{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:50:27Z","timestamp":1784217027201,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,6,26]],"date-time":"2017-06-26T00:00:00Z","timestamp":1498435200000},"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":[[2017,6,26]]},"DOI":"10.1145\/3078597.3078602","type":"proceedings-article","created":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T12:46:51Z","timestamp":1498222011000},"page":"79-92","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":37,"title":["CuMF_SGD"],"prefix":"10.1145","author":[{"given":"Xiaolong","family":"Xie","sequence":"first","affiliation":[{"name":"Peking University & IBM Thomas J. Watson Research Center, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Tan","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liana L.","family":"Fong","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Liang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,6,26]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Recommending items to more than a billion people 2015. https:\/\/code.facebook.com\/posts\/861999383875667\/recommending-items-to-more-than-a-billion-people\/.  Recommending items to more than a billion people 2015. https:\/\/code.facebook.com\/posts\/861999383875667\/recommending-items-to-more-than-a-billion-people\/."},{"key":"e_1_3_2_1_2_1","unstructured":"NVIDIA CUDA programming guide. 2016. http:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide.  NVIDIA CUDA programming guide. 2016. http:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide."},{"key":"e_1_3_2_1_3_1","volume-title":"https:\/\/developer.nvidia.com\/maxwell-compute-architecture","author":"Maxwell Architecture NVIDIA","year":"2016","unstructured":"NVIDIA Maxwell Architecture . https:\/\/developer.nvidia.com\/maxwell-compute-architecture , 2016 . NVIDIA Maxwell Architecture . https:\/\/developer.nvidia.com\/maxwell-compute-architecture, 2016."},{"key":"e_1_3_2_1_4_1","unstructured":"NVIDIA NVLink 2016. http:\/\/www.nvidia.com\/object\/nvlink.html.  NVIDIA NVLink 2016. http:\/\/www.nvidia.com\/object\/nvlink.html."},{"key":"e_1_3_2_1_5_1","unstructured":"NVIDIA Pascal Architecture 2016. http:\/\/www.geforce.com\/hardware\/10series\/architecture.  NVIDIA Pascal Architecture 2016. http:\/\/www.geforce.com\/hardware\/10series\/architecture."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","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 , : A system for large-scale machine learning . In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI) . Savannah, Georgia, USA , 2016 . M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, et al. Tensorflow: A system for large-scale machine learning. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI). Savannah, Georgia, USA, 2016."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2012.239"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2015.73"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33078-0_22"},{"key":"e_1_3_2_1_11_1","volume-title":"NIPS Workshop","author":"Canny J.","year":"2013","unstructured":"J. Canny and H. Zhao . Bidmach: Large-scale learning with zero memory allocation. In BigLearning , NIPS Workshop , 2013 . J. Canny and H. Zhao. Bidmach: Large-scale learning with zero memory allocation. In BigLearning, NIPS Workshop, 2013."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052627"},{"key":"e_1_3_2_1_13_1","first-page":"57","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Chen J.","unstructured":"J. Chen , L. Tan , P. Wu , D. Tao , H. Li , X. Liang , S. Li , R. Ge , L. Bhuyan , and Z. Chen . GreenLA: green linear algebra software for GPU-accelerated heterogeneous computing . In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis , page 57 . IEEE Press, 2016. J. Chen, L. Tan, P. Wu, D. Tao, H. Li, X. Liang, S. Li, R. Ge, L. Bhuyan, and Z. Chen. GreenLA: green linear algebra software for GPU-accelerated heterogeneous computing. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, page 57. IEEE Press, 2016."},{"key":"e_1_3_2_1_14_1","volume-title":"Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274","author":"Chen T.","year":"2015","unstructured":"T. Chen , M. Li , Y. Li , M. Lin , N. Wang , M. Wang , T. Xiao , B. Xu , C. Zhang , and Z. Zhang . Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274 , 2015 . T. Chen, M. Li, Y. Li, M. Lin, N. Wang, M. Wang, T. Xiao, B. Xu, C. Zhang, and Z. Zhang. Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274, 2015."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2668133"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-18038-0_35"},{"key":"e_1_3_2_1_17_1","first-page":"1223","volume-title":"Advances in neural information processing systems","author":"Dean J.","year":"2012","unstructured":"J. Dean , G. Corrado , R. Monga , K. Chen , M. Devin , M. Mao , A. Senior , P. Tucker , K. Yang , Q. V. Le , Large scale distributed deep networks . In Advances in neural information processing systems , pages 1223 -- 1231 , 2012 . J. Dean, G. Corrado, R. Monga, K. Chen, M. Devin, M. Mao, A. Senior, P. Tucker, K. Yang, Q. V. Le, et al. Large scale distributed deep networks. In Advances in neural information processing systems, pages 1223--1231, 2012."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICGHPC.2016.7508071"},{"key":"e_1_3_2_1_19_1","volume-title":"Supercomputing, 2013. Proceedings of the 2013 ACM\/IEEE International Conference on","author":"del Mundo C.","year":"2013","unstructured":"C. del Mundo and W.-c. Feng . Enabling efficient intra-warp communication for Fourier transforms in a many-core architecture . In Supercomputing, 2013. Proceedings of the 2013 ACM\/IEEE International Conference on , 2013 . C. del Mundo and W.-c. Feng. Enabling efficient intra-warp communication for Fourier transforms in a many-core architecture. In Supercomputing, 2013. Proceedings of the 2013 ACM\/IEEE International Conference on, 2013."},{"key":"e_1_3_2_1_20_1","volume-title":"Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12(Jul):2121--2159","author":"Duchi J.","year":"2011","unstructured":"J. Duchi , E. Hazan , and Y. Singer . Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12(Jul):2121--2159 , 2011 . J. Duchi, E. Hazan, and Y. Singer. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12(Jul):2121--2159, 2011."