{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T23:14:07Z","timestamp":1780528447227,"version":"3.54.1"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2016YFB1000403"],"award-info":[{"award-number":["2016YFB1000403"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1016\/j.ins.2020.12.079","type":"journal-article","created":{"date-parts":[[2021,2,9]],"date-time":"2021-02-09T12:51:55Z","timestamp":1612875115000},"page":"831-847","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":9,"special_numbering":"C","title":["swFLOW: A large-scale distributed framework for deep learning on Sunway TaihuLight supercomputer"],"prefix":"10.1016","volume":"570","author":[{"given":"Mingfan","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junshi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jose Monsalve","family":"Diaz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongfen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guang R.","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2020.12.079_b0005","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al., 2016. Tensorflow: a system for large-scale machine learning., in: OSDI, pp. 265\u2013283."},{"key":"10.1016\/j.ins.2020.12.079_b0010","unstructured":"Akiba, T., Fukuda, K., Suzuki, S., 2017. Chainermn: scalable distributed deep learning framework. arXiv preprint arXiv:1710.11351."},{"key":"10.1016\/j.ins.2020.12.079_b0015","doi-asserted-by":"crossref","first-page":"24680","DOI":"10.1109\/ACCESS.2018.2831280","article-title":"Classification of breast cancer based on histology images using convolutional neural networks","volume":"6","author":"Bardou","year":"2018","journal-title":"IEEE Access"},{"key":"10.1016\/j.ins.2020.12.079_b0020","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1137\/16M1080173","article-title":"Optimization methods for large-scale machine learning","volume":"60","author":"Bottou","year":"2018","journal-title":"SIAM Rev."},{"key":"10.1016\/j.ins.2020.12.079_b0025","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1109\/TPDS.2018.2877359","article-title":"A bi-layered parallel training architecture for large-scale convolutional neural networks","volume":"30","author":"Chen","year":"2019","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"10.1016\/j.ins.2020.12.079_b0030","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H., 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation. arXiv preprint arXiv:1802.02611.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"10.1016\/j.ins.2020.12.079_b0035","unstructured":"Chen, T., Li, M., Li, Y., Lin, M., Wang, N., Wang, M., Xiao, T., Xu, B., Zhang, C., Zhang, Z., 2015. Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274."},{"key":"10.1016\/j.ins.2020.12.079_b0040","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1109\/TPDS.2018.2871189","article-title":"Performance-aware model for sparse matrix-matrix multiplication on the sunway taihulight supercomputer","volume":"30","author":"Chen","year":"2019","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"10.1016\/j.ins.2020.12.079_b0045","unstructured":"Chetlur, S., Woolley, C., Vandermersch, P., Cohen, J., Tran, J., Catanzaro, B., Shelhamer, E., 2014. cudnn: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759."},{"key":"10.1016\/j.ins.2020.12.079_b0050","first-page":"1223","article-title":"Large scale distributed deep networks","author":"Dean","year":"2012","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"10.1016\/j.ins.2020.12.079_b0055","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L., 2009. ImageNet: A Large-Scale Hierarchical Image Database, in: CVPR09.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10.1016\/j.ins.2020.12.079_b0060","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1109\/TNNLS.2017.2654357","article-title":"A parallel multiclassification algorithm for big data using an extreme learning machine","volume":"29","author":"Duan","year":"2018","journal-title":"IEEE Trans. Neural Networks Learning Systems"},{"key":"10.1016\/j.ins.2020.12.079_b0065","series-title":"Parallel and Distributed Processing Symposium (IPDPS), 2017 IEEE International","first-page":"615","article-title":"swdnn: A library for accelerating deep learning applications on sunway taihulight, in","author":"Fang","year":"2017"},{"key":"10.1016\/j.ins.2020.12.079_b0070","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-016-5588-7","article-title":"The sunway taihulight supercomputer: system and applications","volume":"59","author":"Fu","year":"2016","journal-title":"Science China Information Sciences"},{"key":"10.1016\/j.ins.2020.12.079_b0075","unstructured":"Goyal, P., Doll\u00e1r, P., Girshick, R.B., Noordhuis, P., Wesolowski, L., Kyrola, A., Tulloch, A., Jia, Y., He, K., 2017. Accurate, large minibatch SGD: training imagenet in 1 hour. CoRR abs\/1706.02677. arXiv:1706.02677."