Presentation 2020-11-17
R-GCN Based Function Inference for An Arithmetic Circuit
Yuichiro Fujishiro, Motoki Amagasaki, Masahiro Iida, Hiroto Ito, Daisuke Ido,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) R-GCN (Relational Graph Convolutional Network) is a convolutional neural network model for graphs consisting of nodes and edges, and is characterized by its ability to input directed graphs. In our previous work, we proposed a method for functional inference of circuits by converting gate-level netlists into graphs and inputting them into R-GCN. As a result, we have realized functional inference in a combinatorial circuit consisting of simple arithmetic functions such as adder, subtractor, multiplier and multiplexer. In order to improve the generalizability of the method, this study proposes a method for function inference for higher-level circuit functions such as FIR and IIR filters and FFTs by using the inference results of arithmetic functions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) R-GCN / netlist
Paper # VLD2020-21,ICD2020-41,DC2020-41,RECONF2020-40
Date of Issue 2020-11-10 (VLD, ICD, DC, RECONF)

Conference Information
Committee VLD / DC / RECONF / ICD / IPSJ-SLDM
Conference Date 2020/11/17(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Design Gaia 2020 -New Field of VLSI Design-
Chair Daisuke Fukuda(Fujitsu Labs.) / Hiroshi Takahashi(Ehime Univ.) / Yuichiro Shibata(Nagasaki Univ.) / Makoto Nagata(Kobe Univ.) / Yuichi Nakamura(NEC)
Vice Chair Kazutoshi Kobayashi(Kyoto Inst. of Tech.) / Tatsuhiro Tsuchiya(Osaka Univ.) / Kentaro Sano(RIKEN) / Yoshiki Yamaguchi(Tsukuba Univ.) / Masafumi Takahashi(masafumi2.takahashi@kioxia.com)
Secretary Kazutoshi Kobayashi(Hitachi) / Tatsuhiro Tsuchiya(Osaka Univ.) / Kentaro Sano(Nihon Univ.) / Yoshiki Yamaguchi(Chiba Univ.) / Masafumi Takahashi(e-trees.Japan) / (NEC)
Assistant Takuma Nishimoto(Hitachi) / / Hiroki Nakahara(Tokyo Inst. of Tech.) / Yukitaka Takemura(INTEL) / Koji Nii(TSMC) / Kosuke Miyaji(Shinshu Univ.) / Takeshi Kuboki(Kyushu Univ.)

Paper Information
Registration To Technical Committee on VLSI Design Technologies / Technical Committee on Dependable Computing / Technical Committee on Reconfigurable Systems / Technical Committee on Integrated Circuits and Devices / Special Interest Group on System and LSI Design Methodology
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) R-GCN Based Function Inference for An Arithmetic Circuit
Sub Title (in English)
Keyword(1) R-GCN
Keyword(2) netlist
1st Author's Name Yuichiro Fujishiro
1st Author's Affiliation Graduate School of Science and Technology, Kumamoto University(Kumamoto Univ.)
2nd Author's Name Motoki Amagasaki
2nd Author's Affiliation Faculty of Advanced Science and Technology, Kumamoto University(Kumamoto Univ.)
3rd Author's Name Masahiro Iida
3rd Author's Affiliation Faculty of Advanced Science and Technology, Kumamoto University(Kumamoto Univ.)
4th Author's Name Hiroto Ito
4th Author's Affiliation MITSUBISHI ELECTRIC ENGINEERING COMPANY LIMITED(MITSUBISHI ELECTRIC ENGINEERING)
5th Author's Name Daisuke Ido
5th Author's Affiliation MITSUBISHI ELECTRIC ENGINEERING COMPANY LIMITED(MITSUBISHI ELECTRIC ENGINEERING)
Date 2020-11-17
Paper # VLD2020-21,ICD2020-41,DC2020-41,RECONF2020-40
Volume (vol) vol.120
Number (no) VLD-234,ICD-235,DC-236,RECONF-237
Page pp.pp.60-65(VLD), pp.60-65(ICD), pp.60-65(DC), pp.60-65(RECONF),
#Pages 6
Date of Issue 2020-11-10 (VLD, ICD, DC, RECONF)