Spatial Information Research

Korea Spatial Information Society (대한공간정보학회)
권호 표지
DOI QR코드

DOI QR Code

A Parallel Processing Method for Partial Nodes in R*-tree Using GPU

GPU를 활용한 R*-tree에서의 부분 노드 병렬 처리 방법

  • Kim, Seong (Dept. of Computer Engneering, Kumoh National Institute of Technology) ;
  • Oh, Byoung-Woo (Dept. of Computer Engneering, Kumoh National Institute of Technology)
  • Received : 2012.12.03
  • Accepted : 2012.12.21
  • Published : 2012.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The R*-tree manages hierarchical nodes for efficient access of spatial data. We propose a method that maintains partial nodes of R*-tree in the GPU memory to improve efficiency using parallel processing. The proposed method attempts to load as many nodes as possible to the GPU memory. The new nodes are inserted to manage the rest of R*-tree nodes in the main memory. The experimental result shows that the proposed method is more efficient than the main memory based R*-tree.

공간 데이터 처리는 GIS, 텔레매틱스 등 광범위한 분야에서 널리 사용되고 있다. 그러나 현재 사용되고 있는 공간 데이터 질의 처리 기법은 CPU를 사용하여 순차적으로 질의 처리를 수행하므로 질의 처리 시간이 상대적으로 오래 걸린다는 단점이 존재한다. 그러나 공간 데이터 질의 처리를 병렬로 수행했을 때 처리 시간을 줄이는 것이 가능하다. 따라서 본 연구에서는 GPU를 활용하여 공간 데이터 질의 처리를 병렬로 수행하는 연구를 진행한다. 또한, CPU를 이용하여 질의 처리를 수행한 결과와 비교하여 속도 향상 정도에 대한 결과를 제시한다.

Keywords

References

  1. AMD, 2011, "AMD Accelerated Parallel Processing OpenCL Programming Guide (Version 1.3f)".
  2. Antonin Guttman, 1984, "R-trees: a dynamic index structure for spatial searching", SIGMOD '84: Proceedings of the 1984 ACM SIGMOD international conference on Management of data, 14(2):47-57.
  3. BoSeon Yu, 2010, "Parallel Range Query processing on R-tree with Graphics Processing Units", pp. 1-32, Inha University.
  4. BoSeon Yu, Hyunduk Kim, Wonik Choi, Dongseop Kwon, 2011, "Parallel Range Query processing on R-tree with Graphics Processing Units ", Journal of Korea Multimedia Society, 14(5):669-680. https://doi.org/10.9717/kmms.2011.14.5.669
  5. Byoung-Woo Oh, 2008, "Efficient Spatial Index for Mobile Software", The Journal of GIS Association of Korea, 16(1):113-127.
  6. Byoung-Woo Oh, 2012, "A Parallel Access Method for Spatial Data Using GPU", International Journal on Computer Science and Engineering(IJCSE), 4(3):492-500.
  7. GPGPU, 2012, General-Purpose Computation on Graphics Hardware, Accessed June 7. http://www.gpgpu.org
  8. Jae-Il Lee, Byoung-Woo Oh, 2009, "An Efficient Technique for Processing of Spatial Data Using GPU", The Journal of GIS Association of Korea, 17(3):371-379.
  9. Mincheol Kim, Wonik Choi, 2011, "Acceleration of Range Query in R-tree Using GPU Parallel Processing", Journal of KIISE : Korea Computer Congress 2011, 38(1):37-40.
  10. Mincheol Kim, Wonik Choi, 2011, "GPU Sensitive R-tree for Efficient Parallel Processing of Range Queries", Journal of KIISE : Autumn Conference 2011, 38(2):61-64.
  11. Norbert Beckmann, Hans-Peter Kriegel, Ralf Schneider, Bernhard Seeger, 1990, "The R*-tree: an efficient and robust access method for points and rectangles", SIGMOD '90: Proceedings of the 1990 ACM SIGMOD international conference on Management of data, 19(2):322-331.
  12. NVIDIA, 2012, "NVIDIA $CUDA^{TM}$ C Programming Guide (Version 4.2)".

Cited by

  1. A Parallel Processing Technique for Large Spatial Data vol.23, pp.2, 2012, https://doi.org/10.12672/ksis.2015.23.2.001
  2. Real-time object motion estimation based on frequency domain matching from a single camera vol.24, pp.4, 2012, https://doi.org/10.1007/s41324-016-0043-9