As one of the core technologies for future mobile communications, the massive MIMO technology can effectively improve the network capacity, enhance the network robustness, and reduce the communication latency. However, the complexity of baseband processing increases sharply as the number of antennas increases. Therefore, the design of high-performance massive MIMO baseband processing chips, especially the design of massive MIMO detection chips featuring low complexity and high parallelism, has become a technical bottleneck that restricts the broad application of the massive MIMO technology in communications systems.