← 返回 JSSC 论文列表JSSC 2022第3期Other65nm
A Scalable CMOS Ising Computer Featuring Sparse and Reconfigurable Spin Interconn
提出一种可扩展的CMOS伊辛计算机，具有稀疏和可重构的自旋互连，用于解决NP难组合优化问题。
65-nm CMOS, 252 spins
伊辛计算机组合优化问题NP难问题CMOS自旋互连
▸创新点1：稀疏和可重构的自旋互连技术，通过动态调整自旋间的连接方式，显著提高了硬件资源的利用效率，减少了不必要的能量消耗，同时支持更灵活的优化问题映射。
▸创新点2：直接映射组合优化问题到硬件的创新方法，无需复杂的映射算法，简化了问题到硬件的转换流程，提高了计算效率和处理速度。
▸创新点3：可扩展的CMOS伊辛计算机设计，采用65-nm工艺制造，支持252个自旋单元，展示了在集成电路层面实现大规模伊辛模型的可行性，为未来更大规模的集成提供了技术基础。
▸创新点4：通过实验验证了该设计在解决最大割问题等组合优化问题上的有效性，证明了其在处理NP难问题上的实用性和高效性。
Abstract
No existing algorithms can find exact solutions to
the combinatorial optimization problems (COPs) classified as
non-deterministic polynomial-time (NP) hard problems. Alter-
natively, Ising computer based on the Ising model and annealing
process has recently drawn significant attention. The Ising
computers can find approximate solutions to the NP-hard COPs
by observing the convergence of dynamic spin states. However,
they have encountered challenges in mapping the optimization
problems to the inflexib