{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:19:45Z","timestamp":1774365585133,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":80,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,11,17]],"date-time":"2019-11-17T00:00:00Z","timestamp":1573948800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100007000","name":"Laboratory Directed Research and Development","doi-asserted-by":"publisher","award":["90001-N90615"],"award-info":[{"award-number":["90001-N90615"]}],"id":[{"id":"10.13039\/100007000","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011661","name":"Pacific Northwest National Laboratory","doi-asserted-by":"publisher","award":["HPDA-SBLAS"],"award-info":[{"award-number":["HPDA-SBLAS"]}],"id":[{"id":"10.13039\/100011661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006192","name":"Advanced Scientific Computing Research","doi-asserted-by":"publisher","award":["66150-Center for Advanced Technology Evaluation (CENATE)"],"award-info":[{"award-number":["66150-Center for Advanced Technology Evaluation (CENATE)"]}],"id":[{"id":"10.13039\/100006192","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,11,17]]},"DOI":"10.1145\/3295500.3356169","type":"proceedings-article","created":{"date-parts":[[2019,11,7]],"date-time":"2019-11-07T19:43:22Z","timestamp":1573155802000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":36,"title":["BSTC"],"prefix":"10.1145","author":[{"given":"Ang","family":"Li","sequence":"first","affiliation":[{"name":"Pacific Northwest National Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Geng","sequence":"additional","affiliation":[{"name":"Boston University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Boston University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Herbordt","sequence":"additional","affiliation":[{"name":"Boston University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuaiwen Leon","family":"Song","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Barker","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,11,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/0370-2693(92)91580-3"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2018.00052"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1711456115"},{"key":"e_1_3_2_1_4_1","volume-title":"Parameterized machine learning for high-energy physics. arXiv preprint arXiv:1601.07913","author":"Baldi Pierre","year":"2016","unstructured":"Pierre Baldi , Kyle Cranmer , Taylor Faucett , Peter Sadowski , and Daniel Whiteson . 2016. Parameterized machine learning for high-energy physics. arXiv preprint arXiv:1601.07913 ( 2016 ). Pierre Baldi, Kyle Cranmer, Taylor Faucett, Peter Sadowski, and Daniel Whiteson. 2016. Parameterized machine learning for high-energy physics. arXiv preprint arXiv:1601.07913 (2016)."},{"key":"e_1_3_2_1_5_1","volume-title":"Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis. arXiv preprint arXiv:1802.09941","author":"Ben-Nun Tal","year":"2018","unstructured":"Tal Ben-Nun and Torsten Hoefler . 2018. Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis. arXiv preprint arXiv:1802.09941 ( 2018 ). Tal Ben-Nun and Torsten Hoefler. 2018. Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis. arXiv preprint arXiv:1802.09941 (2018)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926259"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.05.005"},{"key":"e_1_3_2_1_8_1","volume-title":"Tenth International Workshop on Frontiers in Handwriting Recognition. Suvisoft.","author":"Chellapilla Kumar","year":"2006","unstructured":"Kumar Chellapilla , Sidd Puri , and Patrice Simard . 2006 . High performance convolutional neural networks for document processing . In Tenth International Workshop on Frontiers in Handwriting Recognition. Suvisoft. Kumar Chellapilla, Sidd Puri, and Patrice Simard. 2006. High performance convolutional neural networks for document processing. In Tenth International Workshop on Frontiers in Handwriting Recognition. Suvisoft."