Double MAC on a Cell: A 22-nm 8T-SRAM-Based Analog In-Memory Accelerator for Binary/Ternary Neural Networks Featuring Split Wordline

Abstract

This paper proposes a novel 8T-SRAM based computing-in-memory (CIM) accelerator for the Binary/Ternary neural networks. The proposed split dual-port 8T-SRAM cell has two input ports, simultaneously performing two binary multiply-and-accumulate (MAC) operations on left and right bitlines. This approach enables a twofold increase in throughput without significantly increasing area or power consumption, since the area overhead for doubling throughput is only two additional WL wires compared to the conventional 8T-SRAM. In addition, the proposed circuit supports binary and ternary activation input, allowing flexible adjustment of high energy efficiency and high inference accuracy depending on the application. The proposed SRAM macro consists of a $128 \times 128$ SRAM array that outputs the MAC operation results of 96 binary/ternary inputs and $96 \times 128$ binary weights as 1-5 bit digital values. The proposed circuit performance was evaluated by post-layout simulation with the 22-nm process layout of the overall CIM macro. The proposed circuit is capable of high-speed operation at 1 GHz. It achieves a maximum area efficiency of 3320 TOPS/mm2, which is $3.4 \times $ higher compared to existing research with a reasonable energy efficiency of 1471 TOPS/W. The simulated inference accuracies of the proposed circuit are 96.45%/97.67% for MNIST dataset with binary/ternary MLP model, and 86.32%/88.56% for CIFAR-10 dataset with binary/ternary VGG-like CNN model.

Keywords

• Quantized neural network (QNN)
• analog computing-in-memory (CIM)
• static random access memory (SRAM)
• voltage-mode accumulation
• multiply-and-accumulation (MAC)