{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T14:56:30Z","timestamp":1773413790212,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,2,4]],"date-time":"2017-02-04T00:00:00Z","timestamp":1486166400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,2,4]]},"DOI":"10.1145\/3038228.3038239","type":"proceedings-article","created":{"date-parts":[[2017,2,16]],"date-time":"2017-02-16T15:18:54Z","timestamp":1487258334000},"page":"63-72","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":55,"title":["DNNMark"],"prefix":"10.1145","author":[{"given":"Shi","family":"Dong","sequence":"first","affiliation":[{"name":"Northeastern University"}]},{"given":"David","family":"Kaeli","sequence":"additional","affiliation":[{"name":"Northeastern University"}]}],"member":"320","published-online":{"date-parts":[[2017,2,4]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg S. Corrado Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Ian Goodfellow Andrew Harp Geoffrey Irving Michael Isard Yangqing Jia Rafal Jozefowicz Lukasz Kaiser Manjunath Kudlur Josh Levenberg Dan Man\u00e9 Rajat Monga Sherry Moore Derek Murray Chris Olah Mike Schuster Jonathon Shlens Benoit Steiner Ilya Sutskever Kunal Talwar Paul Tucker Vincent Vanhoucke Vijay Vasudevan Fernanda Vi\u00e9gas Oriol Vinyals Pete Warden Martin Wattenberg Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. (2015). http:\/\/tensorflow.org\/  Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg S. Corrado Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Ian Goodfellow Andrew Harp Geoffrey Irving Michael Isard Yangqing Jia Rafal Jozefowicz Lukasz Kaiser Manjunath Kudlur Josh Levenberg Dan Man\u00e9 Rajat Monga Sherry Moore Derek Murray Chris Olah Mike Schuster Jonathon Shlens Benoit Steiner Ilya Sutskever Kunal Talwar Paul Tucker Vincent Vanhoucke Vijay Vasudevan Fernanda Vi\u00e9gas Oriol Vinyals Pete Warden Martin Wattenberg Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. (2015). http:\/\/tensorflow.org\/"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_3_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_4_1","volume-title":"Proceedings of the 30th International Conference on Machine Learning (ICML-13)","author":"Coates Adam","year":"2013","unstructured":"Adam Coates , Brody Huval , Tao Wang , David Wu , Bryan Catanzaro , and Ng Andrew . 2013 . Deep learning with COTS HPC systems . Proceedings of the 30th International Conference on Machine Learning (ICML-13) 28 (2013), 1337--1345. Adam Coates, Brody Huval, Tao Wang, David Wu, Bryan Catanzaro, and Ng Andrew. 2013. Deep learning with COTS HPC systems. Proceedings of the 30th International Conference on Machine Learning (ICML-13) 28 (2013), 1337--1345."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Ronald A. Cohen. 2011. Lateral Inhibition. Springer New York.  Ronald A. Cohen. 2011. Lateral Inhibition. Springer New York.","DOI":"10.1007\/978-0-387-79948-3_1379"},{"key":"e_1_3_2_1_6_1","unstructured":"NVIDIA Corporation. 2014. CUDA C Programming Guide. (2014).  NVIDIA Corporation. 2014. CUDA C Programming Guide. (2014)."},{"key":"e_1_3_2_1_7_1","unstructured":"NVIDIA Corporation. 2015. CuBlas library v7.5. (2015).  NVIDIA Corporation. 2015. CuBlas library v7.5. (2015)."},{"key":"e_1_3_2_1_8_1","unstructured":"NVIDIA Corporation. 2016. CuDNN library v5.0. (2016).  NVIDIA Corporation. 2016. CuDNN library v5.0. (2016)."},{"key":"e_1_3_2_1_9_1","unstructured":"Randima Fernando. 2004. GPU Gems: Programming Techniques Tips and Tricks for Real-Time Graphics. Pearson Higher Education.   Randima Fernando. 2004. GPU Gems: Programming Techniques Tips and Tricks for Real-Time Graphics. Pearson Higher Education."},{"key":"e_1_3_2_1_10_1","unstructured":"Google. 2016. How To Use gflags. (2016).  Google. 2016. How To Use gflags. (2016)."},{"key":"e_1_3_2_1_11_1","unstructured":"Google. 2016. How To Use Google Logging Library. (2016).  Google. 2016. How To Use Google Logging Library. (2016)."},{"key":"e_1_3_2_1_12_1","unstructured":"Erico Guizzo. 2016. How Google's Self-Driving Car Works. (2016).  Erico Guizzo. 2016. How Google's Self-Driving Car Works. (2016)."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML-15)","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy . 2015 . Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift . Proceedings of the 32nd International Conference on Machine Learning (ICML-15) (2015), 448--456. Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning (ICML-15) (2015), 448--456."},{"key":"e_1_3_2_1_14_1","volume-title":"Caffe: Convolutional Architecture for Fast Feature Embedding. arXiv preprint arXiv:1408.5093","author":"Jia Yangqing","year":"2014","unstructured":"Yangqing Jia , Evan Shelhamer , Jeff Donahue , Sergey Karayev , Jonathan Long , Ross Girshick , Sergio Guadarrama , and Trevor Darrell . 2014 . Caffe: Convolutional Architecture for Fast Feature Embedding. arXiv preprint arXiv:1408.5093 (2014). Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. 2014. Caffe: Convolutional Architecture for Fast Feature Embedding. arXiv preprint arXiv:1408.5093 (2014)."