<br>通过算法和硬件优化加速贝叶斯神经网络,IEEE Transactions on Parallel and Distributed Systems

当前位置： X-MOL 学术 › IEEE Trans. Parallel Distrib. Syst. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

通过算法和硬件优化加速贝叶斯神经网络
IEEE Transactions on Parallel and Distributed Systems ( IF 5.6 ) Pub Date : 2022-02-23 , DOI: 10.1109/tpds.2022.3153682
Hongxiang Fan ₁ , Martin Ferianc ₂ , Zhiqiang Que ₁ , Xinyu Niu ₃ , Miguel Rodrigues ₂ , Wayne Luk ₁

Affiliation

贝叶斯神经网络 (BayesNN) 由于能够捕获和表示模型不确定性，因此在自动驾驶或医疗保健等各种安全关键应用中展示了其优势。然而，由于蒙特卡罗采样来量化其不确定性，标准贝叶斯神经网络需要重复运行，这给它们的实际硬件性能带来了负担。为了解决这个性能问题，本文系统地利用了贝叶斯神经网络中广泛的结构化稀疏性和冗余计算。与标准卷积神经网络中的非结构化或结构化稀疏性不同，贝叶斯神经网络的结构化稀疏性是通过蒙特卡罗 Dropout 及其在不确定性估计和预测过程中所需的相关采样引入的，可以通过算法和硬件优化来利用。我们首先将观察到的稀疏性模式分为三类：通道稀疏性、层稀疏性和样本稀疏性。在算法方面，提出了一个框架来自动探索这三个稀疏类别，而不牺牲算法性能。我们证明了可以利用结构化稀疏性将 CPU 设计加速最多 49 倍，将 GPU 设计加速最多 40 倍。在硬件方面，提出了一种新颖的硬件架构来加速贝叶斯神经网络，利用运行时自适应硬件引擎和智能跳跃支持实现了高硬件性能。在 FPGA 上实现所提出的硬件设计后，我们的实验表明，与未优化的贝叶斯网络相比，算法优化的贝叶斯神经网络可以实现高达 56 倍的加速。与优化的 GPU 实现相比，我们的 FPGA 设计达到了 7。加速 6 倍，能效提升高达 39.3 倍。

"点击查看英文标题和摘要"

Accelerating Bayesian Neural Networks via Algorithmic and Hardware Optimizations

Bayesian neural networks (BayesNNs) have demonstrated their advantages in various safety-critical applications, such as autonomous driving or healthcare, due to their ability to capture and represent model uncertainty. However, standard BayesNNs require to be repeatedly run because of Monte Carlo sampling to quantify their uncertainty, which puts a burden on their real-world hardware performance. To address this performance issue, this article systematically exploits the extensive structured sparsity and redundant computation in BayesNNs. Different from the unstructured or structured sparsity in standard convolutional NNs, the structured sparsity of BayesNNs is introduced by Monte Carlo Dropout and its associated sampling required during uncertainty estimation and prediction, which can be exploited through both algorithmic and hardware optimizations. We first classify the observed sparsity patterns into three categories: channel sparsity, layer sparsity and sample sparsity. On the algorithmic side, a framework is proposed to automatically explore these three sparsity categories without sacrificing algorithmic performance. We demonstrated that structured sparsity can be exploited to accelerate CPU designs by up to 49 times, and GPU designs by up to 40 times. On the hardware side, a novel hardware architecture is proposed to accelerate BayesNNs, which achieves a high hardware performance using the runtime adaptable hardware engines and the intelligent skipping support. Upon implementing the proposed hardware design on an FPGA, our experiments demonstrated that the algorithm-optimized BayesNNs can achieve up to 56 times speedup when compared with unoptimized Bayesian nets. Comparing with the optimized GPU implementation, our FPGA design achieved up to 7.6 times speedup and up to 39.3 times higher energy efficiency.

更新日期：2022-02-23

点击分享查看原文

点击收藏

阅读更多本刊新发论文本刊介绍/投稿指南