With the rapidly evolving internet of things (IoT) era, the ever-rising demand for data transfer and storage has put a knotty problem on conventional computers, known as the von Neumann bottleneck and memory wall problem. Slow scaling of CMOS transistors due to physical and economical limitations further exacerbates the situation. It is only logical to mimic what has been known so far as the most energy-efficient system, the human brain. The brain-inspired neuromorphic computing system computes and stores the data locally, which dramatically reduces energy consumption. In this work, we demonstrate thermal-induced multi-state memristors for memory applications. We also show that in a neural network that consists of memristors and spintronic nano oscillators, with the temperature effect from memristors, the power consumption of the network could be reduced by more than 50 % while remaining the same oscillator output power.