{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:38:15Z","timestamp":1772908695279,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,3,30]],"date-time":"2018-03-30T00:00:00Z","timestamp":1522368000000},"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":[[2018,3,30]]},"DOI":"10.1145\/3184407.3184423","type":"proceedings-article","created":{"date-parts":[[2018,4,4]],"date-time":"2018-04-04T12:25:45Z","timestamp":1522844745000},"page":"96-106","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["Characterizing the Microarchitectural Implications of a Convolutional Neural Network (CNN) Execution on GPUs"],"prefix":"10.1145","author":[{"given":"Shi","family":"Dong","sequence":"first","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Gong","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Sun","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trinayan","family":"Baruah","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Kaeli","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,3,30]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Mart\u00edn Abadi et al. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. (2015). http:\/\/tensorflow.org\/  Mart\u00edn Abadi et al. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. (2015). http:\/\/tensorflow.org\/"},{"key":"e_1_3_2_2_2_1","unstructured":"Tianqi Chen Mu Li and etal 2015. MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems. CoRR (2015). http:\/\/arxiv.org\/abs\/1512.01274  Tianqi Chen Mu Li and et al. 2015. MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems. CoRR (2015). http:\/\/arxiv.org\/abs\/1512.01274"},{"key":"e_1_3_2_2_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_2_4_1","unstructured":"NVIDIA Corporation. 2014. CUDA C Programming Guide. (2014).  NVIDIA Corporation. 2014. CUDA C Programming Guide. (2014)."},{"key":"e_1_3_2_2_5_1","unstructured":"NVIDIA Corporation. 2015. CuBlas library v7.5. (2015).  NVIDIA Corporation. 2015. CuBlas library v7.5. (2015)."},{"key":"e_1_3_2_2_6_1","unstructured":"NVIDIA Corporation. 2017. CuDNN library v6.0. (2017).  NVIDIA Corporation. 2017. CuDNN library v6.0. (2017)."},{"key":"e_1_3_2_2_7_1","volume-title":"DNNMark: A Deep Neural Network Benchmark Suite for GPUs. GPGPU-10","author":"Dong Shi","year":"2017","unstructured":"Shi Dong and David Kaeli . 2017. DNNMark: A Deep Neural Network Benchmark Suite for GPUs. GPGPU-10 ( 2017 ), 63?72. Shi Dong and David Kaeli. 2017. DNNMark: A Deep Neural Network Benchmark Suite for GPUs. GPGPU-10 (2017), 63?72."},{"key":"e_1_3_2_2_8_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_2_9_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_2_10_1","volume-title":"Performance Analysis of CNN Frameworks for GPUs. Performance Analysis of Systems and Software (ISPASS)","author":"Kim Heehoon","year":"2017","unstructured":"Heehoon Kim , Hyoungwook Nam , Wookeun Jung , and Jaejin Lee . 2017. Performance Analysis of CNN Frameworks for GPUs. Performance Analysis of Systems and Software (ISPASS) ( 2017 ). Heehoon Kim, Hyoungwook Nam, Wookeun Jung, and Jaejin Lee. 2017. Performance Analysis of CNN Frameworks for GPUs. Performance Analysis of Systems and Software (ISPASS) (2017)."},{"key":"e_1_3_2_2_11_1","volume-title":"ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems 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."},{"key":"e_1_3_2_2_12_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_2_13_1","volume-title":"Deep learning. Nature","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun , Yoshua Bengio , and Geoffrey Hinton . 2015. Deep learning. Nature ( 2015 ), 436--444. Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature (2015), 436--444."},{"key":"e_1_3_2_2_14_1","volume-title":"Kepler GK110.","author":"NVIDIA.","year":"2012","unstructured":"NVIDIA. 2012. NVIDIA's Next Generation CUDA Compute Architecture , Kepler GK110. ( 2012 ). NVIDIA. 2012. NVIDIA's Next Generation CUDA Compute Architecture, Kepler GK110. (2012)."},{"key":"e_1_3_2_2_15_1","unstructured":"NVIDIA. 2016. CUDA Toolkit Documentation. (2016).  NVIDIA. 2016. CUDA Toolkit Documentation. (2016)."