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03592-1_16"},{"key":"e_1_3_2_1_10_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 ). 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_11_1","volume-title":"Binaryconnect: Training deep neural networks with binary weights during propagations. In Advances in Neural Information Processing Systems. 3123--3131.","author":"Courbariaux Matthieu","year":"2015","unstructured":"Matthieu Courbariaux , Yoshua Bengio , and Jean-Pierre David . 2015 . Binaryconnect: Training deep neural networks with binary weights during propagations. In Advances in Neural Information Processing Systems. 3123--3131. Matthieu Courbariaux, Yoshua Bengio, and Jean-Pierre David. 2015. Binaryconnect: Training deep neural networks with binary weights during propagations. In Advances in Neural Information Processing Systems. 3123--3131."},{"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 ). 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","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_14_1","volume-title":"Improved binary network training. arXiv preprint arXiv:1812.11800","author":"Darabi Sajad","year":"2018","unstructured":"Sajad Darabi , Mouloud Belbahri , Matthieu Courbariaux , and Vahid Partovi Nia . 2018. BNN+ : Improved binary network training. arXiv preprint arXiv:1812.11800 ( 2018 ). Sajad Darabi, Mouloud Belbahri, Matthieu Courbariaux, and Vahid Partovi Nia. 2018. BNN+: Improved binary network training. arXiv preprint arXiv:1812.11800 (2018)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/0010-4655(88)90004-5"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/23.106627"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_18_1","unstructured":"US DOE. 2018. Sensor Technologies and Data Analytics. https:\/\/www.smartgrid.gov\/document\/Sensor_Technologies_and_Data_Analytics_2018.html  US DOE. 2018. Sensor Technologies and Data Analytics. https:\/\/www.smartgrid.gov\/document\/Sensor_Technologies_and_Data_Analytics_2018.html"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPIN.2016.7743581"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1565694.1565702"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2504730.2504756"},{"key":"e_1_3_2_1_22_1","volume-title":"Attacking Binarized Neural Networks. arXiv preprint arXiv:1711.00449","author":"Galloway Angus","year":"2017","unstructured":"Angus Galloway , Graham W Taylor , and Medhat Moussa . 2017. Attacking Binarized Neural Networks. arXiv preprint arXiv:1711.00449 ( 2017 ). Angus Galloway, Graham W Taylor, and Medhat Moussa. 2017. Attacking Binarized Neural Networks. arXiv preprint arXiv:1711.00449 (2017)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2019.00-43"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330386"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2018.00018"},{"key":"e_1_3_2_1_26_1","unstructured":"Google. 2018. TensorFlow: Adding a New Op. http:\/\/www.tensorflow.org\/extend\/adding_an_op  Google. 2018. TensorFlow: Adding a New Op. http:\/\/www.tensorflow.org\/extend\/adding_an_op"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2749472"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_1_30_1","volume-title":"Loss-aware binarization of deep networks. arXiv preprint arXiv:1611.01600","author":"Hou Lu","year":"2016","unstructured":"Lu Hou , Quanming Yao , and James T Kwok . 2016. Loss-aware binarization of deep networks. arXiv preprint arXiv:1611.01600 ( 2016 ). Lu Hou, Quanming Yao, and James T Kwok. 2016. Loss-aware binarization of deep networks. arXiv preprint arXiv:1611.01600 (2016)."},{"key":"e_1_3_2_1_31_1","volume-title":"BitFlow: Exploiting Vector Parallelism for Binary Neural Networks on CPU. In 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 244--253","author":"Hu Yuwei","year":"2018","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 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 244--253 . 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 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 244--253."