A Practical Low-Power Memristor-Based Analog Neural Branch Predictor

Recently, the discovery of memristor brought the promise of high density, low energy, and combined memory/arithmetic capability into computing. This paper demonstrates a practical neural branch predictor based on memristor. By using analog computation techniques, as well as exploiting the accuracy tolerance of branch prediction, the authors' design is able to efficiently realize a neural prediction algorithm. Compared to the digital counterpart, their method achieves significant energy reduction while maintaining a better prediction accuracy and a higher IPC. Their approach also reduces the resource and energy required by an alternative design.