德拉姆
计算机科学
方案(数学)
功率(物理)
相(物质)
材料科学
电子工程
电气工程
光电子学
工程类
物理
数学
数学分析
量子力学
作者
Jinhyung Lee,Kyungjun Cho,Chang Kwon Lee,Yeonho Lee,Jae Hyung Park,Su-Hyun Oh,Yucheon Ju,Chunseok Jeong,Ho Sung Cho,Jaeseung Lee,Tae-Sik Yun,Jin Hee Cho,Sangmuk Oh,Junil Moon,Young‐Jun Park,Hong-Seok Choi,In-Keun Kim,Seung Min Yang,Sun-Yeol Kim,Jaemin Jang
标识
DOI:10.1109/isscc49657.2024.10454440
摘要
With the emergence of large-language models (LLM) and generative AI, which require an enormous amount of model parameters, the required memory bandwidth and capacity for high-end systems is on an unprecedented increase. To meet this need, we present an extended version of the high-bandwidth memory-3 (HBM3 DRAM), HBM3E, which achieves a 1280GB/s bandwidth with a cube density of 48GB. New design schemes and features, such as all-around power-through-silicon via (TSV), a 6-phase read-data-strobe (RDQS) scheme, a byte-mapping swap scheme, and a voltage-drift compensator for write data strobe (WDQS), are implemented to achieve extended bandwidth and capacity with enhanced reliability. The overall architecture and specifications, such as bump map footprint, the number of channel and I/Os, and the operation voltage, are identical to the latest HBM3 [1, 2]; therefore, backward compatibility is provided, avoiding system modification.
科研通智能强力驱动
Strongly Powered by AbleSci AI