期刊文献+

一种新的快速FPGA布局算法

New Fast FPGA Placer
原文传递
导出
摘要 在模拟退火算法的基础上,提出了一种快速FPGA布局算法.该算法先用解析模型快速确定所有宏模块及单个逻辑模块的"理想"位置,然后通过局部扩散消除模块之间的重叠,得到一个较好的初始布局方案,最后再用低温的模拟退火进一步优化,确定各模块的最终位置.实验数据表明,以目前在学术界普遍采用的平方线网总长度为目标函数,与经典的VPR算法相比,新算法大大降低了布局所耗费的时间,而不影响最终布局方案的质量. A new fast FPGA placer which could treat both macro blocks and single blocks simultaneously is proposed. First the new placer determines the ideal position of all the blocks with analytical model, and then eliminates overlaps among blocks by local expansion. Finally, typical simulated low temperature annealing algorithm is used to optimize the placement. Experimental results show that in comparison with the popular VPR algorithm, the proposed method speeds up the placement greatly without deteriorating the quality of final placement.
出处 《复旦学报(自然科学版)》 CAS CSCD 北大核心 2009年第4期431-437,共7页 Journal of Fudan University:Natural Science
基金 国家自然科学基金资助项目(60776023) 国家"八六三"高技术研究发展计划资助项目(2007AA01Z285)
关键词 快速布局 二次规划法 局部扩散 模拟退火 fast placement quadratic programming local expansion simulated annealing
  • 相关文献

参考文献11

  • 1Shi J, Randhar A, Bhatia D. Macro block based FPGA floor planning [J]. VLSI Design, 1997,4(7): 21-26.
  • 2Marquardt A, Betz V. Timing-driven placement for FPGAs [C]// Proceedings of the 8th ACM/SIGDA International Symposium on Field-Programmable Gate Arrays. Monterey, USA: ACM, 2000: 203-213.
  • 3Xu Y B, Khalid M. QPF: Efficient quadratic placement for FPGAs [C]/// Proceedings of 15th International Conference on Field-Programmable Logic and Applications. Finland: IEEE, 2005.
  • 4Viswanathan N, Chu. Fast place: Efficient analytical placement using cell shifting, iterative local refinement, and hybrid net model [J]. IEEE Transactions on computer-aided design of integrated circuits and systems, 2005,24(5) : 722-733.
  • 5Barret R, Berry M, Demmel J, et al. Templates for the solution of linear systems: Building blocks for iterative methods [M].USA: Society for Industrial Mathematics, 1994.
  • 6Luenberger D. Linear and nonlinear programming [M]. USA: Addison Wesley, 1984. 423-427.
  • 7戈卢布GH 范洛恩CF著 袁亚湘译.矩阵计算[M].北京:科学出版社,2001.76-78.
  • 8Betz V. VPR and T-VPack user's manual (Version 4. 30) [DB/OL]. (2000-03-27) [2006-10-08]. http://www, eeeg. toronto, edu/-janders/ece1387/e1/manual 430. pdf.
  • 9Eguro K, Hauck S, Sharma A. Architecture-adaptive range limit windowing for simulated annealing FPGA plaeement [C]// Proceedings of the 42nd Design Automation Conference. Anaheim, USA: ACM, 2005 : 439-444.
  • 10Ramage A. An introduction to iterative solver and preconditioning techniques[M].USA: PIMS Workshop, 2003.

共引文献21

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部