Presentation 2013-11-27
Fast distance calculation method for rooted tree with CUDA
Hiroki SAKAMOTO, Yasuhiro TAKASHIMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a fast distance calculation method for the rooted tree with CUDA. In recent years, GPGPU has been used widely. GPGPU performs fast and parallel calculation for various general problems. But, most of them focus on only the simple iterative calculation. There is little method for the graph algorithm. In this paper, we introduce the fast algorithm for the list ranking and propose a method of the fast distance calculation for the rooted tree. To confirm the efficiency of the proposed method, we apply our method to the rooted tree with the number of its vertices is 1000000. We obtain the result with 200 times faster than the implementation by C language.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) CUDA / GPGPU / list ranking / Wylie's algorithm
Paper # VLD2013-62,DC2013-28
Date of Issue

Conference Information
Committee DC
Conference Date 2013/11/20(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 Dependable Computing (DC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Fast distance calculation method for rooted tree with CUDA
Sub Title (in English)
Keyword(1) CUDA
Keyword(2) GPGPU
Keyword(3) list ranking
Keyword(4) Wylie's algorithm
1st Author's Name Hiroki SAKAMOTO
1st Author's Affiliation Faculty of Environmental Engineering, The University of Kitakyushu()
2nd Author's Name Yasuhiro TAKASHIMA
2nd Author's Affiliation Faculty of Environmental Engineering, The University of Kitakyushu
Date 2013-11-27
Paper # VLD2013-62,DC2013-28
Volume (vol) vol.113
Number (no) 321
Page pp.pp.-
#Pages 6
Date of Issue