},{"key":"10.1016\/j.ins.2020.12.079_b0080","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition, in","author":"He","year":"2016"},{"key":"10.1016\/j.ins.2020.12.079_b0085","doi-asserted-by":"crossref","unstructured":"Hou, L., Samaras, D., Kur\u00e7, T.M., Gao, Y., Davis, J.E., Saltz, J.H., 2015. Efficient multiple instance convolutional neural networks for gigapixel resolution image classification. CoRR abs\/1504.07947. arXiv:1504.07947.","DOI":"10.1109\/CVPR.2016.266"},{"key":"10.1016\/j.ins.2020.12.079_b0090","series-title":"Computer Vision and Pattern Recognition Workshops (CVPRW), 2017 IEEE Conference on","first-page":"1175","article-title":"The one hundred layers tiramisu: Fully convolutional densenets for semantic segmentation","author":"J\u00e9gou","year":"2017"},{"key":"10.1016\/j.ins.2020.12.079_b0095","doi-asserted-by":"crossref","unstructured":"Jia, W., Wang, H., Chen, M., Lu, D., Liu, J., Lin, L., Car, R., Zhang, L., et al., 2020. Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning. arXiv preprint arXiv:2005.00223.","DOI":"10.1109\/SC41405.2020.00009"},{"key":"10.1016\/j.ins.2020.12.079_b0100","series-title":"Proceedings of the 22nd ACM international conference on Multimedia","first-page":"675","article-title":"Caffe: Convolutional architecture for fast feature embedding, in","author":"Jia","year":"2014"},{"key":"10.1016\/j.ins.2020.12.079_b0105","unstructured":"Jouppi, N.P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., Borchers, A., et al., 2017. In-datacenter performance analysis of a tensor processing unit, in: Computer Architecture (ISCA), 2017 ACM\/IEEE 44th Annual International Symposium on, IEEE. pp. 1\u201312."},{"key":"10.1016\/j.ins.2020.12.079_b0110","unstructured":"Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., Tang, P.T.P., 2016. On large-batch training for deep learning: Generalization gap and sharp minima. CoRR abs\/1609.04836. arXiv:1609.04836."},{"key":"10.1016\/j.ins.2020.12.079_b0115","unstructured":"Krizhevsky, A., 2014. One weird trick for parallelizing convolutional neural networks. CoRR abs\/1404.5997. arXiv:1404.5997."},{"key":"10.1016\/j.ins.2020.12.079_b0120","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012","journal-title":"Adva. Neural Inform. Process. Syst."},{"key":"10.1016\/j.ins.2020.12.079_b0125","series-title":"Proceedings of the International Conference for High Performance Computing and Analysis","first-page":"51","article-title":"Exascale deep learning for climate analytics","author":"Kurth","year":"2018"},{"key":"10.1016\/j.ins.2020.12.079_b0130","series-title":"IEEE International Conference on Cluster Computing (CLUSTER)","first-page":"413","article-title":"swCaffe: A Parallel Framework for Accelerating Deep Learning Applications on Sunway TaihuLight","author":"Li","year":"2018"},{"key":"10.1016\/j.ins.2020.12.079_b0135","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T., 2014. Fully convolutional networks for semantic segmentation. CoRR abs\/1411.4038. arXiv:1411.4038.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"10.1016\/j.ins.2020.12.079_b0140","doi-asserted-by":"crossref","unstructured":"Markidis, S., Der Chien, S.W., Laure, E., Peng, I.B., Vetter, J.S., 2018. Nvidia tensor core programmability, performance & precision. arXiv preprint arXiv:1803.04014 https:\/\/arxiv.org\/abs\/1803.04014.","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"10.1016\/j.ins.2020.12.079_b0145","series-title":"SC18: International Conference for High Performance Computing, Networking, Storage and Analysis","first-page":"819","article-title":"Cosmoflow: Using deep learning to learn the universe at scale","author":"Mathuriya","year":"2018"},{"key":"10.1016\/j.ins.2020.12.079_b0150","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/BF02478259","article-title":"A logical calculus of the ideas immanent in nervous activity","volume":"5","author":"McCulloch","year":"1943","journal-title":"Bull. Math. Biophys."