{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T18:42:47Z","timestamp":1743100967314,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819615506"},{"type":"electronic","value":"9789819615513"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-1551-3_21","type":"book-chapter","created":{"date-parts":[[2025,2,16]],"date-time":"2025-02-16T09:08:24Z","timestamp":1739696904000},"page":"315-334","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FusionFrame: A Fusion Dataflow Scheduling Framework for\u00a0DNN Accelerators via\u00a0Analytical Modeling"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0376-6058","authenticated-orcid":false,"given":"Liutao","family":"Zheng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3120-5773","authenticated-orcid":false,"given":"Huiying","family":"Lan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8550-3767","authenticated-orcid":false,"given":"Xiang","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8501-9488","authenticated-orcid":false,"given":"Linshan","family":"Jiang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8360-3143","authenticated-orcid":false,"given":"Xuehai","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,17]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Cai, X., Wang, Y., Zhang, L.: Optimus: an operator fusion framework for deep neural networks. ACM Trans. Embed. Comput. Syst. (2022)","key":"21_CR1","DOI":"10.1145\/3520142"},{"doi-asserted-by":"crossref","unstructured":"Chen, Y., Chen, T., Xu, Z., Sun, N., Temam, O.: Diannao family: energy-efficient hardware accelerators for machine learning. Commun. ACM (2016)","key":"21_CR2","DOI":"10.1145\/2996864"},{"doi-asserted-by":"publisher","unstructured":"Chen, Y., et al.: An instruction set architecture for machine learning. ACM Trans. Comput. Syst. 36(3) (2019). https:\/\/doi.org\/10.1145\/3331469","key":"21_CR3","DOI":"10.1145\/3331469"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","key":"21_CR4","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"Hegde, K., Tsai, P.A., Huang, S., Chandra, V., Parashar, A., Fletcher, C.W.: Mind mappings: enabling efficient algorithm-accelerator mapping space search. In: Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 943\u2013958 (2021)","key":"21_CR5","DOI":"10.1145\/3445814.3446762"},{"unstructured":"Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)","key":"21_CR6"},{"doi-asserted-by":"crossref","unstructured":"Jeong, G., et al.: Union: a unified hw-sw co-design ecosystem in mlir for evaluating tensor operations on spatial accelerators. In: 2021 30th International Conference on Parallel Architectures and Compilation Techniques (PACT) (2021)","key":"21_CR7","DOI":"10.1109\/PACT52795.2021.00010"},{"unstructured":"Jouppi, N.P., et\u00a0al.: In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th Annual International Symposium on Computer Architecture, pp. 1\u201312 (2017)","key":"21_CR8"},{"unstructured":"Kao, S.C., Huang, X., Krishna, T.: Dnnfuser: generative pre-trained transformer as a generalized mapper for layer fusion in dnn accelerators. arXiv preprint arXiv:2201.11218 (2022)","key":"21_CR9"},{"doi-asserted-by":"crossref","unstructured":"Kao, S.C., Jeong, G., Krishna, T.: Confuciux: autonomous hardware resource assignment for dnn accelerators using reinforcement learning. In: 2020 53rd Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO) (2020)","key":"21_CR10","DOI":"10.1109\/MICRO50266.2020.00058"},{"doi-asserted-by":"crossref","unstructured":"Kao, S.C., Krishna, T.: Magma: an optimization framework for mapping multiple dnns on multiple accelerator cores. In: 2022 IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 814\u2013830. IEEE (2022)","key":"21_CR11","DOI":"10.1109\/HPCA53966.2022.00065"},{"doi-asserted-by":"crossref","unstructured":"Karl, S., Symons, A., Fasfous, N., Verhelst, M.: Genetic algorithm-based framework for layer-fused scheduling of multiple dnns on multi-core systems. In: 2023 Design, Automation & Test in Europe Conference & Exhibition (DATE) (2023)","key":"21_CR12","DOI":"10.23919\/DATE56975.2023.10137070"},{"issue":"3","key":"21_CR13","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"},{"doi-asserted-by":"crossref","unstructured":"Mei, L., Goetschalckx, K., Symons, A., Verhelst, M.: Defines: enabling fast exploration of the depth-first scheduling space for dnn accelerators through analytical modeling. In: 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 570\u2013583. IEEE (2023)","key":"21_CR14","DOI":"10.1109\/HPCA56546.2023.10071098"},{"issue":"8","key":"21_CR15","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1109\/TC.2021.3059962","volume":"70","author":"L Mei","year":"2021","unstructured":"Mei, L., Houshmand, P., Jain, V., Giraldo, S., Verhelst, M.: Zigzag: enlarging joint architecture-mapping design space exploration for DNN accelerators. IEEE Trans. Comput. 70(8), 1160\u20131174 (2021)","journal-title":"IEEE Trans. Comput."},{"doi-asserted-by":"crossref","unstructured":"Mei, L., Liu, H., Wu, T., Sumbul, H.E., Verhelst, M., Beigne, E.: A uniform latency model for dnn accelerators with diverse architectures and dataflows. In: 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp. 220\u2013225. IEEE (2022)","key":"21_CR16","DOI":"10.23919\/DATE54114.2022.9774728"},{"unstructured":"Moreira, O., Popp, M., Schulz, C.: Graph partitioning with acyclicity constraints. arXiv preprint arXiv:1704.00705 (2017)","key":"21_CR17"},{"doi-asserted-by":"crossref","unstructured":"Parashar, A., et al.: Timeloop: a systematic approach to dnn accelerator evaluation. In: 2019 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 304\u2013315. IEEE (2019)","key":"21_CR18","DOI":"10.1109\/ISPASS.2019.00042"},{"unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)","key":"21_CR19"},{"doi-asserted-by":"publisher","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","key":"21_CR20","DOI":"10.1109\/CVPR.2015.7298594"},{"doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","key":"21_CR21","DOI":"10.1109\/CVPR.2016.308"},{"issue":"2","key":"21_CR22","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"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)","key":"21_CR23"},{"key":"21_CR24","doi-asserted-by":"publisher","first-page":"168245","DOI":"10.1109\/ACCESS.2021.3134930","volume":"9","author":"L Waeijen","year":"2021","unstructured":"Waeijen, L., Sioutas, S., Peemen, M., Lindwer, M., Corporaal, H.: Convfusion: a model for layer fusion in convolutional neural networks. IEEE Access 9, 168245\u2013168267 (2021)","journal-title":"IEEE Access"},{"doi-asserted-by":"crossref","unstructured":"Xing, Y., et al.: Dnnvm: end-to-end compiler leveraging operation fusion on fpga-based cnn accelerators. In: Proceedings of the 2019 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 187\u2013188 (2019)","key":"21_CR25","DOI":"10.1145\/3289602.3293972"},{"doi-asserted-by":"crossref","unstructured":"Yin, J., Mei, L., Guntoro, A., Verhelst, M.: ACCO: automated causal CNN scheduling optimizer for real-time edge accelerators. In: IEEE ICCD (2023)","key":"21_CR26","DOI":"10.1109\/ICCD58817.2023.00065"},{"doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Tileflow: a framework for modeling fusion dataflow via tree-based analysis. In: Proceedings of the 56th Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 1271\u20131288 (2023)","key":"21_CR27","DOI":"10.1145\/3613424.3623792"}],"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\/978-981-96-1551-3_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,16]],"date-time":"2025-02-16T09:09:22Z","timestamp":1739696962000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1551-3_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819615506","9789819615513"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1551-3_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"17 February 2025","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":"Macau","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ica3pp2024.scimeeting.cn\/en\/web\/index\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}