{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:45:28Z","timestamp":1772725528034,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,4,4]],"date-time":"2017-04-04T00:00:00Z","timestamp":1491264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["SHF-1408911"],"award-info":[{"award-number":["SHF-1408911"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,4,4]]},"DOI":"10.1145\/3037697.3037702","type":"proceedings-article","created":{"date-parts":[[2017,4,5]],"date-time":"2017-04-05T08:47:40Z","timestamp":1491382060000},"page":"751-764","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":315,"title":["TETRIS"],"prefix":"10.1145","author":[{"given":"Mingyu","family":"Gao","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"given":"Jing","family":"Pu","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"given":"Xuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"given":"Mark","family":"Horowitz","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"given":"Christos","family":"Kozyrakis","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2017,4,4]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"265","volume-title":"TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Abadi M.","year":"2016"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001138"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2014.55"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418007"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001140"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.2197\/ipsjtsldm.4.31"},{"key":"e_1_3_2_1_11_1","first-page":"1223","volume-title":"Large Scale Distributed Deep Networks. In 25th International Conference on Neural Information Processing Systems (NIPS)","author":"Dean J.","year":"2012"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2014.7040963"},{"key":"e_1_3_2_1_14_1","volume-title":"Thermal Feasibility of Die-Stacked Processing in Memory. In 2nd Workshop on Near-Data Processing (WoNDP)","author":"Eckert Y.","year":"2014"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2011.5981829"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446059"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.22"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"K. He X. Zhang S. Ren and J. Sun. Deep Residual Learning for Image Recognition. arXiv preprint arXiv:1512.03385 2015.  K. He X. Zhang S. Ren and J. Sun. Deep Residual Learning for Image Recognition. arXiv preprint arXiv:1512.03385 2015.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_20_1","unstructured":"Hybrid Memory Cube Consortium. Hybrid Memory Cube Specification 2.1 2014.  Hybrid Memory Cube Consortium. Hybrid Memory Cube Specification 2.1 2014."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/VLSIT.2012.6242474"},{"key":"e_1_3_2_1_22_1","unstructured":"JEDEC Standard. High Bandwidth Memory (HBM) DRAM. JESD235A 2015.  JEDEC Standard. High Bandwidth Memory (HBM) DRAM. JESD235A 2015."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Y. Jia E. Shelhamer J. Donahue S. Karayev J. Long R. Girshick S. Guadarrama and T. Darrell. Caffe: Convolutional Architecture for Fast Feature Embedding. arXiv preprint arXiv:1408.5093 2014.  Y. Jia E. Shelhamer J. Donahue S. Karayev J. Long R. Girshick S. Guadarrama and T. Darrell. Caffe: Convolutional Architecture for Fast Feature Embedding. arXiv preprint arXiv:1408.5093 2014.","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/DATE.2009.5090700"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001178"},{"key":"e_1_3_2_1_26_1","first-page":"1097","volume-title":"ImageNet Classification with Deep Convolutional Neural Networks. In 25th International Conference on Neural Information Processing Systems (NIPS)","author":"Krizhevsky A.","year":"2012"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757501"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2011.6105405"},{"key":"e_1_3_2_1_30_1","first-page":"61","volume-title":"ADRES: An Architecture with Tightly Coupled VLIW Processor and Coarse-Grained Reconfigurable Matrix. In 13th International Conference on Field Programmable Logic and Application (FPL)","author":"Mei B.","year":"2003"},{"key":"e_1_3_2_1_31_1","unstructured":"Micron Technology Inc. TN-41-01: Calculating Memory System Power for DDR3 . https:\/\/www.micron.com\/support\/tools-and-utilities\/power-calc 2007.  Micron Technology Inc. TN-41-01: Calculating Memory System Power for DDR3 . https:\/\/www.micron.com\/support\/tools-and-utilities\/power-calc 2007."},{"key":"e_1_3_2_1_32_1","unstructured":"Micron Technology Inc. Mobile LPDDR3 SDRAM: 178-Ball Single-Channel Mobile LPDDR3 SDRAM Features. https:\/\/www.micron.com\/products\/dram\/lpdram\/16Gb 2014.  Micron Technology Inc. Mobile LPDDR3 SDRAM: 178-Ball Single-Channel Mobile LPDDR3 SDRAM Features. https:\/\/www.micron.com\/products\/dram\/lpdram\/16Gb 2014."},{"key":"e_1_3_2_1_33_1","first-page":"1","volume-title":"Scalable Deep Learning\/Inference Processor with Tetra-Parallel MIMD Architecture for Big-Data Applications. In IEEE International Solid-State Circuits Conference (ISSCC)","author":"Park S.","year":"2015"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2013.6657019"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844483"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001165"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485963"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540725"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2434872"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001139"},{"key":"e_1_3_2_1_41_1","unstructured":"K. Simonyan and A. Zisserman. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556 2014.  K. Simonyan and A. Zisserman. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556 2014."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.859540"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.42"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/DATE.2011.5763068"},{"key":"e_1_3_2_1_45_1","unstructured":"X. Yang J. Pu B. B. Rister N. Bhagdikar S. Richardson S. Kvatinsky J. Ragan-Kelley A. Pedram and M. Horowitz. A Systematic Approach to Blocking Convolutional Neural Networks. arXiv preprint arXiv:1606.04209 2016.  X. Yang J. Pu B. B. Rister N. Bhagdikar S. Richardson S. Kvatinsky J. Ragan-Kelley A. Pedram and M. Horowitz. A Systematic Approach to Blocking Convolutional Neural Networks. arXiv preprint arXiv:1606.04209 2016."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"e_1_3_2_1_47_1","first-page":"161","volume-title":"Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks. In 2015 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA)","author":"Zhang C.","year":"2015"}],"event":{"name":"ASPLOS '17: Architectural Support for Programming Languages and Operating Systems","location":"Xi'an China","acronym":"ASPLOS '17","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-Second International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3037697.3037702","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3037697.3037702","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3037697.3037702","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:50:26Z","timestamp":1750204226000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3037697.3037702"}},"subtitle":["Scalable and Efficient Neural Network Acceleration with 3D Memory"],"short-title":[],"issued":{"date-parts":[[2017,4,4]]},"references-count":47,"alternative-id":["10.1145\/3037697.3037702","10.1145\/3037697"],"URL":"https:\/\/doi.org\/10.1145\/3037697.3037702","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/3093336.3037702","asserted-by":"object"},{"id-type":"doi","id":"10.1145\/3093337.3037702","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2017,4,4]]},"assertion":[{"value":"2017-04-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}