{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:01:30Z","timestamp":1780639290778,"version":"3.54.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,20]]},"DOI":"10.23919\/date69613.2026.11539401","type":"proceedings-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:53:10Z","timestamp":1780602790000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["KirbyMM: Outer-Product Based Matrix Multiplication on ARMv9 Processor"],"prefix":"10.23919","author":[{"given":"Lanshu","family":"Huang","sequence":"first","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Huang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiguang","family":"Chen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutong","family":"Lu","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.42"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656634"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s12182-019-00399-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00069"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref6","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00032"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref9","article-title":"Flashdecoding++: Faster large language model inference on gpus","author":"Hong","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2015.29"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00071"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00090"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330355"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2012.97"},{"key":"ref15","article-title":"Apple introduces m4 pro and m4 max","year":"2024"},{"key":"ref16","article-title":"Nvidia gb200 nvl72: Hpc & ai gpu for data centers","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546786"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476217"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/sc41406.2024.00027"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545032"},{"key":"ref21","article-title":"Introducing-neon","author":"Developer"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/mm.2017.35"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS56514.2022.00018"},{"key":"ref24","article-title":"Hpc kit download","year":"2024"},{"key":"ref25","article-title":"Accelerate","year":"2025"},{"key":"ref26","article-title":"Streaming sve mode and za storage","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2925987"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404407"},{"key":"ref31","volume-title":"SME and SME2 - SME Overview","author":"Limited","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.83"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1109\/SCW63240.2024.00185","article-title":"Hello sme! generating fast matrix multiplication kernels using the scalable matrix extension","author":"Remke","year":"2024"},{"key":"ref34","article-title":"kvcache-ai\/ktransformers: A flexible framework for experiencing cutting-edge llm inference optimizations","volume-title":"GitHub repository, 2025","year":"2025"},{"key":"ref35","volume-title":"Intel\u00ae Advanced Vector Extensions 512 (Intel\u00ae AVX-512) Overview","year":"2023"},{"key":"ref36","volume-title":"Advanced matrix extensions overview","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759769"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"}],"event":{"name":"2026 Design, Automation &amp; Test in Europe Conference (DATE)","location":"Verona, Italy","start":{"date-parts":[[2026,4,20]]},"end":{"date-parts":[[2026,4,22]]}},"container-title":["2026 Design, Automation &amp;amp; Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11539023\/11539024\/11539401.pdf?arnumber=11539401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:12:03Z","timestamp":1780636323000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11539401\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":38,"URL":"https:\/\/doi.org\/10.23919\/date69613.2026.11539401","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]}}}