{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T20:51:52Z","timestamp":1765486312389},"reference-count":109,"publisher":"Association for Computing Machinery (ACM)","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2019,3]]},"abstract":"<jats:p>Learning from the data stored in a database is an important function increasingly available in relational engines. Methods using lower precision input data are of special interest given their overall higher efficiency. However, in databases, these methods have a hidden cost: the quantization of the real value into a smaller number is an expensive step. To address this issue, we present ML-Weaving, a data structure and hardware acceleration technique intended to speed up learning of generalized linear models over low precision data. MLWeaving provides a compact in-memory representation that enables the retrieval of data at any level of precision. MLWeaving also provides a highly efficient implementation of stochastic gradient descent on FPGAs and enables the dynamic tuning of precision, instead of using a fixed precision level during learning. Experimental results show that MLWeaving converges up to 16 x faster than low-precision implementations of first-order methods on CPUs.<\/jats:p>","DOI":"10.14778\/3317315.3317322","type":"journal-article","created":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T13:27:58Z","timestamp":1556717278000},"page":"807-821","source":"Crossref","is-referenced-by-count":23,"title":["Accelerating generalized linear models with MLWeaving"],"prefix":"10.14778","volume":"12","author":[{"given":"Zeke","family":"Wang","sequence":"first","affiliation":[{"name":"ETH Zurich, Switzerland"}]},{"given":"Kaan","family":"Kara","sequence":"additional","affiliation":[{"name":"ETH Zurich, Switzerland"}]},{"given":"Hantian","family":"Zhang","sequence":"additional","affiliation":[{"name":"ETH Zurich, Switzerland"}]},{"given":"Gustavo","family":"Alonso","sequence":"additional","affiliation":[{"name":"ETH Zurich, Switzerland"}]},{"given":"Onur","family":"Mutlu","sequence":"additional","affiliation":[{"name":"ETH Zurich, Switzerland"}]},{"given":"Ce","family":"Zhang","sequence":"additional","affiliation":[{"name":"ETH Zurich, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2019,3]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.21"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00061"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123982"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.11"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2018.00014"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2009.34"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173212"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195647"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.40"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/376284.375692"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3177540.3177561"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071131"},{"key":"e_1_2_1_16_1","volume-title":"Low Precision Arithmetic For Deep Learning. CoRR, abs\/1412.7024","author":"Courbariaux M.","year":"2014","unstructured":"M. Courbariaux , Y. Bengio , and J. David . Low Precision Arithmetic For Deep Learning. CoRR, abs\/1412.7024 , 2014 . M. Courbariaux, Y. Bengio, and J. David. Low Precision Arithmetic For Deep Learning. CoRR, abs\/1412.7024, 2014."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080248"},{"key":"e_1_2_1_18_1","volume-title":"ArXiv","author":"Sa C. De","year":"2018","unstructured":"C. De Sa , M. Leszczynski , J. Zhang , A. Marzoev , C. R. Aberger , K. Olukotun , and C. R\u00e9 . High-Accuracy Low-Precision Training . ArXiv , 2018 . C. De Sa, M. Leszczynski, J. Zhang, A. Marzoev, C. R. Aberger, K. Olukotun, and C. R\u00e9. High-Accuracy Low-Precision Training. ArXiv, 2018."},{"key":"e_1_2_1_19_1","volume-title":"Tartan: Accelerating Fully-Connected and Convolutional Layers in Deep Learning Networks by Exploiting Numerical Precision Variability. CoRR, abs\/1707.09068","author":"Delmas A.","year":"2017","unstructured":"A. Delmas , S. Sharify , P. Judd , and A. Moshovos . Tartan: Accelerating Fully-Connected and Convolutional Layers in Deep Learning Networks by Exploiting Numerical Precision Variability. CoRR, abs\/1707.09068 , 2017 . A. Delmas, S. Sharify, P. Judd, and A. Moshovos. Tartan: Accelerating Fully-Connected and Convolutional Layers in Deep Learning Networks by Exploiting Numerical Precision Variability. CoRR, abs\/1707.09068, 2017."