{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T21:31:15Z","timestamp":1777498275902,"version":"3.51.4"},"reference-count":38,"publisher":"Association for Computing Machinery (ACM)","issue":"9","license":[{"start":{"date-parts":[[2018,8,22]],"date-time":"2018-08-22T00:00:00Z","timestamp":1534896000000},"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":["Commun. ACM"],"published-print":{"date-parts":[[2018,8,22]]},"abstract":"<jats:p>Tensor processing units improve performance per watt of neural networks in Google datacenters by roughly 50x.<\/jats:p>","DOI":"10.1145\/3154484","type":"journal-article","created":{"date-parts":[[2018,8,23]],"date-time":"2018-08-23T11:48:27Z","timestamp":1535024907000},"page":"50-59","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":135,"title":["A domain-specific architecture for deep neural networks"],"prefix":"10.1145","volume":"61","author":[{"given":"Norman P.","family":"Jouppi","sequence":"first","affiliation":[{"name":"Google, Mountain View, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cliff","family":"Young","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nishant","family":"Patil","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Patterson","sequence":"additional","affiliation":[{"name":"University of California at Berkeley, Berkeley, CA and Google, Mountain View, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,8,22]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"et al. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint","author":"Abadi M.","year":"2016","unstructured":"Abadi , M. et al. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint , 2016 ; https:\/\/arxiv.org\/abs\/1603.04467 Abadi, M. et al. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint, 2016; https:\/\/arxiv.org\/abs\/1603.04467"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.11"},{"key":"e_1_2_1_3_1","volume-title":"The Handbook of Brain Theory and Neural Networks","author":"Asanovi\u0107 K.","year":"2002","unstructured":"Asanovi\u0107 , K. Programmable neurocomputing . In The Handbook of Brain Theory and Neural Networks , Second Edition, M.A. Arbib, Ed . MIT Press , Cambridge, MA, Nov. 2002 ; https:\/\/people.eecs.berkeley.edu\/~krste\/papers\/neurocomputing.pdf Asanovi\u0107, K. Programmable neurocomputing. In The Handbook of Brain Theory and Neural Networks, Second Edition, M.A. Arbib, Ed. MIT Press, Cambridge, MA, Nov. 2002; https:\/\/people.eecs.berkeley.edu\/~krste\/papers\/neurocomputing.pdf"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2007.443"},{"key":"e_1_2_1_5_1","volume-title":"Sept. 29","author":"Barr J.","year":"2016","unstructured":"Barr , J. New G2 Instance Type for Amazon EC2: Up to 16 GPUs. Amazon blog , Sept. 29 , 2016 ; https:\/\/aws.amazon.com\/about-aws\/whats-new\/2015\/04\/introducing-a-new-g2-instance-size-the-g28xlarge\/ Barr, J. New G2 Instance Type for Amazon EC2: Up to 16 GPUs. Amazon blog, Sept. 29, 2016; https:\/\/aws.amazon.com\/about-aws\/whats-new\/2015\/04\/introducing-a-new-g2-instance-size-the-g28xlarge\/"},{"key":"e_1_2_1_6_1","volume-title":"July 13","author":"Barr J.","year":"2017","unstructured":"Barr , J. New Next-Generation GPU-Powered EC2 Instances (G3). Amazon blog , July 13 , 2017 ; https:\/\/aws.amazon.com\/blogs\/aws\/new-next-generation-gpu-powered-ec2-instances-g3\/ Barr, J. New Next-Generation GPU-Powered EC2 Instances (G3). Amazon blog, July 13, 2017; https:\/\/aws.amazon.com\/blogs\/aws\/new-next-generation-gpu-powered-ec2-instances-g3\/"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2996864"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.40"},{"key":"e_1_2_1_9_1","volume-title":"Google turning its lucrative Web search over to AI machines. Bloomberg Technology (0ct. 26","author":"Clark J.","year":"2015","unstructured":"Clark , J. Google turning its lucrative Web search over to AI machines. Bloomberg Technology (0ct. 26 , 2015 ). Clark, J. Google turning its lucrative Web search over to AI machines. Bloomberg Technology (0ct. 26, 2015)."