{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T10:51:30Z","timestamp":1775559090764,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819583980","type":"print"},{"value":"9789819583997","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-8399-7_24","type":"book-chapter","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T09:56:27Z","timestamp":1775555787000},"page":"438-457","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Mapping Strategy Optimization Framework for\u00a0Systolic Array Accelerators"],"prefix":"10.1007","author":[{"given":"Xin","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hengshan","family":"Yue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haixiao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"issue":"6","key":"24_CR1","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","journal-title":"Commun. ACM"},{"key":"24_CR2","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"24_CR3","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Alwani, M., Chen, H., Ferdman, M., Milder, P.: Fused-layer CNN accelerators. In: 2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), pp. 1\u201312. IEEE (2016)","DOI":"10.1109\/MICRO.2016.7783725"},{"issue":"2","key":"24_CR6","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1145\/3140659.3080254","volume":"45","author":"A Parashar","year":"2017","unstructured":"Parashar, A., Rhu, M., Mukkara, A., Puglielli, A., Venkatesan, R., Khailany, B., et al.: SCNN: an accelerator for compressed-sparse convolutional neural networks. ACM SIGARCH Comput. Archit. News 45(2), 27\u201340 (2017)","journal-title":"ACM SIGARCH Comput. Archit. News"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., Cong, J.: Optimizing FPGA-based accelerator design for deep convolutional neural networks. In: Proceedings of the 2015 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 161\u2013170 (2015)","DOI":"10.1145\/2684746.2689060"},{"key":"24_CR8","unstructured":"Jouppi, N.P., et al.: In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th Annual International Symposium on Computer Architecture, pp. 1\u201312 (2017)"},{"issue":"2","key":"24_CR9","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1109\/MM.2020.2975764","volume":"40","author":"E Talpes","year":"2020","unstructured":"Talpes, E., et al.: Compute solution for tesla\u2019s full self-driving computer. IEEE Micro 40(2), 25\u201335 (2020)","journal-title":"IEEE Micro"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Parashar, A., et al.: Timeloop: a systematic approach to DNN accelerator evaluation. In: Proceedings of ISPASS, pp. 304\u2013315 (2019)","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Sun, H., et al.: FAMS: a framework of memory-centric mapping for DNNs on systolic array accelerators. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 1\u201314 (2025)","DOI":"10.1109\/TVLSI.2024.3522326"},{"issue":"3","key":"24_CR12","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MM.2020.2985963","volume":"40","author":"H Kwon","year":"2020","unstructured":"Kwon, H., Chatarasi, P., Sarkar, V., Krishna, T., Pellauer, M., Parashar, A.: MAESTRO: a data-centric approach to understand reuse, performance, and hardware cost of DNN mappings. IEEE Micro 40(3), 20\u201329 (2020)","journal-title":"IEEE Micro"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Kwon, H., Chatarasi, P., Pellauer, M., Parashar, A., Sarkar, V., Krishna, T.: Understanding reuse, performance, and hardware cost of DNN dataflow: a data-centric approach. In: Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 754\u2013768 (2019)","DOI":"10.1145\/3352460.3358252"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Lu, L., et al.: TENET: a framework for modeling tensor dataflow based on relation-centric notation. In: 2021 ACM\/IEEE 48th Annual International Symposium on Computer Architecture (ISCA), pp. 720\u2013733 (2021)","DOI":"10.1109\/ISCA52012.2021.00062"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Yang, X., et al.: Interstellar: using halide\u2019s scheduling language to analyze DNN accelerators. In: Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 369\u2013383 (2020)","DOI":"10.1145\/3373376.3378514"},{"issue":"1","key":"24_CR16","first-page":"1","volume":"56","author":"R Xu","year":"2023","unstructured":"Xu, R., Ma, S., Guo, Y., Li, D.: A survey of design and optimization for systolic array-based DNN accelerators. ACM Comput. Surv. 56(1), 1\u201337 (2023)","journal-title":"ACM Comput. Surv."},{"issue":"3","key":"24_CR17","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1109\/MM.2017.54","volume":"37","author":"YH Chen","year":"2017","unstructured":"Chen, Y.H., Emer, J., Sze, V.: Using dataflow to optimize energy efficiency of deep neural network accelerators. IEEE Micro 37(3), 12\u201321 (2017)","journal-title":"IEEE Micro"},{"issue":"3","key":"24_CR18","doi-asserted-by":"publisher","first-page":"511","DOI":"10.3390\/electronics14030511","volume":"14","author":"H Sun","year":"2025","unstructured":"Sun, H., Shen, J., Zhang, C., Liu, H.: A coarse-and fine-grained co-exploration approach for optimizing DNN spatial accelerators: improving speed and performance. Electronics 14(3), 511 (2025)","journal-title":"Electronics"},{"issue":"1","key":"24_CR19","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1109\/JSSC.2016.2616357","volume":"52","author":"YH Chen","year":"2016","unstructured":"Chen, Y.H., Krishna, T., Emer, J.S., Sze, V.: Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE J. Solid-State Circuits 52(1), 127\u2013138 (2016)","journal-title":"IEEE J. Solid-State Circuits"},{"key":"24_CR20","unstructured":"Samajdar, A., Zhu, Y., Whatmough, P., Mattina, M., Krishna, T.: SCALE-Sim: Systolic CNN Accelerator Simulator (2019)"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Samajdar, A., Joseph, J.M., Zhu, Y., Whatmough, P., Mattina, M., Krishna, T.: A systematic methodology for characterizing scalability of DNN accelerators using scale-sim. In: 2020 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 58\u201368. IEEE (2020)","DOI":"10.1109\/ISPASS48437.2020.00016"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8399-7_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T09:56:32Z","timestamp":1775555792000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8399-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819583980","9789819583997"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8399-7_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"8 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}