{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T07:17:21Z","timestamp":1790752641191,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,6,26]],"date-time":"2019-06-26T00:00:00Z","timestamp":1561507200000},"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":[[2019,6,26]]},"DOI":"10.1145\/3330345.3330382","type":"proceedings-article","created":{"date-parts":[[2019,6,18]],"date-time":"2019-06-18T12:14:30Z","timestamp":1560860070000},"page":"414-424","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["The anatomy of efficient FFT and winograd convolutions on modern CPUs"],"prefix":"10.1145","author":[{"given":"Aleksandar","family":"Zlateski","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Jia","sequence":"additional","affiliation":[{"name":"Princeton University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Li","sequence":"additional","affiliation":[{"name":"Princeton University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fredo","family":"Durand","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,6,26]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2016. FALCON Library: Fast Image Convolution in Neural Networks on Intel Architecture. \"https:\/\/colfaxresearch.com\/falcon-library\/\". (2016).  2016. FALCON Library: Fast Image Convolution in Neural Networks on Intel Architecture. \"https:\/\/colfaxresearch.com\/falcon-library\/\". (2016)."},{"key":"e_1_3_2_1_2_1","unstructured":"2016. Intel(R) Math Kernel Library for Deep Neural Networks. \"https:\/\/github.com\/01org\/mkl-dnn\". (2016).  2016. Intel(R) Math Kernel Library for Deep Neural Networks. \"https:\/\/github.com\/01org\/mkl-dnn\". (2016)."},{"key":"e_1_3_2_1_3_1","unstructured":"2018. N-Dimensional Winograd-based convolution framework. https:\/\/bitbucket.org\/poozh\/ond-winograd. (2018).  2018. N-Dimensional Winograd-based convolution framework. https:\/\/bitbucket.org\/poozh\/ond-winograd. (2018)."},{"key":"e_1_3_2_1_4_1","unstructured":"2018. Winograd and FFT Convolution. https:\/\/bitbucket.org\/jiazhentim\/winograd-fft-conv\/src\/master.  2018. Winograd and FFT Convolution. https:\/\/bitbucket.org\/jiazhentim\/winograd-fft-conv\/src\/master."},{"key":"e_1_3_2_1_5_1","unstructured":"Accessed: 01-31-2019. Imagenet Winners Benchmarking. https:\/\/github.com\/soumith\/convnet-benchmarks. (Accessed: 01-31-2019).  Accessed: 01-31-2019. Imagenet Winners Benchmarking. https:\/\/github.com\/soumith\/convnet-benchmarks. (Accessed: 01-31-2019)."},{"key":"e_1_3_2_1_6_1","unstructured":"Accessed: 01-31-2019. Intel\u00ae Nervana reference deep learning framework. https:\/\/github.com\/NervanaSystems\/neon. (Accessed: 01-31-2019).  Accessed: 01-31-2019. Intel\u00ae Nervana reference deep learning framework. https:\/\/github.com\/NervanaSystems\/neon. (Accessed: 01-31-2019)."},{"key":"e_1_3_2_1_7_1","unstructured":"Accessed: 01-31-2019. LIBXSMM. https:\/\/github.com\/hfp\/libxsmm. (Accessed: 01-31-2019).  Accessed: 01-31-2019. LIBXSMM. https:\/\/github.com\/hfp\/libxsmm. (Accessed: 01-31-2019)."},{"key":"e_1_3_2_1_8_1","unstructured":"Accessed: 01-31-2019. Wincnn. \"https:\/\/github.com\/andravin\/wincnn\". (Accessed: 01-31-2019).  Accessed: 01-31-2019. Wincnn. \"https:\/\/github.com\/andravin\/wincnn\". (Accessed: 01-31-2019)."},{"key":"e_1_3_2_1_9_1","unstructured":"Jeremy Appleyard. Accessed: 01-31-2019. Optimizing Recurrent Neural Networks in cuDNN 5. https:\/\/devblogs.nvidia.com\/parallelforall\/optimizing-recurrent-neural-networks-cudnn-5\/. (Accessed: 01-31-2019).  Jeremy Appleyard. Accessed: 01-31-2019. Optimizing Recurrent Neural Networks in cuDNN 5. https:\/\/devblogs.nvidia.com\/parallelforall\/optimizing-recurrent-neural-networks-cudnn-5\/. (Accessed: 01-31-2019)."},{"key":"e_1_3_2_1_10_1","volume-title":"Shraman Ray Chaudhuri, and Nir Shavit","author":"Budden David","year":"2016","unstructured":"David Budden , Alexander Matveev , Shibani Santurkar , Shraman Ray Chaudhuri, and Nir Shavit . 2016 . Deep Tensor Convolution on Multicores . arXiv preprint arXiv:1611.06565 (2016). David Budden, Alexander Matveev, Shibani Santurkar, Shraman Ray Chaudhuri, and Nir Shavit. 2016. Deep Tensor Convolution on Multicores. arXiv preprint arXiv:1611.06565 (2016)."},{"key":"e_1_3_2_1_11_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_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_13_1","volume-title":"Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on","volume":"3","author":"Frigo Matteo","year":"1998","unstructured":"Matteo Frigo and Steven G Johnson . 