A datapath classification method for FPGA-based scientific application accelerator systems

Yui Ogawa, Tomonori Ooya, Yasunori Osana, Masato Yoshimi, Yuri Nishikawa, Akira Funahashi, Noriko Hiroi, Hideharu Amano, Yuichiro Shibata, Kiyoshi Oguri

研究成果: Conference contribution

抄録

Resource reduction design techniques play an important role to implement large-scale FPGA-based accelerator systems in floating point applications since available resources on FPGAs are limited. This paper proposes a dataflow graph classification method which makes groups of graphs based on their similarity in order to bring out efficient graph combining. Aiming at finding effective parameters for the k-means algorithm, various parameter combinations are evaluated and compared in terms of resource reduction effects and performance. The experimental results using an FPGA-based biochemical simulator reveal that the graph clustering that uses information on the maximum common subgraphs achieve 73.3% of resource reduction rate while alleviating the performance degradation.

本文言語English
ホスト出版物のタイトルProceedings - 2010 International Conference on Field-Programmable Technology, FPT'10
ページ441-444
ページ数4
DOI
出版ステータスPublished - 2010
イベント2010 International Conference on Field-Programmable Technology, FPT'10 - Beijing, China
継続期間: 2010 12 82010 12 10

出版物シリーズ

名前Proceedings - 2010 International Conference on Field-Programmable Technology, FPT'10

Other

Other2010 International Conference on Field-Programmable Technology, FPT'10
CountryChina
CityBeijing
Period10/12/810/12/10

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications

フィンガープリント 「A datapath classification method for FPGA-based scientific application accelerator systems」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル