A Computing-in-Memory SRAM Macro Based on Fully-Capacitive-Coupling With Hierarchical Capacity Attenuator for 4-b MAC Operation.

In this work, we present a fully capacitive-coupling-based SRAM computing-in-memory (CIM) macro aimed at improving the energy efficiency and throughput of edge devices running multi-bit multiply-and-accumulate (MAC) operations. The proposed architecture is built around a customized 9T1C bit-cell in charge-domain computation in a 28nm technology. The proposed design supports 8192 4b x 4b MAC operations simultaneously. A 4-bit input is generated by DAC, while a 4-bit weight is achieved by a hierarchical capacity attenuator array without additional sharing switches, long sharing time, and complicated controlling signal. To minimize the expensive AD conversion, an input sparsity sensing scheme is proposed, allowing to skip redundant comparators. Access time is 4 ns with 0.9 V power supply at room temperature. The proposed design achieves energy efficiency of 666 TOPS/W and throughput of 4096 GOPS.