{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T13:47:05Z","timestamp":1772113625718,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,5,13]],"date-time":"2019-05-13T00:00:00Z","timestamp":1557705600000},"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":[[2019,5,13]]},"DOI":"10.1145\/3317550.3321441","type":"proceedings-article","created":{"date-parts":[[2019,5,10]],"date-time":"2019-05-10T19:01:58Z","timestamp":1557514918000},"page":"177-183","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":41,"title":["Machine Learning Systems are Stuck in a Rut"],"prefix":"10.1145","author":[{"given":"Paul","family":"Barham","sequence":"first","affiliation":[{"name":"Google Brain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Isard","sequence":"additional","affiliation":[{"name":"Google Brain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,5,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Matrix capsules with em routing,\" in International Conference on Learning Representations (ICLR)","author":"Hinton G.","year":"2018","unstructured":"G. Hinton , S. Sabour , and N. Frosst , \" Matrix capsules with em routing,\" in International Conference on Learning Representations (ICLR) , 2018 . G. Hinton, S. Sabour, and N. Frosst, \"Matrix capsules with em routing,\" in International Conference on Learning Representations (ICLR), 2018."},{"key":"e_1_3_2_1_2_1","first-page":"265","volume-title":"OSDI'16, (Berkeley, CA, USA)","author":"Abadi M.","year":"2016","unstructured":"M. Abadi , P. Barham , J. Chen , Z. Chen , A. Davis , J. Dean , M. Devin , S. Ghemawat , G. Irving , M. Isard , M. Kudlur , J. Levenberg , R. Monga , S. Moore , D. G. Murray , B. Steiner , P. Tucker , V. Vasudevan , P. Warden , M. Wicke , Y. Yu , and X. Zheng , \" Tensorflow: A system for large-scale machine learning,\" in Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation , OSDI'16, (Berkeley, CA, USA) , pp. 265 -- 283 , USENIX Association , 2016 . M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, S. Moore, D. G. Murray, B. Steiner, P. Tucker, V. Vasudevan, P. Warden, M. Wicke, Y. Yu, and X. Zheng, \"Tensorflow: A system for large-scale machine learning,\" in Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, OSDI'16, (Berkeley, CA, USA), pp. 265--283, USENIX Association, 2016."},{"key":"e_1_3_2_1_3_1","unstructured":"\"PyTorch.\" https:\/\/pytorch.org\/. Accessed 2019-01-09. \"PyTorch.\" https:\/\/pytorch.org\/. Accessed 2019-01-09."},{"key":"e_1_3_2_1_4_1","unstructured":"\"Understanding Matrix Capsules with EM Routing.\" https:\/\/jhui.github.io\/2017\/11\/14\/Matrix-Capsules-with-EM-routing-Capsule-Network. Accessed 2019-01-09. \"Understanding Matrix Capsules with EM Routing.\" https:\/\/jhui.github.io\/2017\/11\/14\/Matrix-Capsules-with-EM-routing-Capsule-Network. Accessed 2019-01-09."},{"key":"e_1_3_2_1_5_1","first-page":"1","volume-title":"Networking, Storage, and Analysis, SC '18, (Piscataway, NJ, USA)","author":"Georganas E.","year":"2018","unstructured":"E. Georganas , S. Avancha , K. Banerjee , D. Kalamkar , G. Henry , H. Pabst , and A. Heinecke , \" Anatomy of high-performance deep learning convolutions on simd architectures,\" in Proceedings of the International Conference for High Performance Computing , Networking, Storage, and Analysis, SC '18, (Piscataway, NJ, USA) , pp. 66: 1 -- 66 :12, IEEE Press , 2018 . E. Georganas, S. Avancha, K. Banerjee, D. Kalamkar, G. Henry, H. Pabst, and A. Heinecke, \"Anatomy of high-performance deep learning convolutions on simd architectures,\" in Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, SC '18, (Piscataway, NJ, USA), pp. 66:1--66:12, IEEE Press, 2018."