},{"key":"10.1016\/j.ins.2020.12.079_b0155","doi-asserted-by":"crossref","unstructured":"Mei, X., Lee, H.C., Diao, K.y., Huang, M., Lin, B., Liu, C., Xie, Z., Ma, Y., Robson, P.M., Chung, M., et al., 2020. Artificial intelligence\u2013enabled rapid diagnosis of patients with covid-19. Nature Medicine, 1\u20135.","DOI":"10.1038\/s41591-020-0931-3"},{"key":"10.1016\/j.ins.2020.12.079_b0160","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., Chintala, S., 2019. Pytorch: An imperative style, high-performance deep learning library, in: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., Garnett, R. (Eds.), Advances in Neural Information Processing Systems, Curran Associates, Inc. pp. 8026\u20138037. https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf."},{"key":"10.1016\/j.ins.2020.12.079_b0165","series-title":"Proceedings of the International Conference for High Performance Computing and Analysis","first-page":"50","article-title":"167-pflops deep learning for electron microscopy: from learning physics to atomic manipulation","author":"Patton","year":"2018"},{"key":"10.1016\/j.ins.2020.12.079_b0170","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T., 2015. U-net: Convolutional networks for biomedical image segmentation. CoRR arXiv:1505.04597.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"10.1016\/j.ins.2020.12.079_b0175","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1037\/h0042519","article-title":"The perceptron: a probabilistic model for information storage and organization in the brain","volume":"65","author":"Rosenblatt","year":"1958","journal-title":"Psychol. Rev."},{"key":"10.1016\/j.ins.2020.12.079_b0180","unstructured":"Simonyan, K., Zisserman, A., 2015. Very deep convolutional networks for large-scale image recognition, in: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings."},{"key":"10.1016\/j.ins.2020.12.079_b0185","unstructured":"Sun, Y., Liang, D., Wang, X., Tang, X., 2015. DeepID3: Face recognition with very deep neural networks. arXiv preprint arXiv:1502.00873."},{"key":"10.1016\/j.ins.2020.12.079_b0190","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A., 2017. Inception-v4, inception-resnet and the impact of residual connections on learning, in: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, AAAI Press. p. 4278\u20134284.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"10.1016\/j.ins.2020.12.079_b0195","unstructured":"Wang, D., Khosla, A., Gargeya, R., Irshad, H., Beck, A.H., 2016. Deep learning for identifying metastatic breast cancer. arXiv:1606.05718."},{"key":"10.1016\/j.ins.2020.12.079_b0200","first-page":"1","article-title":"Caspmv: A customized and accelerative spmv framework for the sunway taihulight","author":"Xiao","year":"2019","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"10.1016\/j.ins.2020.12.079_b0205","unstructured":"You, Y., Gitman, I., Ginsburg, B., 2017a. Large batch training of convolutional networks. arXiv preprint arXiv:1708.03888."},{"key":"10.1016\/j.ins.2020.12.079_b0210","unstructured":"You, Y., Gitman, I., Ginsburg, B., 2017b. Scaling SGD batch size to 32k for imagenet training. CoRR abs\/1708.03888. arXiv:1708.03888."},{"key":"10.1016\/j.ins.2020.12.079_b0215","series-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","first-page":"1","article-title":"Large-batch training for lstm and beyond","author":"You","year":"2019"},{"key":"10.1016\/j.ins.2020.12.079_b0220","doi-asserted-by":"crossref","DOI":"10.1016\/j.cell.2020.08.029","article-title":"Clinically applicable ai system for accurate diagnosis, quantitative measurements, and prognosis of covid-19 pneumonia using computed tomography","author":"Zhang","year":"2020","journal-title":"Cell"},{"key":"10.1016\/j.ins.2020.12.079_b0225","first-page":"685","article-title":"Deep learning with elastic averaging sgd","author":"Zhang","year":"2015","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"10.1016\/j.ins.2020.12.079_b0230","series-title":"IFIP International Conference on Network and Parallel Computing","first-page":"39","article-title":"On retargeting the ai programming framework to new hardwares","author":"Zhao","year":"2018"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025520312457?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025520312457?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T05:24:31Z","timestamp":1758086671000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025520312457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9]]},"references-count":46,"alternative-id":["S0020025520312457"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2020.12.079","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2021,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"swFLOW: A large-scale distributed framework for deep learning on Sunway TaihuLight supercomputer","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2020.12.079","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}]}}