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00040"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994515"},{"key":"e_1_2_1_23_1","volume-title":"ISCA","author":"Espasa R.","year":"2002","unstructured":"R. Espasa , F. Ardanaz , J. Emer , S. Felix , J. Gago , R. Gramunt , I. Hernandez , T. Juan , G. Lowney , M. Mattina , and A. Seznec . Tarantula: a vector extension to the alpha architecture . In ISCA , 2002 . R. Espasa, F. Ardanaz, J. Emer, S. Felix, J. Gago, R. Gramunt, I. Hernandez, T. Juan, G. Lowney, M. Mattina, and A. Seznec. Tarantula: a vector extension to the alpha architecture. In ISCA, 2002."},{"key":"e_1_2_1_24_1","volume-title":"IEEE Data Eng. Bull.","author":"Farber F.","year":"2012","unstructured":"F. Farber , N. May , W. Lehner , I. Muller , H. Rauhe , J. Dees , and S. Ag . The SAP HANA Database: An Architecture Overview . In IEEE Data Eng. Bull. , 2012 . F. Farber, N. May, W. Lehner, I. Muller, H. Rauhe, J. Dees, and S. Ag. The SAP HANA Database: An Architecture Overview. In IEEE Data Eng. Bull., 2012."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2747642"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00012"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.14778\/1921071.1921077"},{"key":"e_1_2_1_28_1","volume-title":"FPL","author":"Gupta P.","year":"2016","unstructured":"P. Gupta . Accelerating Datacenter Workloads . FPL , 2016 . P. Gupta. Accelerating Datacenter Workloads. FPL, 2016."},{"key":"e_1_2_1_29_1","volume-title":"ICML","author":"Gupta S.","year":"2015","unstructured":"S. Gupta , A. Agrawal , K. Gopalakrishnan , and P. Narayanan . Deep Learning with Limited Numerical Precision . In ICML , 2015 . S. Gupta, A. Agrawal, K. Gopalakrishnan, and P. Narayanan. Deep Learning with Limited Numerical Precision. In ICML, 2015."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"e_1_2_1_31_1","volume-title":"Trained Quantization and Huffman Coding. In ICLR","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. In ICLR , 2015 . S. Han, H. Mao, and W. J. Dally. Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding. In ICLR, 2015."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367510"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/6519"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1247480.1247525"},{"key":"e_1_2_1_35_1","volume-title":"MonetDB: Two Decades of Research in Column-oriented Database","author":"Idreos S.","year":"2012","unstructured":"S. Idreos , F. Groffen , N. Nes , S. Manegold , S. Mullender , and M. Kersten . MonetDB: Two Decades of Research in Column-oriented Database . IEEE Data Engineering Bulletin , 2012 . S. Idreos, F. Groffen, N. Nes, S. Manegold, S. Mullender, and M. Kersten. MonetDB: Two Decades of Research in Column-oriented Database. IEEE Data Engineering Bulletin, 2012."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2016.61"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2612174"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00070"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173205"},{"key":"e_1_2_1_40_1","volume-title":"CIDR","author":"Johnson R.","year":"2013","unstructured":"R. Johnson and I. Pandis . The Bionic DBMS is Coming, but What Will It Look Like ? In CIDR , 2013 . R. Johnson and I. Pandis. The Bionic DBMS is Coming, but What Will It Look Like? In CIDR, 2013."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926294"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195661"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017616"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.39"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.14778\/3297753.3297756"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035946"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2012.290"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.37"},{"key":"e_1_2_1_50_1","volume-title":"NIPS.","author":"K\u00f6ster U.","year":"2017","unstructured":"U. K\u00f6ster , T. Webb , X. Wang , M. Nassar , A. K. Bansal , W. Constable , O. Elibol , S. Gray , S. Hall , L. Hornof , A. Khosrowshahi , C. Kloss , R. J. Pai , and N. Rao . Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks . In NIPS. 2017 . U. K\u00f6ster, T. Webb, X. Wang, M. Nassar, A. K. Bansal, W. Constable, O. Elibol, S. Gray, S. Hall, L. Hornof, A. Khosrowshahi, C. Kloss, R. J. Pai, and N. Rao. Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks. In NIPS. 2017."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/774861.774892"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2003.1261385"},{"key":"e_1_2_1_53_1","volume-title":"NIPS.","author":"Krizhevsky A.","year":"2012","unstructured":"A. Krizhevsky , I. Sutskever , and G. Hinton . ImageNet Classification with Deep Convolutional Neural Networks . In NIPS. 2012 . A. Krizhevsky, I. Sutskever, and G. Hinton. ImageNet Classification with Deep Convolutional Neural Networks. In NIPS. 2012."