{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:00:52Z","timestamp":1780639252900,"version":"3.54.1"},"reference-count":36,"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\/date69613.2026.11539481","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":["FlashGEMM: Mesh-Aware Efficient GEMM for 3D-Stacked LLM Accelerators"],"prefix":"10.23919","author":[{"given":"Xin","family":"Fan","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Bai","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Yang","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenhua","family":"Zhu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanhong","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaode","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"DeepSeek-V3 Technical Report","author":"Liu","year":"2024"},{"key":"ref2","article-title":"OpenAI o3 and o4-mini System Card","year":"2025"},{"key":"ref3","article-title":"Kimi K2: Open Agentic Intelligence","author":"Team","year":"2025"},{"key":"ref4","first-page":"148","article-title":"FlashDecoding++: Faster Large Language Model Inference with Asynchronization, Flat GEMM Optimization, and Heuristics","volume":"6","author":"Hong","year":"2024","journal-title":"Machine Learning and Systems (MLSys)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00071"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061394"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3256796"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00068"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3256384"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3258906"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCPMT.2023.3265529"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM19573.2019.8993637"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC.2019.00095"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD66269.2025.11240867"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/iedm13553.2020.9372039"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49657.2024.10454440"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC32696.2021.00028"},{"key":"ref19","article-title":"JEDEC Standard: High Bandwidth Memory (HBM3) DRAM, JEDEC Solid State Technology Association","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/140993478"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731077"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2"},{"key":"ref23","article-title":"WaferLLM: Large Language Model Inference at Wafer Scale","volume-title":"USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"He"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"ref25","article-title":"GLU Variants Improve Transformer","author":"Shazeer","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10993126"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM50854.2024.10873522"},{"key":"ref28","first-page":"606","article-title":"Efficiently Scaling Transformer Inference","volume":"5","author":"Pope","year":"2023","journal-title":"Machine Learning and Systems (MLSys)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-023-2894-6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3397800"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607102"},{"key":"ref32","article-title":"Scale-Sim: Systolic CNN Accelerator Simulator","author":"Samajdar","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2013.6557149"},{"key":"ref34","article-title":"Gemma: Open Models Based on Gemini Research and Technology","author":"Mesnard","year":"2024"},{"key":"ref35","article-title":"Llama: Open and Efficient Foundation Language Models","author":"Touvron","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/DAC63849.2025.11132534"}],"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\/11539481.pdf?arnumber=11539481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:09:24Z","timestamp":1780636164000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11539481\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":36,"URL":"https:\/\/doi.org\/10.23919\/date69613.2026.11539481","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]}}}