An Approach for Effective Design Space Exploration
An Approach for Effective Design Space Exploration
复制标题
DOI：
10.1007/978-3-642-21292-5_3
复制
发表时间：
2010-03
期刊：
影响因子：
--
通讯作者：
Eunsuk Kang;Ethan K. Jackson;Wolfram Schulte
中科院分区：
文献类型：
--
作者：
Eunsuk Kang;Ethan K. Jackson;Wolfram Schulte
设计空间探索（Design Space Exploration，DSE）是指在设计实施之前探索设计方案的活动。在潜在设计候选空间上操作的能力使得DSE可用于许多工程任务，包括快速原型设计，优化和系统集成。DSE的主要挑战来自于必须探索的设计空间的庞大规模。通常，一个大型系统有数百万甚至数十亿的可能性，因此枚举设计空间中的每一个点是不允许的。在本文中，我们提出了一种方法，系统地探索设计空间的成本效益的方式。关键思想是，就用户而言，许多设计候选者可能被认为是等效的，因此只需要探索空间的一小部分。我们的方法采用用户定义的等价概念，并生成对称破坏谓词，以确保底层的探索引擎不会对多个等价设计候选者进行采样。我们描述了如何将该方法集成到我们的DSE框架，FORMULA，它使用SMT求解器来解决一组全局设计约束和搜索有效的设计实例。
Design space exploration(DSE) refers to the activity of exploring design alternatives prior to implementation. The power to operate on the space of potential design candidates renders DSE useful for many engineering tasks, including rapid prototyping, optimization, and system integration. The main challenge in DSE arises from the sheer size of the design space that must be explored. Typically, a large system has millions, if not billions, of possibilities, and so enumerating every point in the design space is prohibitive. In this paper, we present a method for systematically exploring the design space in a cost-effective manner. The key idea is that many of the design candidates may be considered equivalent as far as the user is concerned, and so only a small subset of the space needs to be explored. Our approach takes the user-defined notion of equivalence, and generatessymmetry breaking predicatesto ensure that the underlying exploration engine does not sample multiple equivalent design candidates. We describe how the method is integrated into our DSE framework,FORMULA, which uses an SMT solver to solve a set of global design constraints and search for valid design instances.