},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173176"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/360933.360994"},{"key":"e_1_2_1_56_1","volume-title":"NIPS.","author":"Lee D.","year":"2001","unstructured":"D. Lee and S. Sebastian . Algorithms for Non-negative Matrix Factorization . In NIPS. 2001 . D. Lee and S. Sebastian. Algorithms for Non-negative Matrix Factorization. In NIPS. 2001."},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623612"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898064"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465322"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732951.2732965"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00028"},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694358"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.14778\/3231751.3231770"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.14778\/3236187.3236188"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446050"},{"key":"e_1_2_1_66_1","volume-title":"VLSI-Circuits","author":"Moons B.","year":"2016","unstructured":"B. Moons and M. Verhelst . A 0.3 \u00d72013;2.6 TOPS\/W precision-scalable processor for real-time large-scale ConvNets . In VLSI-Circuits , 2016 . B. Moons and M. Verhelst. A 0.3 \u00d72013;2.6 TOPS\/W precision-scalable processor for real-time large-scale ConvNets. In VLSI-Circuits, 2016."},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056066"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687730"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687654"},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807307"},{"key":"e_1_2_1_71_1","volume-title":"NIPS.","author":"Niu F.","year":"2011","unstructured":"F. Niu , B. Recht , C. Re , and S. Wright . Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent . In NIPS. 2011 . F. Niu, B. Recht, C. Re, and S. Wright. Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent. In NIPS. 2011."},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/253260.253268"},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.37"},{"key":"e_1_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540724"},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/2771937.2771943"},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2008.4497414"},{"key":"e_1_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.32"},{"key":"e_1_2_1_78_1","volume-title":"Defense of One-Vs-All Classification. In JMLR.","author":"Rifkin R.","year":"2004","unstructured":"R. Rifkin and A. Klautau . In Defense of One-Vs-All Classification. In JMLR. 2004 . R. Rifkin and A. Klautau. In Defense of One-Vs-All Classification. In JMLR. 2004."},{"key":"e_1_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/376284.375669"},{"key":"e_1_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/359327.359336"},{"key":"e_1_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/1869389.1869394"},{"key":"e_1_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2434872"},{"key":"e_1_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124544"},{"key":"e_1_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195659"},{"key":"e_1_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"},{"key":"e_1_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035954"},{"key":"e_1_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3058746"},{"key":"e_1_2_1_88_1","volume-title":"Energy Efficient Filtering Using Adaptive Precision and Variable Voltage. In IEEE International ASIC\/SOC Conference","author":"Sinha A.","year":"1999","unstructured":"A. Sinha and A. P. Chandrakasan . Energy Efficient Filtering Using Adaptive Precision and Variable Voltage. In IEEE International ASIC\/SOC Conference , 1999 . A. Sinha and A. P. Chandrakasan. Energy Efficient Filtering Using Adaptive Precision and Variable Voltage. In IEEE International ASIC\/SOC Conference, 1999."},{"key":"e_1_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_2_1_90_1","volume-title":"CVPR.","author":"Szegedy C.","year":"2016","unstructured":"C. Szegedy , V. Vanhoucke , S. Ioffe , J. Shlens , and Z. Wojna . Rethinking the Inception Architecture For Computer Vision . In CVPR. 2016 . C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna. Rethinking the Inception Architecture For Computer Vision. In CVPR. 2016."},{"key":"e_1_2_1_91_1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01849-7","volume-title":"Data Processing on FPGAs Synthesis Lectures on Data Management","author":"Teubner J.","year":"2013","unstructured":"J. Teubner and L. Woods . Data Processing on FPGAs Synthesis Lectures on Data Management . 