A Brain-Inspired ADC-Free SRAM-Based In-Memory Computing Macro With High-Precision MAC for AI Application

In this brief, an ADC-free SRAM-based IMC macro is proposed, which enables energy-efficient and high-precision MAC operation by brain-inspired computing. We identify two key features that support IMC macro to achieve high energy efficiency and high precision MAC calculation. First, the temporal-coding spiking neuron circuit is used to replace the analog-to-digital converter (ADC) to achieve high-efficiency data conversion. Second, the digital adder tree logic eliminates the cost of moving partial sums between PEs and increases the parallelism of the calculations. The mixed-signal SRAM-based IMC macro is designed for processing artificial intelligence (AI) algorithms with reconfigurable precisions based on bit-wise input and weight. In an experiment, the proposed SRAM-based IMC macro with an area of 3.41 mm(2 )was designed in 0.18um CMOS technology. Post-layout simulation results indicate that the 16Kb IMC macro achieves 10.8-13.5 TOPS/W with 4-b inputs, 4-b weights, and 14-b MAC-value outputs.

Automated summary

This paper proposes an ADC-free SRAM-based IMC macro that achieves energy-efficient and high-precision MAC operation by utilizing brain-inspired computing. It introduces two key features, including the use of temporal-coding spiking neuron circuit for high-efficiency data conversion and digital adder tree logic for increased parallelism of calculations. The designed mixed-signal SRAM-based IMC macro is specifically intended for processing AI algorithms with reconfigurable precisions based on bit-wise input and weight.