# Using Branch Predictors to Monitor Brain Activity

## TL;DR

This paper demonstrates that branch predictors, especially perceptron predictors, can effectively forecast brain activity, enabling energy-efficient neuroprosthetic devices by switching processor modes based on predicted neuronal signals.

## Contribution

It introduces a novel application of branch predictors to monitor brain activity, achieving high prediction accuracy and significant energy savings in neuroprosthetic systems.

## Key findings

- Perceptron branch predictors predict cerebellar activity with up to 85% accuracy.
- Using branch predictors for mode switching saves up to 59% of processor energy.
- The technique is validated through brain surgeries on awake and anesthetized mice.

## Abstract

A key problem with neuroprostheses and brain monitoring interfaces is that they need extreme energy efficiency. One way of lowering energy is to use the low power modes avail- able 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. By performing brain surgeries on awake and anesthetized mice, we evaluate several branch predictors and 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.