PRIMAL: Power Inference using Machine Learning
PRIMAL: Power Inference using Machine Learning
复制标题
DOI：
10.1145/3316781.3317884
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Yuan Zhou;Haoxing Ren;Yanqing Zhang;Ben Keller;Brucek Khailany;Zhiru Zhang
中科院分区：
文献类型：
--
作者：
Yuan Zhou;Haoxing Ren;Yanqing Zhang;Ben Keller;Brucek Khailany;Zhiru Zhang
本文介绍了PRIMAL，一种新的基于学习的框架，使快速和准确的ASIC设计的功耗估计。PRIMAL使用设计验证测试平台训练机器学习（ML）模型，以表征可重用电路构建块的能力。然后，训练的模型可以用于在不同的工作负载下生成相同块的详细功率分布。我们评估了几种已建立的ML模型在此任务上的性能，包括岭回归，梯度树提升，多层感知器和卷积神经网络（CNN）。对于平均功耗估计，基于ML的技术可以在各种现实基准测试中实现小于1%的平均误差，在准确性和速度方面都优于商业RTL功耗估计工具（快15倍）。对于逐周期功耗估计，PRIMAL平均比商业门级功耗分析工具快50倍，平均误差小于5%。特别是，我们的基于CNN的方法实现了35倍的加速，RISC-V处理器内核的逐周期功耗估计误差为5.2%。此外，我们对NoC路由器的案例研究表明，PRIMAL可以实现4.5%的小估计误差使用SystemC模拟的循环近似跟踪。CCS概念·计算方法学·机器学习;建模方法学;。硬件功率估算和最佳化
This paper introduces PRIMAL, a novel learning-based frame-work that enables fast and accurate power estimation for ASIC designs. PRIMAL trains machine learning (ML) models with design verification testbenches for characterizing the power of reusable circuit building blocks. The trained models can then be used to generate detailed power profiles of the same blocks under different workloads. We evaluate the performance of several established ML models on this task, including ridge regression, gradient tree boosting, multi-layer perceptron, and convolutional neural network (CNN). For average power estimation, ML-based techniques can achieve an average error of less than 1% across a diverse set of realistic benchmarks, outperforming a commercial RTL power estimation tool in both accuracy and speed (15x faster). For cycle-by-cycle power estimation, PRIMAL is on average 50x faster than a commercial gate-level power analysis tool, with an average error less than 5%. In particular, our CNN-based method achieves a 35x speed-up and an error of 5.2% for cycle-by-cycle power estimation of a RISC-V processor core. Furthermore, our case study on a NoC router shows that PRIMAL can achieve a small estimation error of 4.5% using cycle-approximate traces from SystemC simulation.CCS Concepts• Computing methodologies ⟶ Machine learning; Modeling methodologies;. Hardware ⟶ Power estimation and optimization;