},{"key":"e_1_2_1_10_1","volume-title":"CA","author":"Dally W.","unstructured":"Dally , W. High-performance hardware for machine learning. Invited talk at Cadence ENN Summit (Santa Clara , CA , Feb. 9, 2016); https:\/\/ip.cadence.com\/uploads\/presentations\/1000AM_Dally_Cadence_ENN.pdf Dally, W. High-performance hardware for machine learning. Invited talk at Cadence ENN Summit (Santa Clara, CA, Feb. 9, 2016); https:\/\/ip.cadence.com\/uploads\/presentations\/1000AM_Dally_Cadence_ENN.pdf"},{"key":"e_1_2_1_11_1","volume-title":"July 7","author":"Dean J.","year":"2016","unstructured":"Dean , J. Large-Scale Deep Learning with TensorFlow for Building Intelligent Systems. ACM webinar , July 7 , 2016 ; https:\/\/www.youtube.com\/watch?v=vzoe2G5g-w4 Dean, J. Large-Scale Deep Learning with TensorFlow for Building Intelligent Systems. ACM webinar, July 7, 2016; https:\/\/www.youtube.com\/watch?v=vzoe2G5g-w4"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1990.137621"},{"key":"e_1_2_1_13_1","volume-title":"Proceedings of Advances in Neural Information Processing Systems (Montreal Canada, Dec.) MIT Press","author":"Han S.","year":"2015","unstructured":"Han , S. , Pool , J. , Tran , J. , and Dally , W . Learning both weights and connections for efficient neural networks . In Proceedings of Advances in Neural Information Processing Systems (Montreal Canada, Dec.) MIT Press , Cambridge, MA , 2015 . Han, S., Pool, J., Tran, J., and Dally, W. Learning both weights and connections for efficient neural networks. In Proceedings of Advances in Neural Information Processing Systems (Montreal Canada, Dec.) MIT Press, Cambridge, MA, 2015."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"e_1_2_1_15_1","volume-title":"Apr. 2017","author":"Huang J.","year":"2017","unstructured":"Huang , J. AI Drives the Rise of Accelerated Computing in Data Centers. Nvidia blog , Apr. 2017 ; https:\/\/blogs.nvidia.com\/blog\/ 2017 \/04\/10\/ai-drives-rise-accelerated-computing-datacenter\/ Huang, J. AI Drives the Rise of Accelerated Computing in Data Centers. Nvidia blog, Apr. 2017; https:\/\/blogs.nvidia.com\/blog\/2017\/04\/10\/ai-drives-rise-accelerated-computing-datacenter\/"},{"key":"e_1_2_1_16_1","volume-title":"Mar. 16","author":"He K.","year":"2016","unstructured":"He , K. , Zhang , X. , Ren , S. , and Sun , J . Identity mappings in deep residual networks. arXiv preprint , Mar. 16 , 2016 ; https:\/\/arxiv.org\/abs\/1603.05027 He, K., Zhang, X., Ren, S., and Sun, J. Identity mappings in deep residual networks. arXiv preprint, Mar. 16, 2016; https:\/\/arxiv.org\/abs\/1603.05027"},{"key":"e_1_2_1_17_1","volume-title":"Computer Architecture: A Quantitative Approach","author":"Hennessy J.L.","year":"2018","unstructured":"Hennessy , J.L. and Patterson , D.A . Computer Architecture: A Quantitative Approach , Sixth Edition. Elsevier , New York , 2018 . Hennessy, J.L. and Patterson, D.A. Computer Architecture: A Quantitative Approach, Sixth Edition. Elsevier, New York, 2018."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00930664"},{"key":"e_1_2_1_19_1","volume-title":"May 18","author":"Jouppi N.","year":"2016","unstructured":"Jouppi , N. Google Supercharges Machine Learning Tasks with TPU Custom Chip. Google platform blog , May 18 , 2016 ; https:\/\/cloudplatform.googleblog.com\/2016\/05\/Google-supercharges-machine-learning-tasks-with-custom-chip.html Jouppi, N. Google Supercharges Machine Learning Tasks with TPU Custom Chip. Google platform blog, May 18, 2016; https:\/\/cloudplatform.googleblog.com\/2016\/05\/Google-supercharges-machine-learning-tasks-with-custom-chip.html"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2996862"},{"key":"e_1_2_1_22_1","volume-title":"Proceedings of Advances in Neural Information Processing Systems (Lake Tahoe, NV)","author":"Krizhevsky A.","year":"2012","unstructured":"Krizhevsky , A. , Sutskever , I. , and Hinton , G . Imagenet classification with deep convolutional neural networks . In Proceedings of Advances in Neural Information Processing Systems (Lake Tahoe, NV) . MIT Press , Cambridge, MA , 2012 . Krizhevsky, A., Sutskever, I., and Hinton, G. Imagenet classification with deep convolutional neural networks. In Proceedings of Advances in Neural Information Processing Systems (Lake Tahoe, NV). MIT Press, Cambridge, MA, 2012."