{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T11:32:44Z","timestamp":1763724764323,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T00:00:00Z","timestamp":1719100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"European High-Performance Computing Joint Undertaking","award":["101034126"],"award-info":[{"award-number":["101034126"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3649329.3658494","type":"proceedings-article","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:27:22Z","timestamp":1731007642000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["SARIS: Accelerating Stencil Computations on Energy-Efficient RISC-V Compute Clusters with Indirect Stream Registers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4230-1381","authenticated-orcid":false,"given":"Paul","family":"Scheffler","sequence":"first","affiliation":[{"name":"Integrated Systems Laboratory, ETH Zurich, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7986-1975","authenticated-orcid":false,"given":"Luca","family":"Colagrande","sequence":"additional","affiliation":[{"name":"Integrated Systems Laboratory, ETH Zurich, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8068-3806","authenticated-orcid":false,"given":"Luca","family":"Benini","sequence":"additional","affiliation":[{"name":"Integrated Systems Laboratory, ETH Zurich, Zurich, Switzerland"},{"name":"University of Bologna, Bologna, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3329930"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240850"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3252002"},{"key":"e_1_3_2_1_4_1","volume-title":"Unlimited Vector Extension with Data Streaming Support. In 2021 ACM\/IEEE 48th Annu. Int. Symp. Comput. Architecture (ISCA). IEEE","author":"Domingos Joao Mario","year":"2021","unstructured":"Joao Mario Domingos, Nuno Neves, Nuno Roma, and Pedro Tom\u00e1s. 2021. Unlimited Vector Extension with Data Streaming Support. In 2021 ACM\/IEEE 48th Annu. Int. Symp. Comput. Architecture (ISCA). IEEE, New York, NY, USA, 209--222."},{"key":"e_1_3_2_1_5_1","volume-title":"Scalable Distributed High-Order Stencil Computations. In SC '22: Proc. Int. Conf. High Perform. Comput., Netw., Storage Analysis. IEEE Press","author":"Jacquelin Mathias","year":"2022","unstructured":"Mathias Jacquelin, Mauricio Araya-Polo, and Jie Meng. 2022. Scalable Distributed High-Order Stencil Computations. In SC '22: Proc. Int. Conf. High Perform. Comput., Netw., Storage Analysis. IEEE Press, New York, NY, USA, Article 30, 13 pages."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368826.3377904"},{"key":"e_1_3_2_1_7_1","unstructured":"Louis-No\u00ebl Pouchet. 2015. Polybench\/C: The polyhedral benchmark suite. https:\/\/web.cse.ohio-state.edu\/~pouchet.2\/software\/polybench\/"},{"volume-title":"Process. Symp. (IPDPS). IEEE","author":"Rawat Prashant Singh","key":"e_1_3_2_1_8_1","unstructured":"Prashant Singh Rawat, Miheer Vaidya, Aravind Sukumaran-Rajam, Atanas Rountev, Louis-No\u00ebl Pouchet, and P. Sadayappan. 2019. On Optimizing Complex Stencils on GPUs. In 2019 IEEE Int. Parallel Distrib. Process. Symp. (IPDPS). IEEE, New York, NY, USA, 641--652."},{"key":"e_1_3_2_1_9_1","volume-title":"SC20: Int. Conf. High Perf. Comput., Netw., Storage Analysis. IEEE Press","author":"Rocki Kamil","year":"2020","unstructured":"Kamil Rocki, Dirk T. Van Essendelft, Ilya Sharapov, Robert S. Schreiber, Michael Morrison, Vladimir Kibardin, Andrey Portnoy, Jean Fran\u00e7ois Dietiker, Madhava Syamlal, and Michael James. 2020. Fast Stencil-Code Computation on a Wafer-Scale Processor. In SC20: Int. Conf. High Perf. Comput., Netw., Storage Analysis. IEEE Press, New York, NY, USA, Article 58, 14 pages."