PreAxC: Error Distribution Prediction for Approximate Computing Quality Control using Graph Neural Networks
PreAxC: Error Distribution Prediction for Approximate Computing Quality Control using Graph Neural Networks
复制标题
DOI：
10.1109/isqed57927.2023.10129393
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Lakshmi Sathidevi;Abhinav Sharma;Nan Wu;Xun Jiao;Cong Hao
中科院分区：
文献类型：
--
作者：
Lakshmi Sathidevi;Abhinav Sharma;Nan Wu;Xun Jiao;Cong Hao
虽然近似计算(AXC)是一种有希望在精度和能源效率之间进行权衡的技术，但一个根本的挑战是缺乏准确和信息丰富的AXC应用程序的误差模型。在这项工作中，我们提出了一种新的AXC设计误差建模和预测流程--PreAxC。我们不像现有的工作那样使用简单的错误统计，而是使用错误分布来进行具有输入感知的AXC电路错误分析。提出了基于图神经网络(GNN)的AXC程序误差分布预测方法，用数据流图(DFG)表示。我们提出了两种方法：无模型方法和基于模型方法，前者直接预测误差分布直方图，后者使用高斯混合模型(GMM)对分布建模并预测GMM参数。实验结果表明，在训练过程中，即使对于完全不可见的图(代表新的AXC程序)，我们的方法也能比现有的误差统计方法更好地预测误差分布，尤其是无模型方法。
While Approximate Computing (AxC) is a promising technique to trade off accuracy for energy efficiency, one fundamental challenge is the lack of accurate and informative error models of AxC applications. In this work, we propose PreAxC, a novel error modeling and prediction flow for AxC designs. Instead of using simple error statistics as in existing work, we use error distribution for AxC circuit error analysis with input awareness. We propose graph neural network (GNN) based methods to predict the error distribution of AxC programs, which are represented as data flow graphs (DFGs). We propose two approaches: model-free and model-based, where the former directly predicts the error distribution histogram, and the latter models the distribution using Gaussian Mixture Model (GMM) and predicts the GMM parameters. Experiment results demonstrate that our approaches can outperform existing error statistics and can successfully predict the error distribution, especially the model-free approach, even for completely unseen graphs (representing new AxC programs) during training.