In-Memory Neural Stochastic Differential Equations with Probabilistic Differential Pair Achieved by In-Situ P-Bit Using CMOS Integrated Voltage-Controlled Magnetic Tunnel Junctions

作者：Zhihua Xiao, Yaoru Hou, Zihan Tong, Yicheng Jiang, Yiyang Zhang, Xuezhao Wu, Albert Lee, Di Wu, Hao Cai, Qiming Shao · 年份：2024 · DOI：10.1109/iedm50854.2024.10873318 · 被引用次数：6 · 研究领域：Neural Networks and Applications、Machine Learning and ELM、Neural Networks and Reservoir Computing

The probabilistic bit (P-bit) is the core of probabilistic computing. We propose a novel in-situ P-bit compatible with compute-in-memory (CIM) schemes using voltage-controlled magnetic tunnel junctions (MTJs) to eliminate the generation-sample-transfer-compute paradigm of current P-bits. The conventional approach of sampling and transferring random sequences between separate P-bits and computing units reintroduces the memory bottleneck seen in von Neumann architectures, thereby limiting the efficiency of probabilistic computing. By pairing a data-bit and a P-bit as a probabilistic differential pair in a crossbar array, we enable random sequences to be directly utilized for computing. This generation-compute scheme eradicates the sampling and transfer costs associated with previous probabilistic computing methods. Full reuse of devices in the differential cells allows for probabilistic CIM with a large number of P-bits and high parallelism, suitable for real-world probabilistic computing tasks. We demonstrated in-memory neural stochastic differential equations for the reverse diffusion process in generative models. The results shows that without the bottlenecks, in-situ P-bit throughput is$6\times$faster and$2.19\times$more efficient than ex-situ P-bits using the same technology. Compared to other devices and schemes, the proposed scheme is$3\times$faster than state-of-the-art CMOS designs and$1.36\times$more energy efficient.