Acceleration of Computing the Kleene Star in Max-Plus Algebra Using CUDA GPUs

• GOTO Hiroyuki

  Nagaoka University of Technology

抄録

This research aims to accelerate the computation module in max-plus algebra using CUDA technology on graphics processing units (GPUs) designed for high-performance computing. Our target is the Kleene star of a weighted adjacency matrix for directed acyclic graphs (DAGs). Using a inexpensive GPU card for our experiments, we obtained more than a 16-fold speedup compared with an Athlon 64 X2.

収録刊行物

• IEICE Transactions on Information and Systems

  IEICE Transactions on Information and Systems E94-D (2), 371-374, 2011

  一般社団法人 電子情報通信学会

キーワード

• Kleene star
• max-plus algebra
• adjacency matrix
• DAG
• GPU
• CUDA

詳細情報

• CRID: 1390282679355067008
• NII論文ID: 130000453899
• DOI: 10.1587/transinf.e94.d.371
• ISSN: 17451361
• ISSN: 09168532
• Web Site: http://www.jstage.jst.go.jp/article/transinf/E94.D/2/E94.D_2_371/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用不可