A Reconfigurable SRAM Computing-in-Memory Macro Supporting Ping-Pong Operation and CIM pipeline for Multi-mode MAC operations
Authors:
- 28 October 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 182-183
Abstract
In this work, we present a reconfigurable SRAM computing-in-memory (CIM) macro supporting ping-pong operation and pipeline operation for multi-mode multiply-and-accumulate (MAC) operations. The macro can be reconfigured to execute AND or XNOR, offering great flexibilities to cover binary neural network (BNN), ternary neural network (TNN), and multi-bit operation through serially 1-bit AND operations. The main contributions include: (1) A reconfigurable scheme to map inputs and weight of 8T1C bit-cell, supporting three MAC operations; (2) An architecture integrated ping-pong operation and two-level CIM pipeline. Simulated in a standard 28-nm process, the proposed design shows good computing linearity and variations. The average energy efficiency of 1b-AND, BNN, and TNN MAC operation are 1533.7, 1522.9, and 1713.2 TOPS/W, respectively.Keywords
Funding Information
- National Key Research and Development Program of China (2018YFE0203801)
This publication has 6 references indexed in Scilit:
- A Local Computing Cell and 6T SRAM-Based Computing-in-Memory Macro With 8-b MAC Operation for Edge AI ChipsIEEE Journal of Solid-State Circuits, 2021
- 15.2 A 2.75-to-75.9TOPS/W Computing-in-Memory NN Processor Supporting Set-Associate Block-Wise Zero Skipping and Ping-Pong CIM with Simultaneous Computation and Weight Updating2021
- 16.3 A 28nm 384kb 6T-SRAM Computation-in-Memory Macro with 8b Precision for AI Edge Chips2021
- 15.1 A Programmable Neural-Network Inference Accelerator Based on Scalable In-Memory Computing2021
- C3SRAM: An In-Memory-Computing SRAM Macro Based on Robust Capacitive Coupling Computing MechanismIEEE Journal of Solid-State Circuits, 2020
- XNOR-SRAM: In-Memory Computing SRAM Macro for Binary/Ternary Deep Neural NetworksIEEE Journal of Solid-State Circuits, 2020