},{"key":"e_1_3_2_1_6_1","unstructured":"\"How to access global memory efficiently in CUDA C\/C++ kernels.\" https:\/\/devblogs.nvidia.com\/how-access-global-memory-efficiently-cuda-c-kernels\/. Accessed 2019-01-09. \"How to access global memory efficiently in CUDA C\/C++ kernels.\" https:\/\/devblogs.nvidia.com\/how-access-global-memory-efficiently-cuda-c-kernels\/. Accessed 2019-01-09."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"e_1_3_2_1_8_1","first-page":"04730","article-title":"Tensor comprehensions: Framework-agnostic high-performance machine learning abstractions","volume":"1802","author":"Vasilache N.","year":"2018","unstructured":"N. Vasilache , O. Zinenko , T. Theodoridis , P. Goyal , Z. DeVito , W. S. Moses , S. Verdoolaege , A. Adams , and A. Cohen , \" Tensor comprehensions: Framework-agnostic high-performance machine learning abstractions ,\" CoRR , vol. abs\/ 1802 . 04730 , 2018 . N. Vasilache, O. Zinenko, T. Theodoridis, P. Goyal, Z. DeVito, W. S. Moses, S. Verdoolaege, A. Adams, and A. Cohen, \"Tensor comprehensions: Framework-agnostic high-performance machine learning abstractions,\" CoRR, vol. abs\/1802.04730, 2018.","journal-title":"CoRR"},{"key":"e_1_3_2_1_9_1","unstructured":"\"PlaidML.\" https:\/\/github.com\/plaidml\/plaidml. Accessed 2019-01-09. \"PlaidML.\" https:\/\/github.com\/plaidml\/plaidml. Accessed 2019-01-09."},{"key":"e_1_3_2_1_10_1","unstructured":"\"cuDNN.\" https:\/\/developer.nvidia.com\/cudnn. Accessed 2019-01-09. \"cuDNN.\" https:\/\/developer.nvidia.com\/cudnn. Accessed 2019-01-09."},{"key":"e_1_3_2_1_11_1","unstructured":"\"End to end deep learning compiler stack.\" https:\/\/tvm.ai\/. Accessed 2019-01-09. \"End to end deep learning compiler stack.\" https:\/\/tvm.ai\/. Accessed 2019-01-09."},{"issue":"1","key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"Dempster A. P.","year":"1977","unstructured":"A. P. Dempster , N. M. Laird , and D. B. Rubin , \" Maximum likelihood from incomplete data via the EM algorithm ,\" Journal Of The Royal Statistical Society, Series B , vol. 39 , no. 1 , pp. 1 -- 38 , 1977 . A. P. Dempster, N. M. Laird, and D. B. Rubin, \"Maximum likelihood from incomplete data via the EM algorithm,\" Journal Of The Royal Statistical Society, Series B, vol. 39, no. 1, pp. 1--38, 1977.","journal-title":"Journal Of The Royal Statistical Society, Series B"},{"key":"e_1_3_2_1_13_1","first-page":"03385","article-title":"Deep residual learning for image recognition","volume":"1512","author":"He K.","year":"2015","unstructured":"K. He , X. Zhang , S. Ren , and J. Sun , \" Deep residual learning for image recognition ,\" CoRR , vol. abs\/ 1512 . 03385 , 2015 . K. He, X. Zhang, S. Ren, and J. Sun, \"Deep residual learning for image recognition,\" CoRR, vol. abs\/1512.03385, 2015.","journal-title":"CoRR"},{"key":"e_1_3_2_1_14_1","unstructured":"\"XLA: Accelerated linear algebra.\" https:\/\/www.tensorflow.org\/xla\/. Accessed 2019-01-09. \"XLA: Accelerated linear algebra.\" https:\/\/www.tensorflow.org\/xla\/. Accessed 2019-01-09."},{"key":"e_1_3_2_1_15_1","first-page":"00149","article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding","volume":"1510","author":"Han S.","year":"2015","unstructured":"S. Han , H. Mao , and W. J. Dally , \" Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding ,\" CoRR , vol. abs\/ 1510 . 