng, Xuehai Zhou, and Yunji Chen. 2015. PuDianNao : A Polyvalent Machine Learning Accelerator. In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 369\u2013381."},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the 43rd ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 393\u2013405","author":"Liu Shaoli","year":"2016","unstructured":"Shaoli Liu , Zidong Du , Jinhua Tao , Dong Han , Tao Luo , Yuan Xie , Yunji Chen , and Tianshi Chen . 2016 . Cambricon: An instruction set architecture for neural networks . In Proceedings of the 43rd ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 393\u2013405 . Shaoli Liu, Zidong Du, Jinhua Tao, Dong Han, Tao Luo, Yuan Xie, Yunji Chen, and Tianshi Chen. 2016. Cambricon: An instruction set architecture for neural networks. In Proceedings of the 43rd ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 393\u2013405."},{"key":"e_1_3_2_1_50_1","volume-title":"Proceedings of the 2019 USENIX Conference on Usenix Annual Technical Conference (ATC). 1025\u20131040","author":"Liu Yizhi","year":"2019","unstructured":"Yizhi Liu , Yao Wang , Ruofei Yu , Mu Li , Vin Sharma , and Yida Wang . 2019 . Optimizing CNN Model Inference on CPUs . In Proceedings of the 2019 USENIX Conference on Usenix Annual Technical Conference (ATC). 1025\u20131040 . Yizhi Liu, Yao Wang, Ruofei Yu, Mu Li, Vin Sharma, and Yida Wang. 2019. Optimizing CNN Model Inference on CPUs. In Proceedings of the 2019 USENIX Conference on Usenix Annual Technical Conference (ATC). 1025\u20131040."},{"key":"e_1_3_2_1_51_1","volume-title":"2007 IEEE Congress on Evolutionary Computation, 935\u2013942","author":"Lukasiewycz Martin","year":"2007","unstructured":"Martin Lukasiewycz , Michael Gla\u00df , Christian Haubelt , and J\u00fcrgen Teich . 2007 . SAT-decoding in evolutionary algorithms for discrete constrained optimization problems . 2007 IEEE Congress on Evolutionary Computation, 935\u2013942 . Martin Lukasiewycz, Michael Gla\u00df, Christian Haubelt, and J\u00fcrgen Teich. 2007. SAT-decoding in evolutionary algorithms for discrete constrained optimization problems. 2007 IEEE Congress on Evolutionary Computation, 935\u2013942."},{"key":"e_1_3_2_1_52_1","volume-title":"Coello Coello","author":"Mezura-Montes Efr\u00e9n","year":"2008","unstructured":"Efr\u00e9n Mezura-Montes and Carlos A . Coello Coello . 2008 . Constrained Optimization via Multiobjective Evolutionary Algorithms. In Multiobjective Problem Solving from Nature . Efr\u00e9n Mezura-Montes and Carlos A. Coello Coello. 2008. Constrained Optimization via Multiobjective Evolutionary Algorithms. In Multiobjective Problem Solving from Nature."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2011.10.001"},{"key":"e_1_3_2_1_54_1","first-page":"2","volume-title":"Proceedings of 1995 IEEE International Conference on Evolutionary Computation","volume":"2","author":"Michalewicz Zbigniew","year":"1995","unstructured":"Zbigniew Michalewicz and Girish Nazhiyath . 1995 . Genocop III: a co-evolutionary algorithm for numerical optimization problems with nonlinear constraints . Proceedings of 1995 IEEE International Conference on Evolutionary Computation , 2 (1995), 647\u2013651 vol. 2 . Zbigniew Michalewicz and Girish Nazhiyath. 1995. Genocop III: a co-evolutionary algorithm for numerical optimization problems with nonlinear constraints. Proceedings of 1995 IEEE International Conference on Evolutionary Computation, 2 (1995), 647\u2013651 vol.2."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2019.2928962"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925952"},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the 47th ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 349\u2013362","author":"Narayanan Surya","year":"2020","unstructured":"Surya Narayanan , Karl Taht , Rajeev Balasubramonian , Edouard Giacomin , and Pierre-Emmanuel Gaillardon . 2020 . SpinalFlow: An Architecture and Dataflow Tailored for Spiking Neural Networks . In Proceedings of the 47th ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 349\u2013362 . Surya Narayanan, Karl Taht, Rajeev Balasubramonian, Edouard Giacomin, and Pierre-Emmanuel Gaillardon. 2020. SpinalFlow: An Architecture and Dataflow Tailored for Spiking Neural Networks. In Proceedings of the 47th ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 349\u2013362."