Logo image
A 4-Kb 1-to-8-bit Configurable 6T SRAM-Based Computation-in-Memory Unit-Macro for CNN-Based AI Edge Processors
期刊文章   同儕審查

A 4-Kb 1-to-8-bit Configurable 6T SRAM-Based Computation-in-Memory Unit-Macro for CNN-Based AI Edge Processors

Yen-Cheng Chiu, Zhixiao Zhang, Jia-Jing Chen, Xin Si, Ruhui Liu, Yung-Ning Tu, Jian-Wei Su, Wei-Hsing Huang, Jing-Hong Wang, Wei-Chen Wei, …
IEEE Journal of Solid-State Circuits, 卷.55(10), 頁碼.2790-2801
10/2020

摘要

AI edge processor CNN computing-in-memory (CIM) SRAM Electrical and Electronic Engineering
Previous SRAM-based computing-in-memory (SRAM-CIM) macros suffer small read margins for high-precision operations, large cell array area overhead, and limited compatibility with many input and weight configurations. This work presents a 1-to-8-bit configurable SRAM CIM unit-macro using: 1) a hybrid structure combining 6T-SRAM based in-memory binary product-sum (PS) operations with digital near-memory-computing multibit PS accumulation to increase read accuracy and reduce area overhead; 2) column-based place-value-grouped weight mapping and a serial-bit input (SBIN) mapping scheme to facilitate reconfiguration and increase array efficiency under various input and weight configurations; 3) a self-reference multilevel reader (SRMLR) to reduce read-out energy and achieve a sensing margin 2 $ imes $ that of the mid-point reference scheme; and 4) an input-aware bitline voltage compensation scheme to ensure successful read operations across various input-weight patterns. A 4-Kb configurable 6T-SRAM CIM unit-macro was fabricated using a 55-nm CMOS process with foundry 6T-SRAM cells. The resulting macro achieved access times of 3.5 ns per cycle (pipeline) and energy efficiency of 0.6-40.2 TOPS/W under binary to 8-b input/8-b weight precision.

相關連結

指標

1 檢視次數

詳細資料

Logo image