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2011.45"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2015.7363811"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020426"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2016.94"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/3018843.3018854"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020577"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3722"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2499368.2451158"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818950.2818979"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508148.2485951"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2716282.2716289"},{"key":"e_1_3_2_1_32_1","volume-title":"Newnes","author":"Kirk D. B.","year":"2012","unstructured":"D. B. Kirk and W. H. Wen-mei . Programming massively parallel processors: a hands-on approach . Newnes , 2012 . D. B. Kirk and W. H. Wen-mei. Programming massively parallel processors: a hands-on approach. Newnes, 2012."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1137\/07070111X"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2452376.2452449"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751237"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623612"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2792838.2800191"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.14778\/2212351.2212354"},{"key":"e_1_3_2_1_40_1","volume-title":"JMLR","author":"Meng X.","year":"2016","unstructured":"X. Meng , J. Bradley , B. Yuvaz , E. Sparks , S. Venkataraman , D. Liu , J. Freeman , D. Tsai , M. Amde , S. Owen , : Machine learning in apache spark . JMLR , 2016 . X. Meng, J. Bradley, B. Yuvaz, E. Sparks, S. Venkataraman, D. Liu, J. Freeman, D. Tsai, M. Amde, S. Owen, et al. Mllib: Machine learning in apache spark. JMLR, 2016."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2015.135"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783322"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_44_1","first-page":"693","volume-title":"Advances in Neural Information Processing Systems","author":"Recht B.","year":"2011","unstructured":"B. Recht , C. Re , S. Wright , and F. Niu . Hogwild: A lock-free approach to parallelizing stochastic gradient descent . In Advances in Neural Information Processing Systems , pages 693 -- 701 , 2011 . B. Recht, C. Re, S. Wright, and F. Niu. Hogwild: A lock-free approach to parallelizing stochastic gradient descent. In Advances in Neural Information Processing Systems, pages 693--701, 2011."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/1345206.1345220"},{"key":"e_1_3_2_1_46_1","volume-title":"Factorbird-a parameter server approach to distributed matrix factorization. arXiv preprint arXiv:1411.0602","author":"Schelter S.","year":"2014","unstructured":"S. Schelter , V. Satuluri , and R. Zadeh . Factorbird-a parameter server approach to distributed matrix factorization. arXiv preprint arXiv:1411.0602 , 2014 . S. Schelter, V. Satuluri, and R. Zadeh. Factorbird-a parameter server approach to distributed matrix factorization. arXiv preprint arXiv:1411.0602, 2014."},{"key":"e_1_3_2_1_47_1","first-page":"10","volume-title":"Proceedings 20th IEEE International Parallel and Distributed Processing Symposium","author":"Shipman G. M.","unstructured":"G. M. Shipman , T. S. Woodall , R. L. Graham , A. B. Maccabe , and P. G. Bridges . Infiniband scalability in Open MPI . In Proceedings 20th IEEE International Parallel and Distributed Processing Symposium , pages 10 --pp. IEEE, 2006. G. M. Shipman, T. S. Woodall, R. L. Graham, A. B. Maccabe, and P. G. Bridges. Infiniband scalability in Open MPI. In Proceedings 20th IEEE International Parallel and Distributed Processing Symposium, pages 10--pp. IEEE, 2006."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2016.7495635"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370903"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967951"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2907294.2907297"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.120"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2016.0139"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830813"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.5555\/2561828.2561929"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056023"},{"key":"e_1_3_2_1_58_1","first-page":"26","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Yan F.","unstructured":"F. Yan , O. Ruwase , Y. He , and E. Smirni . SERF: efficient scheduling for fast deep neural network serving via judicious parallelism . In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis , page 26 . IEEE Press, 2016. F. Yan, O. Ruwase, Y. He, and E. Smirni. SERF: efficient scheduling for fast deep neural network serving via judicious parallelism. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, page 26. IEEE Press, 2016."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/1806596.1806606"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.168"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.168"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741682"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732967.2732973"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33347-7_17"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015332"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68880-8_32"},{"key":"e_1_3_2_1_67_1","volume-title":"NIPS","author":"Zinkevich M.","year":"2010","unstructured":"M. Zinkevich , M. Weimer , L. Li , and A. J. Smola . Parallelized stochastic gradient descent . In NIPS , 2010 . M. Zinkevich, M. Weimer, L. Li, and A. J. Smola. Parallelized stochastic gradient descent. In NIPS, 2010."}],"event":{"name":"HPDC '17: The 26th International Symposium on High-Performance Parallel and Distributed Computing","location":"Washington DC USA","acronym":"HPDC '17","sponsor":["University of Arizona University of Arizona","SIGARCH ACM Special Interest Group on Computer Architecture","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the 26th International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3078597.3078602","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3078597.3078602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:03:15Z","timestamp":1750215795000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3078597.3078602"}},"subtitle":["Parallelized Stochastic Gradient Descent for Matrix Factorization on GPUs"],"short-title":[],"issued":{"date-parts":[[2017,6,26]]},"references-count":67,"alternative-id":["10.1145\/3078597.3078602","10.1145\/3078597"],"URL":"https:\/\/doi.org\/10.1145\/3078597.3078602","relation":{},"subject":[],"published":{"date-parts":[[2017,6,26]]},"assertion":[{"value":"2017-06-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}