Improving Microarchitectural Performance with Neural Predictors

这个项目将探索神经学习在微架构预测器中的应用，例如分支预测器。 神经分支预测器用神经学习代替常用的基于计数器的技术，提供更好的预测能力。 将特别强调减少神经预测器的延迟，这阻碍了它们对整体性能的贡献。 我们期望取得以下成果：（1）提高神经预测器的准确性，（2）降低神经预测器等待时间对性能的影响，（3）对神经预测器所利用的分支预测问题的性质有更深的理解，以及（4）用于在微架构中实现神经预测器的新数字电路。一个程序的长期行为，以便对未来指令的工作可以提前开始，从而减少程序运行所需的时间。 这些预测必须高度准确。借用神经科学的概念，我们将探索使用人工神经元来取代今天使用的预测器。 人工神经元已被用作其他领域的预测器，初步结果表明，它们可以很好地预测程序的行为。 我们将通过探索使神经元工作更快，更准确，更大范围的方法来改善这些结果，从而提高计算机的整体性能。

This project will explore the use of neural learning in micro architectural predictors such as branch predictors. Neural branch predictors replace commonly used counter-based techniques with neural learning, providing better predictive capabilities. Special emphasis will be placed on reducing the latency of neural predictors, which hinders their contribution to overall performance. We expect the following results: (1) improved accuracy for neural predictors, (2) decreased impact of neural predictor latency on performance, (3) a deeper under understanding of the properties of the branch prediction problem that are exploited by neural predictors, and (4) new digital circuits for implementing neural predictors in micro architectures.Microprocessors predict the near-term behavior of a program so that work on future instructions may begin early, reducing the amount of time the program takes to run. These predictions must be highly accurate. Borrowing concepts from neuroscience, we will explore the use of artificial neurons to replace the predictors used today. Artificial neurons have been used as predictors in other domains, and preliminary results show that they work well for predicting program behavior. We will improve these results by exploring ways to make the neurons work faster, more accurately, and with a larger scope, thus improving overall performance of computers.