SSA-over-array(SSoA):A stacked DRAM architecture for nearmemory computingOACSTPCDEI
Aiming to enhance the bandwidth in near-memory computing,this paper proposes a SSA-over-array(SSoA)architecture.By relocating the secondary sense amplifier(SSA)from dynamic random access memory(DRAM)to the logic die and repositioning the DRAM-to-logic stacking interface closer to the DRAM core,the SSoA overcomes the layout and area limitations of SSA and master DQ(MDQ),leading to improvements in DRAM data-width density and frequency,significantly enhancing bandwidth density.The quantitative evaluation results show a 70.18 times improvement in bandwidth per unit area over the baseline,with a maximum bandwidth of 168.296 Tbps/Gb.We believe the SSoA is poised to redefine near-memory computing development strategies.
Xiping Jiang;Fujun Bai;Song Wang;Yixin Guo;Fengguo Zuo;Wenwu Xiao;Yubing Wang;Jianguo Yang;Ming Liu;
Institute of Microelectronics of the Chinese Academy of Sciences,Beijing 100029,China School of Integrated Circuits,University of Chinese Academy of Sciences,Beijing 100029,China Xi’an UniIC Semiconductors,Xi’an 710075,ChinaXi’an UniIC Semiconductors,Xi’an 710075,ChinaXi’an UniIC Semiconductors,Xi’an 710075,China School of Microelectronics,University of Science and Technology of China,Hefei 230026,ChinaInstitute of Microelectronics of the Chinese Academy of Sciences,Beijing 100029,ChinaInstitute of Microelectronics of the Chinese Academy of Sciences,Beijing 100029,China School of Integrated Circuits,University of Chinese Academy of Sciences,Beijing 100029,China
计算机与自动化
near-memoryvertical stackingSSAbandwidth density
《Journal of Semiconductors》 2024 (010)
P.42-53 / 12
supported in part by the Strategic Priority Research Program of the Chinese Academy of Sciences under Grant No.XDB44000000。
评论