},{"key":"e_1_3_2_1_15_1","unstructured":"Alex Krizhevsky Vinod Nair and Geoffrey Hinton. 2009. CIFAR-10 (Canadian Institute for Advanced Research). (2009).  Alex Krizhevsky Vinod Nair and Geoffrey Hinton. 2009. CIFAR-10 (Canadian Institute for Advanced Research). (2009)."},{"key":"e_1_3_2_1_16_1","first-page":"1097","article-title":"ImageNet Classification with Deep Convolutional Neural Networks","volume":"25","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E Hinton . 2012 . ImageNet Classification with Deep Convolutional Neural Networks . Advances in Neural Information Processing Systems 25 (2012), 1097 -- 1105 . Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems 25 (2012), 1097--1105.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_17_1","volume-title":"Fast Algorithms for Convolutional Neural Networks. arXiv preprint arXiv:1509.09308","author":"Lavin Andrew","year":"2015","unstructured":"Andrew Lavin and Scott Gray . 2015. Fast Algorithms for Convolutional Neural Networks. arXiv preprint arXiv:1509.09308 ( 2015 ). Andrew Lavin and Scott Gray. 2015. Fast Algorithms for Convolutional Neural Networks. arXiv preprint arXiv:1509.09308 (2015)."},{"key":"e_1_3_2_1_18_1","unstructured":"Yann LeCun and Corinna Cortes. 2010. MNIST handwritten digit database. (2010).  Yann LeCun and Corinna Cortes. 2010. MNIST handwritten digit database. (2010)."},{"key":"e_1_3_2_1_19_1","volume-title":"Kepler\u2122 GK110.","author":"NVIDIA.","year":"2012","unstructured":"NVIDIA. 2012. NVIDIA's Next Generation CUDA\u2122 Compute Architecture , Kepler\u2122 GK110. ( 2012 ). NVIDIA. 2012. NVIDIA's Next Generation CUDA\u2122 Compute Architecture, Kepler\u2122 GK110. (2012)."},{"key":"e_1_3_2_1_20_1","unstructured":"NVIDIA. 2016. CUDA Toolkit Documentation. (2016).  NVIDIA. 2016. CUDA Toolkit Documentation. (2016)."},{"key":"e_1_3_2_1_21_1","unstructured":"NVIDIA. 2016. Tesla GPU Accelerators for Servers. (2016).  NVIDIA. 2016. Tesla GPU Accelerators for Servers. (2016)."},{"key":"e_1_3_2_1_22_1","volume-title":"Orr and Klaus-Robert Mueller (Eds.)","author":"Genevieve","year":"1998","unstructured":"Genevieve B. Orr and Klaus-Robert Mueller (Eds.) . 1998 . Neural Networks : Tricks of the Trade. Lecture Notes in Computer Science, Vol. 1524 . Springer . Genevieve B. Orr and Klaus-Robert Mueller (Eds.). 1998. Neural Networks: Tricks of the Trade. Lecture Notes in Computer Science, Vol. 1524. Springer."},{"key":"e_1_3_2_1_23_1","unstructured":"Victor Podlozhnyuk. 2007. FFT-based 2D convolution. (2007).  Victor Podlozhnyuk. 2007. FFT-based 2D convolution. (2007)."},{"key":"e_1_3_2_1_24_1","unstructured":"Victor Podlozhnyuk. 2013. Image Convolution with CUDA. (2013).  Victor Podlozhnyuk. 2013. Image Convolution with CUDA. (2013)."},{"key":"e_1_3_2_1_25_1","volume-title":"Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition. arXiv preprint arXiv:1402.1128","author":"Sak Haim","year":"2014","unstructured":"Haim Sak , Andrew Senior , and Franoise Beaufays . 2014. Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition. arXiv preprint arXiv:1402.1128 ( 2014 ). Haim Sak, Andrew Senior, and Franoise Beaufays. 2014. Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition. arXiv preprint arXiv:1402.1128 (2014)."},{"key":"e_1_3_2_1_26_1","unstructured":"David Silver and Google DeepMind Demis Hassabis. 2016. AlphaGo: Mastering the ancient game of Go with Machine Learning. (2016).  David Silver and Google DeepMind Demis Hassabis. 2016. AlphaGo: Mastering the ancient game of Go with Machine Learning. (2016)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"e_1_3_2_1_28_1","volume-title":"Theano: A Python framework for fast computation of mathematical expressions. arXiv e-prints abs\/1605.02688 (May","author":"Team Theano Development","year":"2016","unstructured":"Theano Development Team . 2016 . Theano: A Python framework for fast computation of mathematical expressions. arXiv e-prints abs\/1605.02688 (May 2016). Theano Development Team. 2016. Theano: A Python framework for fast computation of mathematical expressions. arXiv e-prints abs\/1605.02688 (May 2016)."}],"event":{"name":"PPoPP '17: 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","location":"Austin TX USA","acronym":"PPoPP '17","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the General Purpose GPUs"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3038228.3038239","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3038228.3038239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:03:11Z","timestamp":1750215791000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3038228.3038239"}},"subtitle":["A Deep Neural Network Benchmark Suite for GPUs"],"short-title":[],"issued":{"date-parts":[[2017,2,4]]},"references-count":28,"alternative-id":["10.1145\/3038228.3038239","10.1145\/3038228"],"URL":"https:\/\/doi.org\/10.1145\/3038228.3038239","relation":{},"subject":[],"published":{"date-parts":[[2017,2,4]]},"assertion":[{"value":"2017-02-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}