},{"key":"e_1_3_2_1_32_1","unstructured":"Itay Hubara Matthieu Courbariaux Daniel Soudry Ran El-Yaniv and Yoshua Bengio. 2016. Binarized neural networks. In Advances in Neural Information Processing Systems. 4107--4115.  Itay Hubara Matthieu Courbariaux Daniel Soudry Ran El-Yaniv and Yoshua Bengio. 2016. Binarized neural networks. In Advances in Neural Information Processing Systems. 4107--4115."},{"key":"e_1_3_2_1_33_1","volume-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy . 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 ( 2015 ). Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303958"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-61510-5_1"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-94144-8_27"},{"key":"e_1_3_2_1_38_1","volume-title":"The CIFAR-10 dataset. online: http:\/\/www.cs.toronto.edu\/kriz\/cifar.html","author":"Krizhevsky Alex","year":"2014","unstructured":"Alex Krizhevsky , Vinod Nair , and Geoffrey Hinton . 2014. The CIFAR-10 dataset. online: http:\/\/www.cs.toronto.edu\/kriz\/cifar.html ( 2014 ). Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton. 2014. The CIFAR-10 dataset. online: http:\/\/www.cs.toronto.edu\/kriz\/cifar.html (2014)."},{"key":"e_1_3_2_1_39_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105.  Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105."},{"key":"e_1_3_2_1_40_1","volume-title":"Self-Binarizing Networks. arXiv preprint arXiv:1902.00730","author":"Lahoud Fayez","year":"2019","unstructured":"Fayez Lahoud , Radhakrishna Achanta , Pablo M\u00e1rquez-Neila , and Sabine S\u00fcsstrunk . 2019. Self-Binarizing Networks. arXiv preprint arXiv:1902.00730 ( 2019 ). Fayez Lahoud, Radhakrishna Achanta, Pablo M\u00e1rquez-Neila, and Sabine S\u00fcsstrunk. 2019. Self-Binarizing Networks. arXiv preprint arXiv:1902.00730 (2019)."},{"key":"e_1_3_2_1_41_1","volume-title":"XLA: TensorFlow, compiled. TensorFlow Dev Summit","author":"Leary Chris","year":"2017","unstructured":"Chris Leary and Todd Wang . 2017 . XLA: TensorFlow, compiled. TensorFlow Dev Summit (2017). Chris Leary and Todd Wang. 2017. XLA: TensorFlow, compiled. TensorFlow Dev Summit (2017)."},{"key":"e_1_3_2_1_42_1","volume-title":"MNIST handwritten digit database. AT&T Labs [Online]. Available: http:\/\/yann.lecun.com\/exdb\/mnist 2","author":"LeCun Yann","year":"2010","unstructured":"Yann LeCun , Corinna Cortes , and CJ Burges . 2010. MNIST handwritten digit database. AT&T Labs [Online]. Available: http:\/\/yann.lecun.com\/exdb\/mnist 2 ( 2010 ). Yann LeCun, Corinna Cortes, and CJ Burges. 2010. MNIST handwritten digit database. AT&T Labs [Online]. Available: http:\/\/yann.lecun.com\/exdb\/mnist 2 (2010)."},{"key":"e_1_3_2_1_43_1","volume-title":"International conference on artificial neural networks","volume":"60","author":"LeCun Yann","year":"1995","unstructured":"Yann LeCun , LD Jackel , Leon Bottou , A Brunot , Corinna Cortes , JS Denker , Harris Drucker , I Guyon , UA Muller , Eduard Sackinger , 1995 . Comparison of learning algorithms for handwritten digit recognition . In International conference on artificial neural networks , Vol. 60 . Perth, Australia, 53--60. Yann LeCun, LD Jackel, Leon Bottou, A Brunot, Corinna Cortes, JS Denker, Harris Drucker, I Guyon, UA Muller, Eduard Sackinger, et al. 1995. Comparison of learning algorithms for handwritten digit recognition. In International conference on artificial neural networks, Vol. 60. Perth, Australia, 53--60."},{"key":"e_1_3_2_1_44_1","volume-title":"Automated verification of neural networks: Advances, challenges and perspectives. arXiv preprint arXiv:1805.09938","author":"Leofante Francesco","year":"2018","unstructured":"Francesco Leofante , Nina Narodytska , Luca Pulina , and Armando Tacchella . 2018. Automated verification of neural networks: Advances, challenges and perspectives. arXiv preprint arXiv:1805.09938 ( 2018 ). Francesco Leofante, Nina Narodytska, Luca Pulina, and Armando Tacchella. 