Presentation 2011-09-26
FPGA placement based on Self-Organized Map
Yasuaki TOMONARI, Motoki AMAGASAKI, Masahiro IIDA, Morihiro KUGA, Toshinori SUEYOSHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Cell placement is an important phase of current FPGA(Field Programmable Gate Array) circuit design. However, this placement problem is NP-hard. Although nondeterministic algorithms such as Simulated Annealing(SA) are successful in slolving this problem, they are known to be slow. In this paper, we introduce a new neural network approach to placement problem of FPGA. The used network is a Kohonen self-organising map. A connection relation ship of cluster-level netlists is converted to a a set of appropriate input vectors. These vectors which have higher dimensionality are fed to the self-organizing map at random to map themselves onto a 2-dimensional plane of the regular chip. The key feature is that som algorithm perform the cell placement to minimize total connection length in the circuit. In this paper, we evaluate our placement tool using some benchmark circuits.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) FPGA placement / Self-Organizing Maps / SOM
Paper # RECONF2011-26
Date of Issue

Conference Information
Committee RECONF
Conference Date 2011/9/19(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Reconfigurable Systems (RECONF)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) FPGA placement based on Self-Organized Map
Sub Title (in English)
Keyword(1) FPGA placement
Keyword(2) Self-Organizing Maps
Keyword(3) SOM
1st Author's Name Yasuaki TOMONARI
1st Author's Affiliation Graduate School of Science and Technology, Kumamoto University()
2nd Author's Name Motoki AMAGASAKI
2nd Author's Affiliation Graduate School of Science and Technology, Kumamoto University
3rd Author's Name Masahiro IIDA
3rd Author's Affiliation Graduate School of Science and Technology, Kumamoto University
4th Author's Name Morihiro KUGA
4th Author's Affiliation Graduate School of Science and Technology, Kumamoto University
5th Author's Name Toshinori SUEYOSHI
5th Author's Affiliation Graduate School of Science and Technology, Kumamoto University
Date 2011-09-26
Paper # RECONF2011-26
Volume (vol) vol.111
Number (no) 218
Page pp.pp.-
#Pages 6
Date of Issue