{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T14:30:27Z","timestamp":1787495427021,"version":"build-2736575974"},"publisher-location":"Singapore","reference-count":10,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819248049","type":"print"},{"value":"9789819248056","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-4805-6_39","type":"book-chapter","created":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:45:57Z","timestamp":1787492757000},"page":"579-585","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["WaferSim: A Simulation Infrastructure for\u00a0LLM Service on\u00a0Wafer-Scale Chips"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5264-2818","authenticated-orcid":false,"given":"Zheng","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9405-8548","authenticated-orcid":false,"given":"Jiaxin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1087-307X","authenticated-orcid":false,"given":"Dehao","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0577-3788","authenticated-orcid":false,"given":"Jiamu","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4702-0635","authenticated-orcid":false,"given":"Xu","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6971-6572","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7933-9941","authenticated-orcid":false,"given":"Jian","family":"Weng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8666-8463","authenticated-orcid":false,"given":"Jinyi","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6942-4395","authenticated-orcid":false,"given":"Yang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8438-8588","authenticated-orcid":false,"given":"Shouyi","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"39_CR1","unstructured":"Azurepublicdataset. https:\/\/github.com\/Azure\/AzurePublicDataset\/tree\/master (2023)"},{"key":"39_CR2","unstructured":"Agrawal, A., et al.: Sarathi: efficient LLM inference by piggybacking decodes with chunked prefills. arXiv preprint arXiv:2308.16369 (2023)"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Cho, J., et al.: Llmservingsim: a HW\/SW co-simulation infrastructure for LLM inference serving at scale. In: Proceedings of the 2024 IEEE International Symposium on Workload Characterization (IISWC) (2024)","DOI":"10.1109\/IISWC63097.2024.00012"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Dijkstra, E.W.: A note on two problems in connexion with graphs. In: Edsger Wybe Dijkstra: his life, work, and legacy, pp. 287\u2013290 (2022)","DOI":"10.1145\/3544585.3544600"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Ghodrati, S., et al.: Tandem processor: grappling with emerging operators in neural networks. In: Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (2024)","DOI":"10.1145\/3620665.3640365"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: Wafer-scale computing: advancements, challenges, and future perspectives. IEEE Circuits Syst. Mag. (2024)","DOI":"10.1109\/MCAS.2024.3349669"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Patel, P., et al.: Splitwise: efficient generative LLM inference using phase splitting. In: Proceedings of the 2024 ACM\/IEEE 51st Annual International Symposium on Computer Architecture (ISCA) (2024)","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"39_CR8","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: WSC-LLM: efficient LLM service and architecture co-exploration for wafer-scale chips. In: Proceedings of the 52nd Annual International Symposium on Computer Architecture (ISCA) (2025)","DOI":"10.1145\/3695053.3731101"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Face: fully overlapped pd scheduling and multi-level architecture co-exploration on wafer. In: Proceedings of the 2026 IEEE International Symposium on High Performance Computer Architecture (HPCA) (2026)","DOI":"10.1109\/HPCA68181.2026.11408518"}],"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\/978-981-92-4805-6_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:45:58Z","timestamp":1787492758000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-4805-6_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"ISBN":["9789819248049","9789819248056"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-4805-6_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"assertion":[{"value":"24 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Brussels","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"appt2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.appt-conference.com\/2026","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}