{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:22:38Z","timestamp":1763922158898,"version":"3.45.0"},"publisher-location":"Cham","reference-count":12,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032076113","type":"print"},{"value":"9783032076120","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"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\/978-3-032-07612-0_33","type":"book-chapter","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T17:57:29Z","timestamp":1763920649000},"page":"431-443","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generation of\u00a0Mixed-Precision Kernels for\u00a0Quantized Transformer Encoders with\u00a0Exo"],"prefix":"10.1007","author":[{"given":"Adri\u00e1n","family":"Castell\u00f3","sequence":"first","affiliation":[]},{"given":"H\u00e9ctor","family":"Mart\u00ednez","sequence":"additional","affiliation":[]},{"given":"Francisco D.","family":"Igual","sequence":"additional","affiliation":[]},{"given":"Enrique S.","family":"Quintana-Ort\u00ed","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Castell\u00f3, A., et\u00a0al.: Tackling the matrix multiplication micro-kernel generation with Exo. In: 2024 IEEE\/ACM CGO, pp. 182\u2013193 (2024)","DOI":"10.1109\/CGO57630.2024.10444883"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Castell\u00f3, A., et\u00a0al.: Portable, high performance matrix multiplication micro-kernels for risc-v with exo. In: 2025 33rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP), pp. 25\u201332 (2025)","DOI":"10.1109\/PDP66500.2025.00013"},{"key":"33_CR3","unstructured":"Dettmers, T., et\u00a0al.: LLM.int8(): 8-bit matrix multiplication for transformers at scale. In: 36th NIPS. Curran Associates Inc., Red Hook, NY, USA (2024)"},{"key":"33_CR4","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Goto, K., van\u00a0de Geijn, R.: Anatomy of high-performance matrix multiplication. ACM Trans. Math. Softw. 34(3), 12:1\u201312:25 (2008)","DOI":"10.1145\/1356052.1356053"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Igual, F., et\u00a0al.: Automatic generation of micro-kernels for performance portability of matrix multiplication on RISC-V vector processors. In: Proceedings of the SC \u201923 Workshops, pp. 1523\u20131532 (2023)","DOI":"10.1145\/3624062.3624229"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Ikarashi, Y., et\u00a0al.: Exocompilation for productive programming of hardware accelerators. In: PLDI 2022, pp. 703\u2013718, New York, NY, USA (2022)","DOI":"10.1145\/3519939.3523446"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Low, T.M., et\u00a0al.: Analytical modeling is enough for high-performance BLIS. ACM Trans. Math. Softw. 43(2), 12:1\u201312:18 (2016)","DOI":"10.1145\/2925987"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Mart\u00ednez, H., et\u00a0al.: Inference with transformer encoders on ARM and RISC-V multicore processors. In: Euro-Par 2024: Parallel Processing, pp. 377\u2013392 (2024)","DOI":"10.1007\/978-3-031-69766-1_26"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Smith, T.M., et\u00a0al.: Anatomy of high-performance many-threaded matrix multiplication. In: Proceedings of the IEEE 28th IPDPS, pp. 1049\u20131059 (2014)","DOI":"10.1109\/IPDPS.2014.110"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Van\u00a0Zee, F.G., et\u00a0al.: The BLIS framework: experiments in portability. ACM Trans. Math. Softw. 42(2) (2016)","DOI":"10.1145\/2755561"},{"key":"33_CR12","unstructured":"Vaswani, A., et\u00a0al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol.\u00a030 (2017)"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07612-0_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T17:57:31Z","timestamp":1763920651000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07612-0_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"ISBN":["9783032076113","9783032076120"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07612-0_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"24 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hamburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"40","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}