2018. Automated verification of neural networks: Advances, challenges and perspectives. arXiv preprint arXiv:1805.09938 (2018)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205294"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.89"},{"key":"e_1_3_2_1_47_1","volume-title":"Jieyang Chen, Jiajia Li, Xu Liu, Nathan Tallent, and Kevin Barker.","author":"Li Ang","year":"2019","unstructured":"Ang Li , Shuaiwen Leon Song , Jieyang Chen, Jiajia Li, Xu Liu, Nathan Tallent, and Kevin Barker. 2019 . Evaluating Modern GPU Interconnect: PC Ie , NVLink, NV-SLI, NVSwitch and GPUDirect . arXiv preprint arXiv:1903.04611 (2019). Ang Li, Shuaiwen Leon Song, Jieyang Chen, Jiajia Li, Xu Liu, Nathan Tallent, and Kevin Barker. 2019. Evaluating Modern GPU Interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect. arXiv preprint arXiv:1903.04611 (2019)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573483"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.3850\/9783981537079_0394"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093315.3037709"},{"key":"e_1_3_2_1_51_1","unstructured":"Ang Li YC Tay Akash Kumar and Henk Corporaal. [n. d.]. Transit: A visual analytical model for multithreaded machines. In HPDC-15. ACM.  Ang Li YC Tay Akash Kumar and Henk Corporaal. [n. d.]. Transit: A visual analytical model for multithreaded machines. In HPDC-15. ACM."},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the 29th ACM on International Conference on Supercomputing. ACM, 109--118","author":"Li Ang","unstructured":"Ang Li , Gert-Jan van den Braak, Henk Corporaal, and Akash Kumar. 2015. Fine-grained synchronizations and dataflow programming on GPUs . In Proceedings of the 29th ACM on International Conference on Supercomputing. ACM, 109--118 . Ang Li, Gert-Jan van den Braak, Henk Corporaal, and Akash Kumar. 2015. Fine-grained synchronizations and dataflow programming on GPUs. In Proceedings of the 29th ACM on International Conference on Supercomputing. ACM, 109--118."},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. ACM, 17","author":"Li Ang","unstructured":"Ang Li , Gert-Jan van den Braak, Akash Kumar, and Henk Corporaal. 2015. Adaptive and transparent cache bypassing for GPUs . In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. ACM, 17 . Ang Li, Gert-Jan van den Braak, Akash Kumar, and Henk Corporaal. 2015. Adaptive and transparent cache bypassing for GPUs. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. ACM, 17."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.09.046"},{"key":"e_1_3_2_1_55_1","series-title":"Journal of Physics: Conference Series","volume-title":"LHCb topological trigger reoptimization","author":"Likhomanenko Tatiana","year":"2025","unstructured":"Tatiana Likhomanenko , Philip Ilten , Egor Khairullin , Alex Rogozhnikov , Andrey Ustyuzhanin , and Michael Williams . 2015. LHCb topological trigger reoptimization . In Journal of Physics: Conference Series , Vol. 664 . IOP Publishing , 08 2025 . Tatiana Likhomanenko, Philip Ilten, Egor Khairullin, Alex Rogozhnikov, Andrey Ustyuzhanin, and Michael Williams. 2015. LHCb topological trigger reoptimization. In Journal of Physics: Conference Series, Vol. 664. IOP Publishing, 082025."},{"key":"e_1_3_2_1_56_1","unstructured":"Xiaofan Lin Cong Zhao and Wei Pan. 2017. Towards accurate binary convolutional neural network. In Advances in Neural Information Processing Systems. 345--353.  Xiaofan Lin Cong Zhao and Wei Pan. 2017. Towards accurate binary convolutional neural network. In Advances in Neural Information Processing Systems. 345--353."},{"key":"e_1_3_2_1_57_1","volume-title":"Finding gluon jets with a neural trigger. Physical review letters 65, 11","author":"L\u00f6nnblad Leif","year":"1990","unstructured":"Leif L\u00f6nnblad , Carsten Peterson , and Thorsteinn R\u00f6gnvaldsson . 1990. Finding gluon jets with a neural trigger. Physical review letters 65, 11 ( 1990 ), 1321. Leif L\u00f6nnblad, Carsten Peterson, and Thorsteinn R\u00f6gnvaldsson. 