},{"key":"e_1_3_2_1_58_1","volume-title":"Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence, 548\u2013553","volume":"2","author":"Orvosh David","year":"1994","unstructured":"David Orvosh and Lawrence Davis . 1994 . Using a genetic algorithm to optimize problems with feasibility constraints . Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence, 548\u2013553 vol. 2 . David Orvosh and Lawrence Davis. 1994. Using a genetic algorithm to optimize problems with feasibility constraints. Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence, 548\u2013553 vol.2."},{"key":"e_1_3_2_1_59_1","volume-title":"Proceedings of the 34th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI). 519\u2013530","author":"Ragan-Kelley Jonathan","year":"2013","unstructured":"Jonathan Ragan-Kelley , Connelly Barnes , Andrew Adams , Sylvain Paris , Fr\u00e9do Durand , and Saman Amarasinghe . 2013 . Halide: A Language and Compiler for Optimizing Parallelism, Locality, and Recomputation in Image Processing Pipelines . In Proceedings of the 34th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI). 519\u2013530 . Jonathan Ragan-Kelley, Connelly Barnes, Andrew Adams, Sylvain Paris, Fr\u00e9do Durand, and Saman Amarasinghe. 2013. Halide: A Language and Compiler for Optimizing Parallelism, Locality, and Recomputation in Image Processing Pipelines. In Proceedings of the 34th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI). 519\u2013530."},{"key":"e_1_3_2_1_60_1","unstructured":"Khaled M. Rasheed. 1998. An Adaptive Penalty Approach for Constrained Genetic-Algorithm Optimization. \t\t\t\t  Khaled M. Rasheed. 1998. An Adaptive Penalty Approach for Constrained Genetic-Algorithm Optimization."},{"key":"e_1_3_2_1_61_1","volume-title":"Amitay Isaacs, and Warren F. Smith.","author":"Ray Tapabrata","year":"2009","unstructured":"Tapabrata Ray , Hemant Kumar Singh , Amitay Isaacs, and Warren F. Smith. 2009 . Infeasibility Driven Evolutionary Algorithm for Constrained Optimization . Tapabrata Ray, Hemant Kumar Singh, Amitay Isaacs, and Warren F. Smith. 2009. Infeasibility Driven Evolutionary Algorithm for Constrained Optimization."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/4235.873238"},{"key":"e_1_3_2_1_63_1","series-title":"Sixth-generation computer technology series.","volume-title":"Evolution and optimum seeking","author":"Schwefel Hans-Paul","unstructured":"Hans-Paul Schwefel . 1995. Evolution and optimum seeking . In Sixth-generation computer technology series. Hans-Paul Schwefel. 1995. Evolution and optimum seeking. In Sixth-generation computer technology series."},{"key":"e_1_3_2_1_64_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations.","author":"Simonyan K.","unstructured":"K. Simonyan and A. Zisserman . 2015 . Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations. K. Simonyan and A. Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_65_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2818\u20132826","author":"Szegedy Christian","year":"2016","unstructured":"Christian Szegedy , Vincent Vanhoucke , Sergey Ioffe , Jonathon Shlens , and Zbigniew Wojna . 2016 . Rethinking the Inception Architecture for Computer Vision . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2818\u20132826 . Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. 2016. Rethinking the Inception Architecture for Computer Vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2818\u20132826."},{"key":"e_1_3_2_1_66_1","unstructured":"Nicolas Vasilache Oleksandr Zinenko Theodoros Theodoridis Priya Goyal Zachary DeVito William S Moses Sven Verdoolaege Andrew Adams and Albert Cohen. 2018. Tensor comprehensions: Framework-agnostic high-performance machine learning abstractions. arXiv preprint arXiv:1802.04730. \t\t\t\t  Nicolas Vasilache Oleksandr Zinenko Theodoros Theodoridis Priya Goyal Zachary DeVito William S Moses Sven Verdoolaege Andrew Adams and Albert Cohen. 2018. Tensor comprehensions: Framework-agnostic high-performance machine learning abstractions. arXiv preprint arXiv:1802.04730."},{"key":"e_1_3_2_1_67_1","volume-title":"UNIT: Unifying Tensorized Instruction Compilation. In 2021 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO). 