A high-density logic-on-logic 3DIC design using face-to-face hybrid wafer-bonding on 12nm FinFET process

S. Sinha, S Hung, D. Fisher,X. Xu, C. Chao, P. Chandupatla, F. Frederick, H. Perry,D. Smith, A. Cestero, J. Safran, V. Ayyavu,M. Bhargava,R. Mathur,D. Prasad, R. Katz, A. Kinsbruner, J. Garant,J. Lubguban, S. Knickerbocker, V. Soler,B. Cline, R. Christy, T. McLaurin, N. Robson, D. Berger

2020 IEEE International Electron Devices Meeting (IEDM)(2020)

引用 12|浏览26
暂无评分
摘要
A high-density-3D test-vehicle showcasing a synchronous cache coherent mesh interconnect design (Arm Neoverse ® CMN-600) operational at frequencies up to 2.4 GHz and partitioned in 3D using 5.76μm pitch face-to-face wafer-bond 3D connections on a 12nm FinFET process is presented. The test-vehicle is designed using an industry tool compatible innovative physical implementation flow and serves as the first known industry demonstration of the IEEE 1838 3DIC Design-for-Test (DFT) standard. We demonstrate a 3D aggregate bandwidth of 307 GB/s, a record bandwidth density of 3.4 TB/s/mm 2 , and an energy efficiency of 0.02 pJ/bit for the 3D-stacked dies. We present measurement and analysis data from 945 dies where a total of 13.5 million signal 3D wafer-bond nets and 20 million power-delivery 3D wafer-bond nets on multiple wafer-bonded pairs are tested showing robust functionality, paving the path for 3D-stacked high performance logic-on-logic applications.
更多
查看译文
关键词
wafer-bond nets,multiple wafer-bonded pairs,face-to-face hybrid wafer-bonding,FinFET process,synchronous cache coherent mesh interconnect design,industry tool compatible innovative physical implementation flow,3D aggregate bandwidth,bandwidth density,face-to-face wafer-bond 3D connections,industry demonstration,high-density logic-on-logic 3D IC design,3D IC design-for-test standard,high-density-3D test-vehicle,Arm Neoverse CMN-600,EEE 1838 3DIC design-for-test standard,DFT standard,3D-stacked dies,data analysis,power-delivery 3D wafer-bond nets,3D-stacked high performance logic-on-logic applications,energy efficiency,size 12.0 nm,bit rate 307 Gbit/s
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要