1990. Finding gluon jets with a neural trigger. Physical review letters 65, 11 (1990), 1321."},{"key":"e_1_3_2_1_58_1","first-page":"1","article-title":"Binary volumetric convolutional neural networks for 3--d object recognition","volume":"99","author":"Ma Chao","year":"2018","unstructured":"Chao Ma , Yulan Guo , Yinjie Lei , and Wei An . 2018 . Binary volumetric convolutional neural networks for 3--d object recognition . IEEE Transactions on Instrumentation and Measurement 99 (2018), 1 -- 11 . Chao Ma, Yulan Guo, Yinjie Lei, and Wei An. 2018. Binary volumetric convolutional neural networks for 3--d object recognition. IEEE Transactions on Instrumentation and Measurement 99 (2018), 1--11.","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_3_2_1_59_1","volume-title":"Efficient Super Resolution Using Binarized Neural Network. arXiv preprint arXiv:1812.06378","author":"Ma Yinglan","year":"2018","unstructured":"Yinglan Ma , Hongyu Xiong , Zhe Hu , and Lizhuang Ma. 2018. Efficient Super Resolution Using Binarized Neural Network. arXiv preprint arXiv:1812.06378 ( 2018 ). Yinglan Ma, Hongyu Xiong, Zhe Hu, and Lizhuang Ma. 2018. Efficient Super Resolution Using Binarized Neural Network. arXiv preprint arXiv:1812.06378 (2018)."},{"key":"e_1_3_2_1_60_1","volume-title":"Embedded binarized neural networks. arXiv preprint arXiv:1709.02260","author":"McDanel Bradley","year":"2017","unstructured":"Bradley McDanel , Surat Teerapittayanon , and HT Kung . 2017. Embedded binarized neural networks. arXiv preprint arXiv:1709.02260 ( 2017 ). Bradley McDanel, Surat Teerapittayanon, and HT Kung. 2017. Embedded binarized neural networks. arXiv preprint arXiv:1709.02260 (2017)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"crossref","unstructured":"Nina Narodytska. 2018. Formal Analysis of Deep Binarized Neural Networks.. In IJCAI. 5692--5696.  Nina Narodytska. 2018. Formal Analysis of Deep Binarized Neural Networks.. In IJCAI. 5692--5696.","DOI":"10.24963\/ijcai.2018\/811"},{"key":"e_1_3_2_1_62_1","volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence.","author":"Narodytska Nina","year":"2018","unstructured":"Nina Narodytska , Shiva Kasiviswanathan , Leonid Ryzhyk , Mooly Sagiv , and Toby Walsh . 2018 . Verifying properties of binarized deep neural networks . In Thirty-Second AAAI Conference on Artificial Intelligence. Nina Narodytska, Shiva Kasiviswanathan, Leonid Ryzhyk, Mooly Sagiv, and Toby Walsh. 2018. Verifying properties of binarized deep neural networks. In Thirty-Second AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_63_1","volume-title":"Leonid Ryzhyk, Mooly Sagiv, and Toby Walsh.","author":"Narodytska Nina","year":"2017","unstructured":"Nina Narodytska , Shiva Prasad Kasiviswanathan , Leonid Ryzhyk, Mooly Sagiv, and Toby Walsh. 2017 . Verifying properties of binarized deep neural networks. arXiv preprint arXiv:1709.06662 (2017). Nina Narodytska, Shiva Prasad Kasiviswanathan, Leonid Ryzhyk, Mooly Sagiv, and Toby Walsh. 2017. Verifying properties of binarized deep neural networks. arXiv preprint arXiv:1709.06662 (2017)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2016.7929192"},{"key":"e_1_3_2_1_65_1","unstructured":"NVIDIA. 2018. CUDA Programming Guide. http:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide  NVIDIA. 2018. CUDA Programming Guide. http:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451160"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/2001858.2002031"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1016\/0168-9002(89)91300-4"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1016\/0010-4655(94)90120-1"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"crossref","unstructured":"Buser Sayand Scott Sanner. 2018. Planning in Factored State and Action Spaces with Learned Binarized Neural Network Transition Models.. In IJCAI. 4815--4821.  Buser Sayand Scott Sanner. 2018. Planning in Factored State and Action Spaces with Learned Binarized Neural Network Transition Models.. In IJCAI. 