},{"key":"e_1_2_1_23_1","first-page":"292","article-title":"Algorithms for VLSI processor arrays. Chapter in Introduction to VLSI systems by C. Mead and L. Conway. Addison-Wesley, Reading","volume":"271","author":"Kung H.T.","year":"1980","unstructured":"Kung , H.T. and Leiserson , C.E . Algorithms for VLSI processor arrays. Chapter in Introduction to VLSI systems by C. Mead and L. Conway. Addison-Wesley, Reading , MA , 1980 , 271 -- 292 . Kung, H.T. and Leiserson, C.E. Algorithms for VLSI processor arrays. Chapter in Introduction to VLSI systems by C. Mead and L. Conway. Addison-Wesley, Reading, MA, 1980, 271--292.","journal-title":"MA"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.84"},{"key":"e_1_2_1_25_1","volume-title":"Mar. 10","author":"Larabel M.","year":"2016","unstructured":"Larabel , M. Google Looks to Open Up StreamExecutor to Make GPGPU Programming Easier. Phoronix , Mar. 10 , 2016 ; https:\/\/www.phoronix.com\/scan.php?page=news_item&px=Google-StreamExec-Parallel Larabel, M. Google Looks to Open Up StreamExecutor to Make GPGPU Programming Easier. Phoronix, Mar. 10, 2016; https:\/\/www.phoronix.com\/scan.php?page=news_item&px=Google-StreamExec-Parallel"},{"key":"e_1_2_1_26_1","volume-title":"Wired (Sept. 25, 2016","author":"Metz C.","year":"2016","unstructured":"Metz , C. Microsoft bets its future on a reprogrammable computer chip . Wired (Sept. 25, 2016 ); https:\/\/www.wired.com\/ 2016 \/09\/microsoft-bets-future-chip-reprogram-fly\/ Metz, C. Microsoft bets its future on a reprogrammable computer chip. Wired (Sept. 25, 2016); https:\/\/www.wired.com\/2016\/09\/microsoft-bets-future-chip-reprogram-fly\/"},{"key":"e_1_2_1_27_1","volume-title":"CA, Feb. 13)","author":"Moore G.E.","year":"2003","unstructured":"Moore , G.E. No exponential is forever: But 'forever' can be delayed! In Proceedings of the International Solid-State Circuits Conference (San Francisco , CA, Feb. 13) . IEEE Press , 2003 . Moore, G.E. No exponential is forever: But 'forever' can be delayed! In Proceedings of the International Solid-State Circuits Conference (San Francisco, CA, Feb. 13). IEEE Press, 2003."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1022594.1022596"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/641914.641917"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2996868"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.32"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"e_1_2_1_34_1","volume-title":"Proceedings of the 11<sup>th<\/sup> Annual International Symposium on Computer Architecture","author":"Smith J.E.","year":"1982","unstructured":"Smith , J.E. Decoupled access\/execute computer architectures. In Proceedings of the 11<sup>th<\/sup> Annual International Symposium on Computer Architecture ( Austin, TX, Apr. 26--29). IEEE Computer Society Press , 1982 . Smith, J.E. Decoupled access\/execute computer architectures. In Proceedings of the 11<sup>th<\/sup> Annual International Symposium on Computer Architecture (Austin, TX, Apr. 26--29). IEEE Computer Society Press, 1982."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080244"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_2_1_38_1","volume-title":"Sept. 26","author":"Wu Y.","year":"2016","unstructured":"Wu , Y. et al. Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint , Sept. 26 , 2016 ; arXiv: 1609.03144 Wu, Y. et al. Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint, Sept. 26, 2016; arXiv:1609.03144"}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3154484","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3154484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:11:26Z","timestamp":1750212686000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3154484"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,22]]},"references-count":38,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2018,8,22]]}},"alternative-id":["10.1145\/3154484"],"URL":"https:\/\/doi.org\/10.1145\/3154484","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"value":"0001-0782","type":"print"},{"value":"1557-7317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8,22]]},"assertion":[{"value":"2018-08-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}