1998 . FFTW: An adaptive software architecture for the FFT. In Acoustics , Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on , Vol. 3 . IEEE, 1381--1384. Matteo Frigo and Steven G Johnson. 1998. FFTW: An adaptive software architecture for the FFT. In Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on, Vol. 3. IEEE, 1381--1384."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/647970.761024"},{"key":"e_1_3_2_1_15_1","volume-title":"SC16: International Conference for. IEEE, 981--991","author":"Heinecke Alexander","year":"2016","unstructured":"Alexander Heinecke , Greg Henry , Maxwell Hutchinson , and Hans Pabst . 2016 . LIBXSMM: accelerating small matrix multiplications by runtime code generation. In High Performance Computing, Networking, Storage and Analysis , SC16: International Conference for. IEEE, 981--991 . Alexander Heinecke, Greg Henry, Maxwell Hutchinson, and Hans Pabst. 2016. LIBXSMM: accelerating small matrix multiplications by runtime code generation. In High Performance Computing, Networking, Storage and Analysis, SC16: International Conference for. IEEE, 981--991."},{"key":"e_1_3_2_1_16_1","volume-title":"Libxsmm: A high performance library for small matrix multiplications. Poster and Extended Abstract Presented at SC","author":"Heinecke Alexander","year":"2015","unstructured":"Alexander Heinecke , Hans Pabst , and Greg Henry . 2015 . Libxsmm: A high performance library for small matrix multiplications. Poster and Extended Abstract Presented at SC (2015). Alexander Heinecke, Hans Pabst, and Greg Henry. 2015. Libxsmm: A high performance library for small matrix multiplications. Poster and Extended Abstract Presented at SC (2015)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"James Jeffers James Reinders and Avinash Sodani. 2016. Intel Xeon Phi Processor High Performance Programming: Knights Landing Edition. Morgan Kaufmann.   James Jeffers James Reinders and Avinash Sodani. 2016. Intel Xeon Phi Processor High Performance Programming: Knights Landing Edition. Morgan Kaufmann.","DOI":"10.1016\/B978-0-12-809194-4.00002-8"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178496"},{"key":"e_1_3_2_1_19_1","volume-title":"Towards Optimal Winograd Convolution on Manycores. SysML","author":"Jia Zhen","year":"2018","unstructured":"Zhen Jia , Aleksandar Zlateski , Fredo Durand , and Kai Li. 2018. Towards Optimal Winograd Convolution on Manycores. SysML 2018 . Zhen Jia, Aleksandar Zlateski, Fredo Durand, and Kai Li. 2018. Towards Optimal Winograd Convolution on Manycores. SysML 2018."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1137\/07070111X"},{"key":"e_1_3_2_1_21_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_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807671"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1137\/1012065"},{"key":"e_1_3_2_1_25_1","volume-title":"Fast training of convolutional networks through ffts. arXiv preprint arXiv:1312.5851","author":"Mathieu Michael","year":"2013","unstructured":"Michael Mathieu , Mikael Henaff , and Yann LeCun . 2013. Fast training of convolutional networks through ffts. arXiv preprint arXiv:1312.5851 ( 2013 ). Michael Mathieu, Mikael Henaff, and Yann LeCun. 2013. Fast training of convolutional networks through ffts. arXiv preprint arXiv:1312.5851 (2013)."},{"key":"e_1_3_2_1_26_1","unstructured":"Guido F Montufar Razvan Pascanu Kyunghyun Cho and Yoshua Bengio. 2014. On the number of linear regions of deep neural networks. In Advances in neural information processing systems. 2924--2932.  Guido F Montufar Razvan Pascanu Kyunghyun Cho and Yoshua Bengio. 2014. On the number of linear regions of deep neural networks. In Advances in neural information processing systems. 2924--2932."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1137\/15M1030170"},{"key":"e_1_3_2_1_28_1","volume-title":"Theory and application of digital signal processing","author":"Rabiner Lawrence R","year":"1975","unstructured":"Lawrence R Rabiner and Bernard Gold . 1975. Theory and application of digital signal processing . Englewood Cliffs, NJ , Prentice-Hall , Inc., 1975 . 777 p. (1975). Lawrence R Rabiner and Bernard Gold. 1975. Theory and application of digital signal processing. Englewood Cliffs, NJ, Prentice-Hall, Inc., 1975. 777 p. (1975)."