4815--4821.","DOI":"10.24963\/ijcai.2018\/669"},{"key":"e_1_3_2_1_72_1","volume-title":"Binary generative adversarial networks for image retrieval. arXiv preprint arXiv:1708.04150","author":"Song Jingkuan","year":"2017","unstructured":"Jingkuan Song . 2017. Binary generative adversarial networks for image retrieval. arXiv preprint arXiv:1708.04150 ( 2017 ). Jingkuan Song. 2017. Binary generative adversarial networks for image retrieval. arXiv preprint arXiv:1708.04150 (2017)."},{"key":"e_1_3_2_1_73_1","volume-title":"David Patterson, Michael W Mahoney, Randy Katz, Anthony D Joseph, Michael Jordan, Joseph M Hellerstein, Joseph E Gonzalez, et al.","author":"Stoica Ion","year":"2017","unstructured":"Ion Stoica , Dawn Song , Raluca Ada Popa , David Patterson, Michael W Mahoney, Randy Katz, Anthony D Joseph, Michael Jordan, Joseph M Hellerstein, Joseph E Gonzalez, et al. 2017 . Aberkeley view of systems challenges for ai. arXiv preprint arXiv:1712.05855 (2017). Ion Stoica, Dawn Song, Raluca Ada Popa, David Patterson, Michael W Mahoney, Randy Katz, Anthony D Joseph, Michael Jordan, Joseph M Hellerstein, Joseph E Gonzalez, et al. 2017. Aberkeley view of systems challenges for ai. arXiv preprint arXiv:1712.05855 (2017)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"crossref","unstructured":"Wei Tang Gang Hua and Liang Wang. 2017. How to train a compact binary neural network with high accuracy?. In AAAI. 2625--2631.  Wei Tang Gang Hua and Liang Wang. 2017. How to train a compact binary neural network with high accuracy?. In AAAI. 2625--2631.","DOI":"10.1609\/aaai.v31i1.10862"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021744"},{"key":"e_1_3_2_1_76_1","volume-title":"Tensor Comprehensions: Framework-Agnostic 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: Framework-Agnostic High-Performance Machine Learning Abstractions. arXiv preprint arXiv:1802.04730 (2018). 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 (2018)."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2013.05.067"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021741"},{"key":"e_1_3_2_1_79_1","volume-title":"DoReFa-Net: Training lowbitwidth 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 lowbitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160 ( 2016 ). Shuchang Zhou, Yuxin Wu, Zekun Ni, Xinyu Zhou, He Wen, and Yuheng Zou. 2016. DoReFa-Net: Training lowbitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160 (2016)."},{"key":"e_1_3_2_1_80_1","volume-title":"Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit? arXiv preprint arXiv:1806.07550","author":"Zhu Shilin","year":"2018","unstructured":"Shilin Zhu , XinDong, and Hao Su. 2018. Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit? arXiv preprint arXiv:1806.07550 ( 2018 ). Shilin Zhu, XinDong, and Hao Su. 2018. Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit? arXiv preprint arXiv:1806.07550 (2018)."}],"event":{"name":"SC '19: The International Conference for High Performance Computing, Networking, Storage, and Analysis","location":"Denver Colorado","acronym":"SC '19","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","IEEE CS"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3295500.3356169","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3295500.3356169","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3295500.3356169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:02:13Z","timestamp":1750208533000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3295500.3356169"}},"subtitle":["a novel binarized-soft-tensor-core design for accelerating bit-based approximated neural nets"],"short-title":[],"issued":{"date-parts":[[2019,11,17]]},"references-count":80,"alternative-id":["10.1145\/3295500.3356169","10.1145\/3295500"],"URL":"https:\/\/doi.org\/10.1145\/3295500.3356169","relation":{},"subject":[],"published":{"date-parts":[[2019,11,17]]},"assertion":[{"value":"2019-11-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}