Acceleration of the Fast Multipole Method on FPGA Devices
Summary :
The fast multipole method (FMM) for N-body simulations is attracting much attention since it requires minimal communication between computing nodes. We implemented hardware pipelines specialized for the FMM on an FPGA device, the GRAPE-9. An N-body simulation with 1.6×107 particles ran 16 times faster than that on a CPU. Moreover the particle-to-particle stage of the FMM on the GRAPE-9 executed 2.5 times faster than on a GPU in a limited case.
- Publication
- IEICE TRANSACTIONS on Information Vol.E98-D No.2 pp.309-312
- Publication Date
- 2015/02/01
- Publicized
- 2014/11/19
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2014RCL0002
- Type of Manuscript
- Special Section LETTER (Special Section on Reconfigurable Systems)
- Category
- Application
Authors
Hitoshi UKAWA
University of Tsukuba
Tetsu NARUMI
University of Electro-Communications
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Hitoshi UKAWA, Tetsu NARUMI, "Acceleration of the Fast Multipole Method on FPGA Devices" in IEICE TRANSACTIONS on Information,
vol. E98-D, no. 2, pp. 309-312, February 2015, doi: 10.1587/transinf.2014RCL0002.
Abstract: The fast multipole method (FMM) for N-body simulations is attracting much attention since it requires minimal communication between computing nodes. We implemented hardware pipelines specialized for the FMM on an FPGA device, the GRAPE-9. An N-body simulation with 1.6×107 particles ran 16 times faster than that on a CPU. Moreover the particle-to-particle stage of the FMM on the GRAPE-9 executed 2.5 times faster than on a GPU in a limited case.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014RCL0002/_p
Copy
@ARTICLE{e98-d_2_309,
author={Hitoshi UKAWA, Tetsu NARUMI, },
journal={IEICE TRANSACTIONS on Information},
title={Acceleration of the Fast Multipole Method on FPGA Devices},
year={2015},
volume={E98-D},
number={2},
pages={309-312},
abstract={The fast multipole method (FMM) for N-body simulations is attracting much attention since it requires minimal communication between computing nodes. We implemented hardware pipelines specialized for the FMM on an FPGA device, the GRAPE-9. An N-body simulation with 1.6×107 particles ran 16 times faster than that on a CPU. Moreover the particle-to-particle stage of the FMM on the GRAPE-9 executed 2.5 times faster than on a GPU in a limited case.},
keywords={},
doi={10.1587/transinf.2014RCL0002},
ISSN={1745-1361},
month={February},}
Copy
TY - JOUR
TI - Acceleration of the Fast Multipole Method on FPGA Devices
T2 - IEICE TRANSACTIONS on Information
SP - 309
EP - 312
AU - Hitoshi UKAWA
AU - Tetsu NARUMI
PY - 2015
DO - 10.1587/transinf.2014RCL0002
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2015
AB - The fast multipole method (FMM) for N-body simulations is attracting much attention since it requires minimal communication between computing nodes. We implemented hardware pipelines specialized for the FMM on an FPGA device, the GRAPE-9. An N-body simulation with 1.6×107 particles ran 16 times faster than that on a CPU. Moreover the particle-to-particle stage of the FMM on the GRAPE-9 executed 2.5 times faster than on a GPU in a limited case.
ER -
English
