{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T07:57:22Z","timestamp":1726041442040},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030296100"},{"type":"electronic","value":"9783030296117"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-29611-7_6","type":"book-chapter","created":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T19:02:59Z","timestamp":1565636579000},"page":"71-85","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SPART: Optimizing CNNs by Utilizing Both Sparsity of Weights and Feature Maps"],"prefix":"10.1007","author":[{"given":"Jiaming","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,8,9]]},"reference":[{"issue":"3","key":"6_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3007787.3001138","volume":"44","author":"J Albericio","year":"2016","unstructured":"Albericio, J., Judd, P., Hetherington, T., Aamodt, T., Jerger, N.E., Moshovos, A.: Cnvlutin: ineffectual-neuron-free deep neural network computing. SIGARCH Comput. Archit. News 44(3), 1\u201313 (2016). \n                      https:\/\/doi.org\/10.1145\/3007787.3001138","journal-title":"SIGARCH Comput. Archit. News"},{"key":"6_CR2","doi-asserted-by":"publisher","unstructured":"Bell, N., Garland, M.: Implementing sparse matrix-vector multiplication on throughput-oriented processors. In: SC 2009, p. 11. ACM, New York (2009). \n                      https:\/\/doi.org\/10.1145\/1654059.1654078\n                      \n                    . Article 18","DOI":"10.1145\/1654059.1654078"},{"key":"6_CR3","unstructured":"Chen, X.: Escort: efficient sparse convolutional neural networks on GPUs. CoRR abs\/1802.10280 (2018). \n                      arXiv:1802.10280"},{"key":"6_CR4","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1109\/ACCESS.2014.2325029","volume":"2","author":"XW Chen","year":"2014","unstructured":"Chen, X.W., Lin, X.: Big data deep learning: challenges and perspectives. IEEE Access 2, 514\u2013525 (2014). \n                      https:\/\/doi.org\/10.1109\/ACCESS.2014.2325029","journal-title":"IEEE Access"},{"key":"6_CR5","doi-asserted-by":"publisher","unstructured":"Chen, Y., Emer, J., Sze, V.: Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks. In: ISCA 2016, pp. 367\u2013379 (2016). \n                      https:\/\/doi.org\/10.1109\/ISCA.2016.40","DOI":"10.1109\/ISCA.2016.40"},{"key":"6_CR6","unstructured":"Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12, 2493\u20132537 (2011). \n                      http:\/\/dl.acm.org\/citation.cfm?id=1953048.2078186"},{"issue":"1","key":"6_CR7","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1145\/2049662.2049663","volume":"38","author":"TA Davis","year":"2011","unstructured":"Davis, T.A., Hu, Y.: The University of Florida sparse matrix collection. ACM Trans. Math. Softw. 38(1), 25 (2011). \n                      https:\/\/doi.org\/10.1145\/2049662.2049663\n                      \n                    . Article 1","journal-title":"ACM Trans. Math. Softw."},{"key":"6_CR8","unstructured":"Han, S., et al.: Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. In: ICLR (2015)"},{"key":"6_CR9","unstructured":"Han, S., et al.: EIE: efficient inference engine on compressed deep neural network. CoRR abs\/1602.01528 (2016). \n                      arXiv:1602.01528"},{"key":"6_CR10","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. CoRR abs\/1502.01852 (2015). \n                      arXiv:1502.01852"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: MM (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"6_CR12","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"6_CR13","unstructured":"Lavin, A.: Fast algorithms for convolutional neural networks. CoRR abs\/1509.09308 (2015). \n                      arXiv:1509.09308"},{"key":"6_CR14","doi-asserted-by":"publisher","unstructured":"Li, X., Liang, Y., Yan, S., Jia, L., Li, Y.: A coordinated tiling and batching framework for efficient GEMM on GPUs. In: PPoPP 2019, pp. 229\u2013241. ACM, New York (2019). \n                      https:\/\/doi.org\/10.1145\/3293883.3295734","DOI":"10.1145\/3293883.3295734"},{"key":"6_CR15","doi-asserted-by":"publisher","unstructured":"Li, X., et al.: cuMBIR: an efficient framework for low-dose X-ray CT image reconstruction on GPUs. In: ICS 2018, pp. 184\u2013194. ACM, New York (2018). \n                      https:\/\/doi.org\/10.1145\/3205289.3205309","DOI":"10.1145\/3205289.3205309"},{"key":"6_CR16","unstructured":"Luo, J.H., Wu, J., Lin, W.: ThiNet: a filter level pruning