J. Hu, W. L. Goh and Y. Gao, "A Digital Compute-in-Memory Macro Featuring Two’s Complement Multiplication for LSTM-based Biomedical Signal Classification," 2025 IEEE International Symposium on Circuits and Systems (ISCAS), London, United Kingdom, 2025, pp. 1-5, doi: 10.1109/ISCAS56072.2025.11044146.
Abstract:
This paper presents a digital compute-in-memory (DCIM) macro that supports two’s complement multiplication, specifically designed for processing electrocardiogram (ECG) signals using a Long Short-Term Memory (LSTM) neural network. Two distinct bitcell computing mechanisms are introduced: one for two’s complement bit-serial recurrent inputs using a 6T SRAM bitcell with two transmission gates (TGs) for outputting a weight bit or its complement, and another for encoded one-hot ECG inputs using an 8T bitcell to output weight values based on “1” detection in the input. Each column of bitcells performs multiply-and-accumulate operations, computing bitwise vector-matrix multiplication between inputs and SRAM-stored weights. Partial sums generated by columns of DCIM cells are processed through an adder tree controlled by a shift register, yielding the final LSTM gate-sum result via a parallel adder. The proposed DCIM macro enhances hardware efficiency by reducing transistor count and supports precise two’s complement multiplication. It achieves 96.9% accuracy on a 5-class classification task, using 32-level one-hot ECG input and an INT5 quantized LSTM neural network.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research (A*STAR) - High Linearity Silicon Germanium Photonic Modulator for 6G Analog Radio over Fiber Project
Grant Reference no. : M24M8b0004