{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:19:38Z","timestamp":1768029578362,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T00:00:00Z","timestamp":1554336000000},"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":[[2019,4,4]]},"DOI":"10.1145\/3297858.3304072","type":"proceedings-article","created":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T18:38:43Z","timestamp":1554403123000},"page":"909-923","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":34,"title":["Astra"],"prefix":"10.1145","author":[{"given":"Muthian","family":"Sivathanu","sequence":"first","affiliation":[{"name":"Microsoft Research Indi, Bangalore, India"}]},{"given":"Tapan","family":"Chugh","sequence":"additional","affiliation":[{"name":"Microsoft Research, Bangalore, India"}]},{"given":"Sanjay S.","family":"Singapuram","sequence":"additional","affiliation":[{"name":"Microsoft Research, Bangalore, India"}]},{"given":"Lidong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2019,4,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026899"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628092"},{"key":"e_1_3_2_1_3_1","volume-title":"Tom\u00e1 s Kocisk\u00fd, and Phil Blunsom. Optimizing performance of recurrent neural networks on gpus. arXiv Preprint, abs\/1604.01946","author":"Appleyard Jeremy","year":"2016","unstructured":"Jeremy Appleyard, Tom\u00e1 s Kocisk\u00fd, and Phil Blunsom. Optimizing performance of recurrent neural networks on gpus. arXiv Preprint, abs\/1604.01946, 2016."},{"key":"e_1_3_2_1_4_1","volume-title":"TVM: end-to-end optimization stack for deep learning. CoRR, abs\/1802.04799","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Haichen Shen, Eddie Q. Yan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. TVM: end-to-end optimization stack for deep learning. CoRR, abs\/1802.04799, 2018."},{"key":"e_1_3_2_1_5_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. cudnn: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759, 2014."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294797"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999271"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/301631.301661"},{"key":"e_1_3_2_1_9_1","volume-title":"Open single and half precision gemm implementations","author":"Gray Scott","year":"2017","unstructured":"Scott Gray. Open single and half precision gemm implementations, 2017."},{"key":"e_1_3_2_1_10_1","first-page":"12","volume-title":"Proceedings of the eighth annual conference of the cognitive science society","volume":"1","author":"Hinton Geoffrey E","unstructured":"Geoffrey E Hinton. Learning distributed representations of concepts. In Proceedings of the eighth annual conference of the cognitive science society, volume 1, page 12. Amherst, MA, 1986."},{"key":"e_1_3_2_1_11_1","first-page":"100","volume-title":"Nvidia tesla","author":"Nvidia Inc.","year":"2016","unstructured":"Nvidia Inc. Nvidia tesla p100 gpu accelerator, 2016."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2499370.2462187"},{"key":"e_1_3_2_1_14_1","volume-title":"TensorFlow Dev Summit","author":"Leary Chris","year":"2017","unstructured":"Chris Leary and Todd Wang. Xla: Tensorflow, compiled. TensorFlow Dev Summit, 2017."},{"key":"e_1_3_2_1_15_1","volume-title":"Learning longer memory in recurrent neural networks. arXiv preprint arXiv:1412.7753","author":"Mikolov Tomas","year":"2014","unstructured":"Tomas Mikolov, Armand Joulin, Sumit Chopra, Michael Mathieu, and Marc'Aurelio Ranzato. Learning longer memory in recurrent neural networks. arXiv preprint arXiv:1412.7753, 2014."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3305932"},{"issue":"27","key":"e_1_3_2_1_17_1","first-page":"31","article-title":"Cublas library. NVIDIA Corporation, Santa Clara","volume":"15","author":"Nvidia CUDA","year":"2008","unstructured":"CUDA Nvidia. Cublas library. NVIDIA Corporation, Santa Clara, California, 15(27):31, 2008.","journal-title":"California"},{"key":"e_1_3_2_1_18_1","volume-title":"Pytorch: Tensors and dynamic neural networks in python with strong gpu acceleration","author":"Paszke Adam","year":"2017","unstructured":"Adam Paszke, Sam Gross, Soumith Chintala, and Gregory Chanan. Pytorch: Tensors and dynamic neural networks in python with strong gpu acceleration, 2017."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2499370.2462176"},{"key":"e_1_3_2_1_20_1","first-page":"400","article-title":"\u00aaa stochastic approximation method, \u0718 annals math","volume":"22","author":"Robbins Herbert","year":"1951","unstructured":"Herbert Robbins and S Monro. \u00aaa stochastic approximation method, \u0718 annals math. Statistics, 22:400--407, 1951.","journal-title":"Statistics"},{"key":"e_1_3_2_1_21_1","volume-title":"Learning representations by back-propagating errors. nature, 323(6088):533","author":"Rumelhart David E","year":"1986","unstructured":"David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams. Learning representations by back-propagating errors. nature, 323(6088):533, 1986."},{"key":"e_1_3_2_1_22_1","volume-title":"Intel nervana reference deep learning framework committed to best performance on all hardware","author":"Scott Leishmann Anil Thomas","year":"2017","unstructured":"Anil Thomas Scott Leishmann, Alex Park. Intel nervana reference deep learning framework committed to best performance on all hardware, 2017."},{"key":"e_1_3_2_1_23_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. Tensor comprehensions: Framework-agnostic high-performance machine learning abstractions. arXiv preprint arXiv:1802.04730, 2018."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195656"},{"key":"e_1_3_2_1_25_1","unstructured":"Inside Volta. The world's most advanced data center gpu. URL https:\/\/devblogs.nvidia.com\/parallelforall\/inside-volta."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178491"},{"key":"e_1_3_2_1_27_1","volume-title":"Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144","author":"Wu Yonghui","year":"2016","unstructured":"Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, et al. Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144, 2016."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157418"},{"key":"e_1_3_2_1_29_1","volume-title":"Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853","author":"Xu Bing","year":"2015","unstructured":"Bing Xu, Naiyan Wang, Tianqi Chen, and Mu Li. Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853, 2015."},{"key":"e_1_3_2_1_30_1","volume-title":"Jan Koutnik, and J\u00fcrgen Schmidhuber. Recurrent highway networks. arXiv preprint arXiv:1607.03474","author":"Zilly Julian Georg","year":"2016","unstructured":"Julian Georg Zilly, Rupesh Kumar Srivastava, Jan Koutnik, and J\u00fcrgen Schmidhuber. Recurrent highway networks. arXiv preprint arXiv:1607.03474, 2016."}],"event":{"name":"ASPLOS '19: Architectural Support for Programming Languages and Operating Systems","location":"Providence RI USA","acronym":"ASPLOS '19","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304072","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297858.3304072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:15Z","timestamp":1750204395000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304072"}},"subtitle":["Exploiting Predictability to Optimize Deep Learning"],"short-title":[],"issued":{"date-parts":[[2019,4,4]]},"references-count":30,"alternative-id":["10.1145\/3297858.3304072","10.1145\/3297858"],"URL":"https:\/\/doi.org\/10.1145\/3297858.3304072","relation":{},"subject":[],"published":{"date-parts":[[2019,4,4]]},"assertion":[{"value":"2019-04-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}