Using Branch Predictors to Predict Brain Activity in Brain-Machine Implants

A key problem with implantable brain-machine interfaces is that they need extreme energy efficiency. One way of lowering energy consumption is to use the low power modes available on the processors embedded in these devices. We present a technique to predict when neuronal activity of interest is likely to occur so that the processor can run at nominal operating frequency at those times, and be placed in low power modes otherwise. To achieve this, we discover that branch predictors can also predict brain activity. We perform brain surgeries on awake and anesthetized mice, and evaluate the ability of several branch predictors to predict neuronal activity in the cerebellum. We find that perceptron branch predictors can predict cerebellar activity with accuracies as high as 85%. Consequently, we co-opt branch predictors to dictate when to transition between low power and normal operating modes, saving as much as 59% of processor energy.