{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:44:35Z","timestamp":1772725475828,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":9,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819510207","type":"print"},{"value":"9789819510214","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T00:00:00Z","timestamp":1762214400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T00:00:00Z","timestamp":1762214400000},"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\/978-981-95-1021-4_29","type":"book-chapter","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T10:29:30Z","timestamp":1762165770000},"page":"386-391","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Spatial-Aware Orchestration of\u00a0LLM Attention on\u00a0Waferscale Chips"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3501-3148","authenticated-orcid":false,"given":"Taiquan","family":"Wei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9763-8208","authenticated-orcid":false,"given":"Huizheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7114-0647","authenticated-orcid":false,"given":"Zichuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8438-8588","authenticated-orcid":false,"given":"Shouyi","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6942-4395","authenticated-orcid":false,"given":"Yang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,4]]},"reference":[{"key":"29_CR1","unstructured":"Brown, B., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Bajwa, A.A., et al.: Demonstration of a Heterogeneously Integrated System-on-Wafer (SoW) Assembly. In: 2018 IEEE 68th Electronic Components and Technology Conference (ECTC), pp. 1926\u20131930. IEEE (2018)","DOI":"10.1109\/ECTC.2018.00288"},{"key":"29_CR3","unstructured":"Brandon, W., Nrusimha, A., Qian, K., Ankner, Z., Jin, T., Song, Z., Ragan-Kelley, J.: Striped attention: faster ring attention for causal transformers. arXiv preprint arXiv:2311.09431 (2023)"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Lie, S.: Cerebras architecture deep dive: first look inside the HW\/SW co-design for deep learning: cerebras systems. In: 2022 IEEE Hot Chips 34 Symposium (HCS), pp. 1\u201334. IEEE Computer Society (2022)","DOI":"10.1109\/HCS55958.2022.9895479"},{"key":"29_CR5","unstructured":"Liu, H., Zaharia, M., Abbeel, P.: Ring attention with blockwise transformers for near-infinite context. arXiv preprint arXiv:2310.01889 (2023)"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Narayanan, D., et\u00a0al.: Efficient large-scale language model training on gpu clusters using megatron-LM. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201315 (2021)","DOI":"10.1145\/3458817.3476209"},{"key":"29_CR7","unstructured":"Nvidia: Nvidia gb200 nvl72: Powering the new era of computing (2024). https:\/\/www.nvidia.com\/en- us\/data- center\/gb200- nvl72\/"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Talpes, E., Williams, D., Sarma, D.D.: Dojo: the microarchitecture of tesla\u2019s exa-scale computer. In: 2022 IEEE Hot Chips 34 Symposium (HCS), pp. 1\u201328. IEEE Computer Society (2022)","DOI":"10.1109\/HCS55958.2022.9895534"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Won, W., Heo, T., Rashidi, S., Sridharan, S., Srinivasan, S., Krishna, T.: Astra-sim2. 0: modeling hierarchical networks and disaggregated systems for large-model training at scale. In: 2023 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 283\u2013294. IEEE (2023)","DOI":"10.1109\/ISPASS57527.2023.00035"}],"container-title":["Lecture Notes in Computer Science","Advanced Parallel Processing Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-1021-4_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T10:29:35Z","timestamp":1762165775000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-1021-4_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,4]]},"ISBN":["9789819510207","9789819510214"],"references-count":9,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-1021-4_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,4]]},"assertion":[{"value":"4 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declarethat are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"13 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"appt2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.appt-conference.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}