2013 . J. Teubner and L. Woods. Data Processing on FPGAs Synthesis Lectures on Data Management. 2013."},{"key":"e_1_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021744"},{"key":"e_1_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2018.00059"},{"key":"e_1_2_1_94_1","volume-title":"Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD. CoRR, abs\/1810.08313","author":"Wang J.","year":"2018","unstructured":"J. Wang and G. Joshi . Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD. CoRR, abs\/1810.08313 , 2018 . J. Wang and G. Joshi. Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD. CoRR, abs\/1810.08313, 2018."},{"key":"e_1_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2015.7293941"},{"key":"e_1_2_1_96_1","volume-title":"CoRR","author":"Wang Z.","year":"2019","unstructured":"Z. Wang , K. Kara , H. Zhang , G. Alonso , O. Mutlu , and C. Zhang . Accelerating Generalized Linear Models with MLWeaving:A One-Size-Fits-All System for Any-Precision Learning (Technical Report) . CoRR , 2019 . Z. Wang, K. Kara, H. Zhang, G. Alonso, O. Mutlu, and C. Zhang. Accelerating Generalized Linear Models with MLWeaving:A One-Size-Fits-All System for Any-Precision Learning (Technical Report). CoRR, 2019."},{"key":"e_1_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2016.7577329"},{"issue":"6","key":"e_1_2_1_98_1","first-page":"1906","volume":"25","author":"Wang Z.","year":"2017","unstructured":"Z. Wang , J. Paul , B. He , and W. Zhang . Multikernel Data Partitioning With Channel on OpenCL-Based FPGAs. TVLSI , 25 ( 6 ): 1906 -- 1918 , 2017 . Z. Wang, J. Paul, B. He, and W. Zhang. Multikernel Data Partitioning With Channel on OpenCL-Based FPGAs. TVLSI, 25(6):1906--1918, 2017.","journal-title":"Multikernel Data Partitioning With Channel on OpenCL-Based FPGAs. TVLSI"},{"key":"e_1_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2018.00125"},{"key":"e_1_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553516"},{"key":"e_1_2_1_101_1","doi-asserted-by":"publisher","DOI":"10.1145\/362084.362137"},{"key":"e_1_2_1_102_1","doi-asserted-by":"publisher","DOI":"10.1109\/53.29648"},{"key":"e_1_2_1_103_1","volume-title":"Intel Performance Counter Monitor - A better way to measure CPU utilization, https:\/\/software.intel.com\/en-us\/articles\/intel-performance-counter-monitor","author":"Willhalm T.","year":"2016","unstructured":"T. Willhalm , R. Dementiev , and P. Fay . Intel Performance Counter Monitor - A better way to measure CPU utilization, https:\/\/software.intel.com\/en-us\/articles\/intel-performance-counter-monitor , 2016 . T. Willhalm, R. Dementiev, and P. Fay. Intel Performance Counter Monitor - A better way to measure CPU utilization, https:\/\/software.intel.com\/en-us\/articles\/intel-performance-counter-monitor, 2016."},{"key":"e_1_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732967.2732972"},{"key":"e_1_2_1_105_1","volume-title":"Symposium on VLSI Circuits","author":"Xanthopoulos T.","year":"1999","unstructured":"T. Xanthopoulos and A. Chandrakasan . A Low-power DCT Core Using Adaptive Bitwidth and Arithmetic Activity Exploiting Signal Correlations and Quantization . In Symposium on VLSI Circuits , 1999 . T. Xanthopoulos and A. Chandrakasan. A Low-power DCT Core Using Adaptive Bitwidth and Arithmetic Activity Exploiting Signal Correlations and Quantization. In Symposium on VLSI Circuits, 1999."},{"key":"e_1_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080215"},{"key":"e_1_2_1_107_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732977.2733001"},{"key":"e_1_2_1_108_1","first-page":"4035","volume-title":"ICML","volume":"70","author":"Zhang H.","year":"2017","unstructured":"H. Zhang , J. Li , K. Kara , D. Alistarh , J. Liu , and C. Zhang . ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning . In ICML , volume 70 , pages 4035 -- 4043 , 2017 . H. Zhang, J. Li, K. Kara, D. Alistarh, J. Liu, and C. Zhang. ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning. In ICML, volume 70, pages 4035--4043, 2017."},{"key":"e_1_2_1_109_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."}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3317315.3317322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T11:09:11Z","timestamp":1672225751000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3317315.3317322"}},"subtitle":["a one-size-fits-all system for any-precision learning"],"short-title":[],"issued":{"date-parts":[[2019,3]]},"references-count":109,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["10.14778\/3317315.3317322"],"URL":"https:\/\/doi.org\/10.14778\/3317315.3317322","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2019,3]]}}}