JSSC 2024第7期Memory22nm FD-SOIEmerging Memory

A Fully RowColumn-Parallel In-Memory Computing Macro in Foundry MRAM With Differ

基于22nm FD-SOI工艺的256kb MRAM存内计算宏，采用差分读出架构解决电源和耦合噪声问题。

256kb, 22nm FD-SOI, 128-512行和512列全并行

存内计算MRAM差分读出FD-SOI并行操作

▸差分读出架构克服电源干扰和耦合噪声

▸128-512行和512列全并行操作

▸基于G-to-I转换和IDC的6位数字化技术

Abstract

This work demonstrates two integrated 256-kb in-memory computing (IMC) macros based on foundry MRAM, implemented in a 22-nm fully depleted silicon on insulator (FD- SOI) CMOS process. Embedded non-volatile memory (eNVM), including MRAM, resistive RAM (ReRAM), and phase-change memory (PCM), is an emerging class of technologies that have drawn interest for IMC due to their potential to achieve high den- sity with advanced-node scaling as well as low-power always-on/ duty-cycled operation. However,