"Smart" design space sampling to predict Pareto-optimal solutions
"Smart" design space sampling to predict Pareto-optimal solutions
复制标题
“智能”设计空间采样来预测帕累托最优解决方案
DOI：
10.1145/2248418.2248436
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Markus Püschel
中科院分区：
文献类型：
--
作者：
M. Zuluaga;Andreas Krause;Peter Milder;Markus Püschel
许多高级合成工具在将高级规格映射到寄存器转移级别的描述中提供了自由度。这些选择不会影响功能行为，而是跨越具有不同成本效果的设计空间。在本文中，我们提出了一种基于机器学习的新型方法，该方法有效地确定了帕累托最佳设计，同时仅采样和合成了一部分设计空间。该方法结合了三个关键组成部分：（1）基于高斯过程的回归模型，以根据合成训练数据来预测区域和吞吐量。 （2）一种“智能”采样策略GP-PUCB，通过仔细选择下一个设计以合成以最大化进度，从而迭代地完善模型。 （3）基于评估模型的准确性而无需访问完整综合数据而停止标准。我们使用IP生成器来证明我们的方法的有效性，用于离散的傅立叶变换和分类网络。但是，我们的算法不是该应用程序特定的，可以应用于多种帕累托前预测问题。
Many high-level synthesis tools offer degrees of freedom in mapping high-level specifications to Register-Transfer Level descriptions. These choices do not affect the functional behavior but span a design space of different cost-performance tradeoffs. In this paper we present a novel machine learning-based approach that efficiently determines the Pareto-optimal designs while only sampling and synthesizing a fraction of the design space. The approach combines three key components: (1) A regression model based on Gaussian processes to predict area and throughput based on synthesis training data. (2) A "smart" sampling strategy, GP-PUCB, to iteratively refine the model by carefully selecting the next design to synthesize to maximize progress. (3) A stopping criterion based on assessing the accuracy of the model without access to complete synthesis data. We demonstrate the effectiveness of our approach using IP generators for discrete Fourier transforms and sorting networks. However, our algorithm is not specific to this application and can be applied to a wide range of Pareto front prediction problems.