77\u201389","author":"Weng Jian","year":"2021","unstructured":"Jian Weng , Animesh Jain , Jie Wang , Leyuan Wang , Yida Wang , and Tony Nowatzki . 2021 . UNIT: Unifying Tensorized Instruction Compilation. In 2021 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO). 77\u201389 . Jian Weng, Animesh Jain, Jie Wang, Leyuan Wang, Yida Wang, and Tony Nowatzki. 2021. UNIT: Unifying Tensorized Instruction Compilation. In 2021 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO). 77\u201389."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/4235.585889"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.3390\/mca10010045"},{"key":"e_1_3_2_1_70_1","volume-title":"Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation (PLDI). 1233\u20131248","author":"Zhao Jie","year":"2021","unstructured":"Jie Zhao , Bojie Li , Wang Nie , Zhen Geng , Renwei Zhang , Xiong Gao , Bin Cheng , Chen Wu , Yun Cheng , Zheng Li , Peng Di , Kun Zhang , and Xuefeng Jin . 2021 . AKG: automatic kernel generation for neural processing units using polyhedral transformations . In Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation (PLDI). 1233\u20131248 . Jie Zhao, Bojie Li, Wang Nie, Zhen Geng, Renwei Zhang, Xiong Gao, Bin Cheng, Chen Wu, Yun Cheng, Zheng Li, Peng Di, Kun Zhang, and Xuefeng Jin. 2021. AKG: automatic kernel generation for neural processing units using polyhedral transformations. In Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation (PLDI). 1233\u20131248."},{"key":"e_1_3_2_1_71_1","volume-title":"Proceedings of 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI). 863\u2013879","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 , Joseph Gonzalez , and Ion Stoica . 2020 . Ansor: Generating High-performance Tensor Programs for Deep Learning . In Proceedings of 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI). 863\u2013879 . Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, Joseph Gonzalez, and Ion Stoica. 2020. Ansor: Generating High-performance Tensor Programs for Deep Learning. In Proceedings of 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI). 863\u2013879."},{"key":"e_1_3_2_1_72_1","volume-title":"Proceedings of the 49th Annual International Symposium on Computer Architecture (ISCA). 874\u2013887","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 . 2022 . AMOS: Enabling Automatic Mapping for Tensor Computations On Spatial Accelerators with Hardware Abstraction . In Proceedings of the 49th Annual International Symposium on Computer Architecture (ISCA). 874\u2013887 . Size Zheng, Renze Chen, Anjiang Wei, Yicheng Jin, Qin Han, Liqiang Lu, Bingyang Wu, Xiuhong Li, Shengen Yan, and Yun Liang. 2022. AMOS: Enabling Automatic Mapping for Tensor Computations On Spatial Accelerators with Hardware Abstraction. In Proceedings of the 49th Annual International Symposium on Computer Architecture (ISCA). 874\u2013887."},{"key":"e_1_3_2_1_73_1","volume-title":"Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 859\u2013873","author":"Zheng Size","year":"2020","unstructured":"Size Zheng , Yun Liang , Shuo Wang , Renze Chen , and Kaiwen Sheng . 2020 . FlexTensor: An Automatic Schedule Exploration and Optimization Framework for Tensor Computation on Heterogeneous System . In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 859\u2013873 . Size Zheng, Yun Liang, Shuo Wang, Renze Chen, and Kaiwen Sheng. 2020. FlexTensor: An Automatic Schedule Exploration and Optimization Framework for Tensor Computation on Heterogeneous System. In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 859\u2013873."}],"event":{"name":"ASPLOS '23: 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","location":"Vancouver BC Canada","acronym":"ASPLOS '23","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 28th 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\/3582016.3582061","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:46Z","timestamp":1750178806000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3582016.3582061"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,25]]},"references-count":73,"alternative-id":["10.1145\/3582016.3582061","10.1145\/3582016"],"URL":"https:\/\/doi.org\/10.1145\/3582016.3582061","relation":{},"subject":[],"published":{"date-parts":[[2023,3,25]]},"assertion":[{"value":"2023-03-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}