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3322029"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2987314"},{"key":"e_1_3_2_1_12_1","volume-title":"NERO: A Near High-Bandwidth Memory Stencil Accelerator for Weather Prediction Modeling. In 2020 30th Int. Conf. Field-Programmable Logic Appl. (FPL). IEEE","author":"Singh Gagandeep","year":"2020","unstructured":"Gagandeep Singh, Dionysios Diamantopoulos, Christoph Hagleitner, Juan G\u00f3mez-Luna, Sander Stuijk, Onur Mutlu, and Henk Corporaal. 2020. NERO: A Near High-Bandwidth Memory Stencil Accelerator for Weather Prediction Modeling. In 2020 30th Int. Conf. Field-Programmable Logic Appl. (FPL). IEEE, New York, NY, USA, 9--17."},{"key":"e_1_3_2_1_13_1","volume-title":"Stream-based Memory Access Specialization for General Purpose Processors. In 2019 ACM\/IEEE 46th Annu. Int. Symp. Comput. Architecture (ISCA). IEEE","author":"Wang Zhengrong","year":"2019","unstructured":"Zhengrong Wang and Tony Nowatzki. 2019. Stream-based Memory Access Specialization for General Purpose Processors. In 2019 ACM\/IEEE 46th Annu. Int. Symp. Comput. Architecture (ISCA). IEEE, New York, NY, USA, 736--749."},{"volume-title":"Conf. High Perform. Comput. Commun.","author":"You Xin","key":"e_1_3_2_1_14_1","unstructured":"Xin You, Hailong Yang, Zhonghui Jiang, Zhongzhi Luan, and Depei Qian. 2021. DRStencil: Exploiting Data Reuse within Low-order Stencil on GPU. In 2021 IEEE 23rd Int. Conf. High Perform. Comput. Commun.; 7th Int. Conf. Data Science Syst.; 19th Int. Conf. Smart City; 7th Int. Conf. Dependability in Sensor, Cloud Big Data Syst. Appl. (HPCC\/DSS\/SmartCity\/DependSys). IEEE, New York, NY, USA, 63--70."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC-CSS-ICESS.2015.27"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.3045564"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.3027900"},{"volume-title":"Conf. High Perform. Comput. and Commun.","author":"Zhang Kaifang","key":"e_1_3_2_1_18_1","unstructured":"Kaifang Zhang, Huayou Su, Peng Zhang, and Yong Dou. 2020. Data Layout Transformation for Stencil Computations Using ARM NEON Extension. In 2020 IEEE 22nd Int. Conf. High Perform. Comput. and Commun.; IEEE 18th Int. Conf. Smart City; IEEE 6th Int. Conf. Data Science Syst. (HPCC\/SmartCity\/DSS). IEEE, New York, NY, USA, 180--188."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593716"},{"key":"e_1_3_2_1_20_1","volume-title":"Delivering Performance-Portable Stencil Computations on CPUs and GPUs Using Bricks. In 2018 IEEE\/ACM Int. Workshop on Perform., Portability Productivity HPC (P3HPC). IEEE","author":"Zhao Tuowen","year":"2018","unstructured":"Tuowen Zhao, Samuel Williams, Mary W. Hall, and Hans Johansen. 2018. Delivering Performance-Portable Stencil Computations on CPUs and GPUs Using Bricks. In 2018 IEEE\/ACM Int. Workshop on Perform., Portability Productivity HPC (P3HPC). IEEE, New York, NY, USA, 59--70."}],"event":{"name":"DAC '24: 61st ACM\/IEEE Design Automation Conference","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE-CEDA","SIGBED ACM Special Interest Group on Embedded Systems"],"location":"San Francisco CA USA","acronym":"DAC '24"},"container-title":["Proceedings of the 61st ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3658494","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649329.3658494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:01Z","timestamp":1750295881000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3658494"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":20,"alternative-id":["10.1145\/3649329.3658494","10.1145\/3649329"],"URL":"https:\/\/doi.org\/10.1145\/3649329.3658494","relation":{},"subject":[],"published":{"date-parts":[[2024,6,23]]},"assertion":[{"value":"2024-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}