{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T05:59:15Z","timestamp":1781157555994,"version":"3.54.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"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":[[2026,5,13]]},"DOI":"10.1109\/fccm68464.2026.00034","type":"proceedings-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T19:59:45Z","timestamp":1781121585000},"page":"171-175","source":"Crossref","is-referenced-by-count":0,"title":["TransDot: An Area-efficient Reconfigurable Floating-Point Unit for Trans-Precision Dot-Product Accumulation for FPGA AI Engines"],"prefix":"10.1109","author":[{"given":"Jiayi","family":"Wang","sequence":"first","affiliation":[{"name":"University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maohua","family":"Nie","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sin-Chen","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C.-J. Richard","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"IEEE Standard for Floating-Point Arithmetic","year":"2019","journal-title":"IEEE Std 754-2019 (Revision of IEEE 754-2008)"},{"key":"ref2","first-page":"7686","article-title":"Training deep neural networks with 8-bit floating point numbers","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Wang"},{"key":"ref3","article-title":"Fp8 formats for deep learning","author":"Micikevicius","year":"2022"},{"key":"ref4","article-title":"Introducing nvfp4 for efficient and accurate low-precision inference","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref6","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37","author":"Gupta"},{"key":"ref7","article-title":"Mixed precision training","author":"Micikevicius","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731057"},{"key":"ref9","article-title":"Nvidia rtx blackwell gpu architecture","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3360307"},{"key":"ref11","article-title":"Neuroncore-v2 architecture","year":"2023"},{"key":"ref12","article-title":"Versal\u2122 AI Engine"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2020.3044752"},{"key":"ref14","article-title":"Berkeley hardfloat floating-point arithmetic package","author":"Hauser","year":"2019"},{"key":"ref15","first-page":"40","article-title":"Fused fp8 4-way dot product with scaling and fp32 accumulation","volume-title":"2024 IEEE 31st Symposium on Computer Arithmetic (ARITH)","author":"Lutz"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2016.2525042"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2024.3365354"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2019.2895031"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.mejo.2007.11.001"},{"key":"ref21","first-page":"1","article-title":"Configurable multi-precision floating-point multiplier architecture design for computation in deep learning","volume-title":"2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","author":"Kuo"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1093\/qjmam\/4.2.236"},{"key":"ref23","article-title":"Genus synthesis solution","year":"2025"},{"key":"ref24","article-title":"Ic compiler ii datasheet","year":"2025"},{"key":"ref25","article-title":"Primetime suite","year":"2026"}],"event":{"name":"2026 IEEE 34th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","location":"Atlanta, GA, USA","start":{"date-parts":[[2026,5,13]]},"end":{"date-parts":[[2026,5,16]]}},"container-title":["2026 IEEE 34th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11552597\/11552602\/11552709.pdf?arnumber=11552709","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T05:22:20Z","timestamp":1781155340000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11552709\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,13]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/fccm68464.2026.00034","relation":{},"subject":[],"published":{"date-parts":[[2026,5,13]]}}}