A Quantitative Approach to Development and Validation of Synthetic Benchmarks for Behavioral Synthesis
BibTeX
@MISC{We_aquantitative,
author = {We},
title = {A Quantitative Approach to Development and Validation of Synthetic Benchmarks for Behavioral Synthesis},
year = {}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
this paper is built on the idea of quantitative benchmark selection. We briefly explain the idea and present experimental results on the quantitative selection and validation of benchmarks. We lay out theoretically and statistically sound foundations to address the key issues related to the synthesis and analysis of synthetic benchmarks for behavioral synthesis systems. The key component of the new approach is the synthetic design example generator which composes the behavioral level specification of a design in such a way that a sunthesized design possesses the properties specified by a given set of numerical parameters. Experimental generation and application of synthetic design examples demonstrates the effectiveness of the proposed approach and the developed algorithms.