},{"key":"e_1_3_2_2_16_1","unstructured":"NVIDIA. 2016. NVIDIA GeForce GTX 1080. (2016).  NVIDIA. 2016. NVIDIA GeForce GTX 1080. (2016)."},{"key":"e_1_3_2_2_17_1","unstructured":"NVIDIA. 2016. NVIDIA Tesla P100. (2016).  NVIDIA. 2016. NVIDIA Tesla P100. (2016)."},{"key":"e_1_3_2_2_18_1","unstructured":"NVIDIA. 2016. TESLA GPU ACCELERATORS FOR SERVERS. (2016).  NVIDIA. 2016. TESLA GPU ACCELERATORS FOR SERVERS. (2016)."},{"key":"e_1_3_2_2_19_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_2_20_1","unstructured":"Victor Podlozhnyuk. 2007. FFT-based 2D convolution. (2007).  Victor Podlozhnyuk. 2007. FFT-based 2D convolution. (2007)."},{"key":"e_1_3_2_2_21_1","volume-title":"Keckler","author":"Rhu Minsoo","year":"2016","unstructured":"Minsoo Rhu , Natalia Gimelshein , Jason Clemons , Arslan Zulfiqar , and Stephen W . Keckler . 2016 . vDNN: Virtualized deep neural networks for scalable, memory-efficient neural network design. Microarchitecture (MICRO) ( 2016). Minsoo Rhu, Natalia Gimelshein, Jason Clemons, Arslan Zulfiqar, and Stephen W. Keckler. 2016. vDNN: Virtualized deep neural networks for scalable, memory-efficient neural network design. Microarchitecture (MICRO) (2016)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2945397"},{"key":"e_1_3_2_2_23_1","volume-title":"Chenkai Shao, Asit Mishra, and Hadi Es.","author":"Sharma Hardik","year":"2016","unstructured":"Hardik Sharma , Jongse Park , Divya Mahajan , Emmanuel Amaro , Joon Kyung Kim , Chenkai Shao, Asit Mishra, and Hadi Es. 2016 . From high-level deep neural models to FPGAs. Microarchitecture (MICRO) ( 2016). Hardik Sharma, Jongse Park, Divya Mahajan, Emmanuel Amaro, Joon Kyung Kim, Chenkai Shao, Asit Mishra, and Hadi Es. 2016. From high-level deep neural models to FPGAs. Microarchitecture (MICRO) (2016)."},{"key":"e_1_3_2_2_24_1","volume-title":"Benchmarking State-of-the-Art Deep Learning Software Tools. CoRR abs\/1608.07249","author":"Shi Shaohuai","year":"2016","unstructured":"Shaohuai Shi , Qiang Wang , Pengfei Xu , and Xiaowen Chu . 2016. Benchmarking State-of-the-Art Deep Learning Software Tools. CoRR abs\/1608.07249 ( 2016 ). http:\/\/arxiv.org\/abs\/1608.07249 Shaohuai Shi, Qiang Wang, Pengfei Xu, and Xiaowen Chu. 2016. Benchmarking State-of-the-Art Deep Learning Software Tools. CoRR abs\/1608.07249 (2016). http:\/\/arxiv.org\/abs\/1608.07249"},{"key":"e_1_3_2_2_25_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_2_26_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)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2716282.2716283"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/GreenCom-CPSCom.2010.102"},{"key":"e_1_3_2_2_29_1","volume-title":"Demystifying GPU microarchitecture through microbenchmarking. Performance Analysis of Systems and Software (ISPASS)","author":"Wong Henry","year":"2010","unstructured":"Henry Wong , Misel-Myrto Papadopoulou , Maryam Sadooghi-Alvandi , and Andreas Moshovos . 2010. Demystifying GPU microarchitecture through microbenchmarking. Performance Analysis of Systems and Software (ISPASS) ( 2010 ). Henry Wong, Misel-Myrto Papadopoulou, Maryam Sadooghi-Alvandi, and Andreas Moshovos. 2010. Demystifying GPU microarchitecture through microbenchmarking. Performance Analysis of Systems and Software (ISPASS) (2010)."}],"event":{"name":"ICPE '18: ACM\/SPEC International Conference on Performance Engineering","location":"Berlin Germany","acronym":"ICPE '18","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2018 ACM\/SPEC International Conference on Performance Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3184407.3184423","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3184407.3184423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:08:30Z","timestamp":1750208910000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3184407.3184423"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3,30]]},"references-count":29,"alternative-id":["10.1145\/3184407.3184423","10.1145\/3184407"],"URL":"https:\/\/doi.org\/10.1145\/3184407.3184423","relation":{},"subject":[],"published":{"date-parts":[[2018,3,30]]},"assertion":[{"value":"2018-03-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}