method for deep neural network compression. CoRR abs\/1707.06342 (2017). \n                      arXiv:1707.06342"},{"key":"6_CR17","unstructured":"Mathieu, M., Henaff, M., LeCun, Y.: Fast training of convolutional networks through FFTs. CoRR abs\/1312.5851 (2013). \n                      arXiv:1312.5851"},{"key":"6_CR18","unstructured":"NVIDIA: cuBLAS Library (2018a). \n                      https:\/\/docs.nvidia.com\/cublas"},{"key":"6_CR19","unstructured":"NVIDIA: cuDNN Library (2018b). \n                      https:\/\/developer.nvidia.com\/cudnn"},{"key":"6_CR20","unstructured":"NVIDIA: cuSPARSE Library (2018c). \n                      https:\/\/docs.nvidia.com\/cusparse"},{"key":"6_CR21","unstructured":"NVIDIA: GTX Titan X: a desktop GPU (2018d). \n                      https:\/\/www.geforce.com\/hardware\/desktop-gpus\/geforce-gtx-titan-x"},{"key":"6_CR22","unstructured":"NVIDIA: v100: a data-center GPU for AI (2018e). \n                      https:\/\/www.nvidia.com\/en-us\/data-center\/tesla-v100\/"},{"key":"6_CR23","unstructured":"Parashar, A., et al.: SCNN: an accelerator for compressed-sparse convolutional neural networks. CoRR abs\/1708.04485 (2017). \n                      arXiv:1708.04485"},{"key":"6_CR24","unstructured":"Park, J., Li, S.R., Wen, W., Li, H., Chen, Y., Dubey, P.: Holistic SparseCNN: forging the trident of accuracy, speed, and size. CoRR abs\/1608.01409 (2016). \n                      arXiv:1608.01409"},{"key":"6_CR25","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014). \n                      arXiv:1409.1556"},{"key":"6_CR26","unstructured":"Sze, V., Chen, Y.-H., Yang, T.-J., Emer, J.S.: Efficient processing of deep neural networks: a tutorial and survey. CoRR abs\/1703.09039 (2017). \n                      arXiv:1703.09039"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"6_CR28","unstructured":"Wen, W., Wu, C., Wang, Y., Chen, Y., Li, H.: Learning structured sparsity in deep neural networks. CoRR abs\/1608.03665 (2016). \n                      arXiv:1608.03665"},{"key":"6_CR29","doi-asserted-by":"publisher","unstructured":"Xie, X., Liang, Y., Li, X., Tan, W.: CuLDA: solving large-scale LDA Problems on GPUs. In: HPDC 2019, pp. 195\u2013205. ACM, New York (2019). \n                      https:\/\/doi.org\/10.1145\/3307681.3325407","DOI":"10.1145\/3307681.3325407"},{"key":"6_CR30","doi-asserted-by":"publisher","unstructured":"Xie, X., et al.: Enabling coordinated register allocation and thread-level parallelism optimization for GPUs. In: MICRO 2015, pp. 395\u2013406 (2015a). \n                      https:\/\/doi.org\/10.1145\/2830772.2830813","DOI":"10.1145\/2830772.2830813"},{"key":"6_CR31","doi-asserted-by":"publisher","unstructured":"Xie, X., Liang, Y., Wang, Y., Sun, G., Wang, T.: Coordinated static and dynamic cache bypassing for GPUs. In: HPCA 2015, pp. 76\u201388 (2015b). \n                      https:\/\/doi.org\/10.1109\/HPCA.2015.7056023","DOI":"10.1109\/HPCA.2015.7056023"},{"key":"6_CR32","doi-asserted-by":"publisher","unstructured":"Xie, X., Tan, W., Fong, L.L., Liang, Y.: CuMF\n                      \n                        \n                      \n                      $$\\_$$\n                    SGD: parallelized stochastic gradient descent for matrix factorization on GPUs. In: HPDC 2017, pp. 79\u201392. ACM, New York (2017). \n                      https:\/\/doi.org\/10.1145\/3078597.3078602","DOI":"10.1145\/3078597.3078602"},{"key":"6_CR33","doi-asserted-by":"publisher","unstructured":"Zhang, S., et al.: Cambricon-X: an accelerator for sparse neural networks. In: MICRO 2016, pp. 1\u201312 (2016). \n                      https:\/\/doi.org\/10.1109\/MICRO.2016.7783723","DOI":"10.1109\/MICRO.2016.7783723"}],"container-title":["Lecture Notes in Computer Science","Advanced Parallel Processing Technologies"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-29611-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T19:04:40Z","timestamp":1565636680000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-29611-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030296100","9783030296117"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-29611-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APPT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Advanced Parallel Processing Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"appt2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tc.ccf.org.cn\/tcarch\/appt2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}