00149 , 2015 . S. Han, H. Mao, and W. J. Dally, \"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding,\" CoRR, vol. abs\/1510.00149, 2015.","journal-title":"CoRR"},{"key":"e_1_3_2_1_16_1","first-page":"06174","article-title":"Training deep nets with sublinear memory cost","volume":"1604","author":"Chen T.","year":"2016","unstructured":"T. Chen , B. Xu , C. Zhang , and C. Guestrin , \" Training deep nets with sublinear memory cost ,\" CoRR , vol. abs\/ 1604 . 06174 , 2016 . T. Chen, B. Xu, C. Zhang, and C. Guestrin, \"Training deep nets with sublinear memory cost,\" CoRR, vol. abs\/1604.06174, 2016.","journal-title":"CoRR"},{"key":"e_1_3_2_1_17_1","first-page":"04972","article-title":"Device placement optimization with reinforcement learning","volume":"1706","author":"Mirhoseini A.","year":"2017","unstructured":"A. Mirhoseini , H. Pham , Q. V. Le , B. Steiner , R. Larsen , Y. Zhou , N. Kumar , M. Norouzi , S. Bengio , and J. Dean , \" Device placement optimization with reinforcement learning ,\" CoRR , vol. abs\/ 1706 . 04972 , 2017 . A. Mirhoseini, H. Pham, Q. V. Le, B. Steiner, R. Larsen, Y. Zhou, N. Kumar, M. Norouzi, S. Bengio, and J. Dean, \"Device placement optimization with reinforcement learning,\" CoRR, vol. abs\/1706.04972, 2017.","journal-title":"CoRR"},{"key":"e_1_3_2_1_18_1","volume-title":"Conference on Systems and Machine Learning, SysML '19","author":"Jia Z.","year":"2019","unstructured":"Z. Jia , M. Zaharia , and A. Aiken , \" Beyond data and model parallelism for deep neural networks,\" in Proc . Conference on Systems and Machine Learning, SysML '19 , 2019 . Z. Jia, M. Zaharia, and A. Aiken, \"Beyond data and model parallelism for deep neural networks,\" in Proc. Conference on Systems and Machine Learning, SysML '19, 2019."},{"key":"e_1_3_2_1_19_1","volume-title":"Conference on Systems and Machine Learning, SysML '19","author":"Jia Z.","year":"2019","unstructured":"Z. Jia , J. Thomas , T. Warszawski , M. Gao , M. Zaharia , and A. Aiken , \" Optimizing DNN computation with relaxed graph substitutions,\" in Proc . Conference on Systems and Machine Learning, SysML '19 , 2019 . Z. Jia, J. Thomas, T. Warszawski, M. Gao, M. Zaharia, and A. Aiken, \"Optimizing DNN computation with relaxed graph substitutions,\" in Proc. Conference on Systems and Machine Learning, SysML '19, 2019."},{"key":"e_1_3_2_1_20_1","volume-title":"SIGGRAPH '19","author":"Adams A.","year":"2019","unstructured":"A. Adams , K. Ma , L. Anderson , R. Baghdadi , T.-M. Li , S. Johnson , M. Gharbi , B. Steiner , K. Fatahalian , F. Durand , and J. Ragan-Kelley , \" Learning to optimize halide with tree search and random programs,\" in ACM Transactions on Graphics , SIGGRAPH '19 , 2019 . A. Adams, K. Ma, L. Anderson, R. Baghdadi, T.-M. Li, S. Johnson, M. Gharbi, B. Steiner, K. Fatahalian, F. Durand, and J. Ragan-Kelley, \"Learning to optimize halide with tree search and random programs,\" in ACM Transactions on Graphics, SIGGRAPH '19, 2019."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"e_1_3_2_1_22_1","unstructured":"\"APL programming language.\" https:\/\/en.wikipedia.org\/wiki\/APL_(programming_language). Accessed 2019-01-09. \"APL programming language.\" https:\/\/en.wikipedia.org\/wiki\/APL_(programming_language). Accessed 2019-01-09."},{"key":"e_1_3_2_1_23_1","unstructured":"\"TensorFlow.\" https:\/\/www.tensorflow.org\/. Accessed 2019-01-09. \"TensorFlow.\" https:\/\/www.tensorflow.org\/. Accessed 2019-01-09."},{"key":"e_1_3_2_1_24_1","unstructured":"\"Intel Math Kernel Library.\" https:\/\/software.intel.com\/en-us\/mkl. Accessed 2019-01-09. \"Intel Math Kernel Library.\" https:\/\/software.intel.com\/en-us\/mkl. Accessed 2019-01-09."