A Fully Digital SRAM-Based Four-Layer In-Memory Computing Unit Achieving Multiplication Operations and Results Store
- 26 April 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 31 (6) , 776-788
Abstract
The separation of memory and arithmetic logic unit (ALU) in the von Neumann computing architecture hinders the development of big data and high-performance computing. In-memory computing (IMC) as a new computation method significantly reduces the latency and power consumption of data processing. In this study, we propose a fully digital static random access memory (SRAM)-based IMC architecture, which has the following advantages: 1) it simplifies multiplication to multicycle addition operations, reuses logic cells, and reduces hardware overhead; 2) by adding a pair of nMOS transistors to achieve internal write-back, the computational efficiency is improved, and at the same time, the final result of the multiplication can be stored locally, eliminating the need to read the computational result immediately; and 3) this scheme can be easily expanded to multiplication operations with different bit widths, which provides good scalability. A 4-kb SRAM-IMC macro chip is manufactured using the SMIC 55-nm technology to realize 4-bit multiplication, with an energy efficiency of 51.4 TOPS/W (0.9 V) and a throughput of 234.3 GOPS/mm2. The proposed multiplication–accumulation architecture is applied to a neural network, which achieves 98.7% accuracy with the Mixed National Institute of Standards and Technology database (MNIST) dataset.Keywords
Funding Information
- National Natural Science Foundation of China (62074001)
- State Key Program of the National Natural Science Foundation of China (61934005)
- National Key Research and Development Program of China (2018YFB2202602)
- Joint Funds of the National Natural Science Foundation of China (U19A2074)
This publication has 36 references indexed in Scilit:
- CONV-SRAM: An Energy-Efficient SRAM With In-Memory Dot-Product Computation for Low-Power Convolutional Neural NetworksIEEE Journal of Solid-State Circuits, 2018
- X-SRAM: Enabling In-Memory Boolean Computations in CMOS Static Random Access MemoriesIEEE Transactions on Circuits and Systems I: Regular Papers, 2018
- A Mixed-Signal Binarized Convolutional-Neural-Network Accelerator Integrating Dense Weight Storage and Multiplication for Reduced Data Movement2018
- A 42pJ/decision 3.12TOPS/W robust in-memory machine learning classifier with on-chip training2018
- An Energy-Efficient Precision-Scalable ConvNet Processor in 40-nm CMOSIEEE Journal of Solid-State Circuits, 2017
- Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural NetworksIEEE Journal of Solid-State Circuits, 2016
- In-Memory Computing Architectures for Sparse Distributed MemoryIEEE Transactions on Biomedical Circuits and Systems, 2016
- TrueNorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic ChipIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2015
- Energy-efficient and high throughput sparse distributed memory architecture2015
- An energy-efficient memory-based high-throughput VLSI architecture for convolutional networks2015