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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2010 International Conference on Field-Programmable Technology, FPT'10
Pages441-444
Number of pages4
DOIs
Publication statusPublished - 2010
Event2010 International Conference on Field-Programmable Technology, FPT'10 - Beijing, China
Duration: 2010 Dec 82010 Dec 10

Publication series

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

Other

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

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'A datapath classification method for FPGA-based scientific application accelerator systems'. Together they form a unique fingerprint.

Cite this