},{"key":"e_1_3_2_1_25_1","unstructured":"\"About CUDA.\" https:\/\/developer.nvidia.com\/about-cuda. Accessed 2019-01-09. \"About CUDA.\" https:\/\/developer.nvidia.com\/about-cuda. Accessed 2019-01-09."},{"key":"e_1_3_2_1_26_1","first-page":"1607","article-title":"Julia: A fresh approach to numerical computing","volume":"1411","author":"Bezanson J.","year":"2014","unstructured":"J. Bezanson , A. Edelman , S. Karpinski , and V. B. Shah , \" Julia: A fresh approach to numerical computing ,\" CoRR , vol. abs\/ 1411 . 1607 , 2014 . J. Bezanson, A. Edelman, S. Karpinski, and V. B. Shah, \"Julia: A fresh approach to numerical computing,\" CoRR, vol. abs\/1411.1607, 2014.","journal-title":"CoRR"},{"key":"e_1_3_2_1_27_1","unstructured":"\"Auto-vectorization with vmap.\" https:\/\/github.com\/google\/jax#auto-vectorization-with-vmap. Accessed 2019-01-09. \"Auto-vectorization with vmap.\" https:\/\/github.com\/google\/jax#auto-vectorization-with-vmap. Accessed 2019-01-09."},{"key":"e_1_3_2_1_28_1","unstructured":"\"colah\/LabeledTensor.\" https:\/\/github.com\/colah\/LabeledTensor. Accessed 2019-01-09. \"colah\/LabeledTensor.\" https:\/\/github.com\/colah\/LabeledTensor. Accessed 2019-01-09."},{"key":"e_1_3_2_1_29_1","unstructured":"\"Labels for TensorFlow.\" https:\/\/github.com\/tensorflow\/tensorflow\/tree\/master\/tensorflow\/contrib\/labeled_tensor. Accessed 2019-01-09. \"Labels for TensorFlow.\" https:\/\/github.com\/tensorflow\/tensorflow\/tree\/master\/tensorflow\/contrib\/labeled_tensor. Accessed 2019-01-09."},{"key":"e_1_3_2_1_30_1","unstructured":"\"Tensor considered harmful.\" http:\/\/nlp.seas.harvard.edu\/NamedTensor. Accessed 2019-01-09. \"Tensor considered harmful.\" http:\/\/nlp.seas.harvard.edu\/NamedTensor. Accessed 2019-01-09."},{"key":"e_1_3_2_1_31_1","first-page":"02084","article-title":"Mesh-tensorflow: Deep learning for supercomputers","volume":"1811","author":"Shazeer N.","year":"2018","unstructured":"N. Shazeer , Y. Cheng , N. Parmar , D. Tran , A. Vaswani , P. Koanantakool , P. Hawkins , H. Lee , M. Hong , C. Young , R. Sepassi , and B. A. Hechtman , \" Mesh-tensorflow: Deep learning for supercomputers ,\" CoRR , vol. abs\/ 1811 . 02084 , 2018 . N. Shazeer, Y. Cheng, N. Parmar, D. Tran, A. Vaswani, P. Koanantakool, P. Hawkins, H. Lee, M. Hong, C. Young, R. Sepassi, and B. A. Hechtman, \"Mesh-tensorflow: Deep learning for supercomputers,\" CoRR, vol. abs\/1811.02084, 2018.","journal-title":"CoRR"},{"key":"e_1_3_2_1_32_1","unstructured":"\"Multi-level intermediate representation.\" https:\/\/github.com\/tensorflow\/mlir. Accessed 2019-04-05. \"Multi-level intermediate representation.\" https:\/\/github.com\/tensorflow\/mlir. Accessed 2019-04-05."}],"event":{"name":"HotOS '19: Workshop on Hot Topics in Operating Systems","location":"Bertinoro Italy","acronym":"HotOS '19","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the Workshop on Hot Topics in Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3317550.3321441","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3317550.3321441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:02:27Z","timestamp":1750208547000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3317550.3321441"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,13]]},"references-count":32,"alternative-id":["10.1145\/3317550.3321441","10.1145\/3317550"],"URL":"https:\/\/doi.org\/10.1145\/3317550.3321441","relation":{},"subject":[],"published":{"date-parts":[[2019,5,13]]},"assertion":[{"value":"2019-05-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}