Summary
International Technical Conference on Circuits/Systems, Computers and Communications
2008
Session Number:P2
Session:
Number:P2-45
Exploration of Schedule Space by Random Walk
Liangwei Ge, Song Chen, Takeshi Yoshimura,
pp.-
Publication Date:2008/7/7
Online ISSN:2188-5079
Summary:
Scheduling, an important step in high-level synthesis, is a searching process in the solution space. Due to the vastness of solution space, it is usually difficult to search schedules efficiently. In this paper, we present a random walk based perturbation method to explore the schedule space. The method first limits the search within a specific sub-solution space (SSS). Then, the SSS is repeatedly perturbed by using an N-dimension random walk so that better schedules can be searched in the new SSS. To improve the search efficiency, a guided perturbation strategy is presented that leads the random walk toward promising directions. Experiment shows that in runtime comparable to existing methods, ours finds schedules of better quality.