Parallel algorithm of 3D wave-packet decomposition of seismic data: implementation and optimization for GPU

Viktor Nikitin; Fredrik Andersson; Anton Duchkov

doi:10.1016/j.jocs.2012.08.011

Parallel algorithm of 3D wave-packet decomposition of seismic data: implementation and optimization for GPU

Viktor Nikitin, Fredrik Andersson, Anton Duchkov

Research output: Contribution to journal › Article › peer-review

Abstract

In this paper, we consider 3D wave-packet transform that is useful in 3D data processing. This transform is computationally intensive even though it has a computational complexity of O(N3 log N). Here we present its implementation on GPUs using NVIDIA CUDA technology. The code was tested on different types of graphical processors achieving the average speedup up to 46 times on Tesla M2050 compared to CPU sequential code. Also, we analyzed its scalability for several GPUs. The code was tested for processing synthetic seismic data set: data compression, de-noising, and interpolation.

Original language	English
Pages (from-to)	469-473
Journal	Journal of Computational Science
Volume	3
Issue number	6
DOIs	https://doi.org/10.1016/j.jocs.2012.08.011
Publication status	Published - 2012

Subject classification (UKÄ)

Mathematical Sciences

Free keywords

GPU
Wave-packet decomposition
Seismic processing

Access to Document

10.1016/j.jocs.2012.08.011

Cite this

@article{e6d7aa7e0ad14b51bba6951105dde6c2,

title = "Parallel algorithm of 3D wave-packet decomposition of seismic data: implementation and optimization for GPU",

abstract = "In this paper, we consider 3D wave-packet transform that is useful in 3D data processing. This transform is computationally intensive even though it has a computational complexity of O(N3 log N). Here we present its implementation on GPUs using NVIDIA CUDA technology. The code was tested on different types of graphical processors achieving the average speedup up to 46 times on Tesla M2050 compared to CPU sequential code. Also, we analyzed its scalability for several GPUs. The code was tested for processing synthetic seismic data set: data compression, de-noising, and interpolation.",

keywords = "GPU, Wave-packet decomposition, Seismic processing",

author = "Viktor Nikitin and Fredrik Andersson and Anton Duchkov",

year = "2012",

doi = "10.1016/j.jocs.2012.08.011",

language = "English",

volume = "3",

pages = "469--473",

journal = "Journal of Computational Science",

issn = "1877-7511",

publisher = "Elsevier",

number = "6",

}

TY - JOUR

T1 - Parallel algorithm of 3D wave-packet decomposition of seismic data: implementation and optimization for GPU

AU - Nikitin, Viktor

AU - Andersson, Fredrik

AU - Duchkov, Anton

PY - 2012

Y1 - 2012

N2 - In this paper, we consider 3D wave-packet transform that is useful in 3D data processing. This transform is computationally intensive even though it has a computational complexity of O(N3 log N). Here we present its implementation on GPUs using NVIDIA CUDA technology. The code was tested on different types of graphical processors achieving the average speedup up to 46 times on Tesla M2050 compared to CPU sequential code. Also, we analyzed its scalability for several GPUs. The code was tested for processing synthetic seismic data set: data compression, de-noising, and interpolation.

AB - In this paper, we consider 3D wave-packet transform that is useful in 3D data processing. This transform is computationally intensive even though it has a computational complexity of O(N3 log N). Here we present its implementation on GPUs using NVIDIA CUDA technology. The code was tested on different types of graphical processors achieving the average speedup up to 46 times on Tesla M2050 compared to CPU sequential code. Also, we analyzed its scalability for several GPUs. The code was tested for processing synthetic seismic data set: data compression, de-noising, and interpolation.

KW - GPU

KW - Wave-packet decomposition

KW - Seismic processing

U2 - 10.1016/j.jocs.2012.08.011

DO - 10.1016/j.jocs.2012.08.011

M3 - Article

SN - 1877-7511

VL - 3

SP - 469

EP - 473

JO - Journal of Computational Science

JF - Journal of Computational Science

IS - 6

ER -

Parallel algorithm of 3D wave-packet decomposition of seismic data: implementation and optimization for GPU

Abstract

Subject classification (UKÄ)

Free keywords

Access to Document

Fingerprint

Cite this