},{"key":"e_1_3_2_1_29_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_31_1","volume-title":"Proc. Deep Learning and Unsupervised Feature Learning NIPS Workshop","volume":"1","author":"Vanhoucke Vincent","year":"2011","unstructured":"Vincent Vanhoucke , Andrew Senior , and Mark Z Mao . 2011 . Improving the speed of neural networks on CPUs . In Proc. Deep Learning and Unsupervised Feature Learning NIPS Workshop , Vol. 1 . 4. Vincent Vanhoucke, Andrew Senior, and Mark Z Mao. 2011. Improving the speed of neural networks on CPUs. In Proc. Deep Learning and Unsupervised Feature Learning NIPS Workshop, Vol. 1. 4."},{"key":"e_1_3_2_1_32_1","volume-title":"Fast convolutional nets with fbfft: A GPU performance evaluation. arXiv preprint arXiv:1412.7580","author":"Vasilache Nicolas","year":"2014","unstructured":"Nicolas Vasilache , Jeff Johnson , Michael Mathieu , Soumith Chintala , Serkan Piantino , and Yann LeCun . 2014. Fast convolutional nets with fbfft: A GPU performance evaluation. arXiv preprint arXiv:1412.7580 ( 2014 ). Nicolas Vasilache, Jeff Johnson, Michael Mathieu, Soumith Chintala, Serkan Piantino, and Yann LeCun. 2014. Fast convolutional nets with fbfft: A GPU performance evaluation. arXiv preprint arXiv:1412.7580 (2014)."},{"key":"e_1_3_2_1_33_1","unstructured":"Kevin Vincent Kevin Stephano Michael Frumkin Boris Ginsburg and Julien Demouth. 2017. On Improving the Numerical Stability of Winograd Convolutions.  Kevin Vincent Kevin Stephano Michael Frumkin Boris Ginsburg and Julien Demouth. 2017. On Improving the Numerical Stability of Winograd Convolutions."},{"key":"e_1_3_2_1_34_1","first-page":"24","article-title":"The roofline model: A pedagogical tool for auto-tuning kernels on multicore architectures","volume":"20","author":"Williams Samuel","year":"2008","unstructured":"Samuel Williams , David Patterson , Leonid Oliker , John Shalf , and Katherine Yelick . 2008 . The roofline model: A pedagogical tool for auto-tuning kernels on multicore architectures . In Hot Chips , Vol. 20. 24 -- 26 . Samuel Williams, David Patterson, Leonid Oliker, John Shalf, and Katherine Yelick. 2008. The roofline model: A pedagogical tool for auto-tuning kernels on multicore architectures. In Hot Chips, Vol. 20. 24--26.","journal-title":"Hot Chips"},{"key":"e_1_3_2_1_35_1","volume-title":"Arithmetic complexity of computations","author":"Winograd Shmuel","unstructured":"Shmuel Winograd . 1980. Arithmetic complexity of computations . Vol. 33 . Siam . Shmuel Winograd. 1980. Arithmetic complexity of computations. Vol. 33. Siam."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/216585.216588"},{"key":"e_1_3_2_1_37_1","volume-title":"A Deeper Look at FFT and Winograd Convolutions. SysML","author":"Zlateski Aleksandar","year":"2018","unstructured":"Aleksandar Zlateski , Zhen Jia , Kai Li , and Fredo Durand . 2018. A Deeper Look at FFT and Winograd Convolutions. SysML 2018 . Aleksandar Zlateski, Zhen Jia, Kai Li, and Fredo Durand. 2018. A Deeper Look at FFT and Winograd Convolutions. SysML 2018."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.119"},{"key":"e_1_3_2_1_39_1","volume-title":"SC16: International Conference for. IEEE, 854--865","author":"Zlateski Aleksandar","year":"2016","unstructured":"Aleksandar Zlateski , Kisuk Lee , and H Sebastian Seung . 2016 . ZNNi: maximizing the inference throughput of 3D convolutional networks on CPUs and GPUs. In High Performance Computing, Networking, Storage and Analysis , SC16: International Conference for. IEEE, 854--865 . Aleksandar Zlateski, Kisuk Lee, and H Sebastian Seung. 2016. ZNNi: maximizing the inference throughput of 3D convolutional networks on CPUs and GPUs. In High Performance Computing, Networking, Storage and Analysis, SC16: International Conference for. IEEE, 854--865."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079081"}],"event":{"name":"ICS '19: 2019 International Conference on Supercomputing","location":"Phoenix Arizona","acronym":"ICS '19","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3330345.3330382","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3330345.3330382","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:26Z","timestamp":1750204406000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3330345.3330382"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,26]]},"references-count":40,"alternative-id":["10.1145\/3330345.3330382","10.1145\/3330345"],"URL":"https:\/\/doi.org\/10.1145\/3330345.3330382","relation":{},"subject":[],"published":{"date-parts":[[2019,6,26]]},"assertion":[{"value":"2019-06-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}