Accelerating large-scale simulation of seismic wave propagation by multi-GPUs and three-dimensional domain decomposition

Taro Okamoto, Hiroshi Takenaka, Takeshi Nakamura, Takayuki Aoki

Research output: Chapter in Book/Report/Conference proceedingChapter

8 Citations (Scopus)

Abstract

We adopted the GPU (graphics processing unit) to accelerate the large-scale finite-difference simulation of seismic wave propagation. We describe the main part of our implementation: the memory optimization, the three-dimensional domain decomposition, and overlapping communication and computation. With our GPU program, we achieved a very high single-precision performance of about 61 TFlops by using 1,200 GPUs and 1.5 TB of total memory, and a scalability nearly proportional to the number of GPUs on TSUBAME–2.0, the recently installed GPU supercomputer in Tokyo Institute of Technology, Japan. In a realistic application by using 400 GPUs, only a wall clock time of 2,068 s (including the times for the overhead of snapshot output) was required for a complex structure model with more than 13 billion unit cells and 20,000 time steps. We therefore conclude that GPU computing for large-scale simulation of seismic wave propagation is a promising approach.

Original languageEnglish
Title of host publicationLecture Notes in Earth System Sciences
PublisherSpringer International Publishing
Pages375-389
Number of pages15
Edition9783642164040
DOIs
Publication statusPublished - Jan 1 2013
Externally publishedYes

Publication series

NameLecture Notes in Earth System Sciences
Number9783642164040
ISSN (Print)2193-858X
ISSN (Electronic)2193-8571

Fingerprint

Seismic waves
seismic wave
Wave propagation
wave propagation
decomposition
Decomposition
simulation
communication
Data storage equipment
Supercomputers
Model structures
Graphics processing unit
Scalability
Clocks
Communication

ASJC Scopus subject areas

  • Computers in Earth Sciences
  • Earth and Planetary Sciences(all)

Cite this

Okamoto, T., Takenaka, H., Nakamura, T., & Aoki, T. (2013). Accelerating large-scale simulation of seismic wave propagation by multi-GPUs and three-dimensional domain decomposition. In Lecture Notes in Earth System Sciences (9783642164040 ed., pp. 375-389). (Lecture Notes in Earth System Sciences; No. 9783642164040). Springer International Publishing. https://doi.org/10.1007/978-3-642-16405-7_24

Accelerating large-scale simulation of seismic wave propagation by multi-GPUs and three-dimensional domain decomposition. / Okamoto, Taro; Takenaka, Hiroshi; Nakamura, Takeshi; Aoki, Takayuki.

Lecture Notes in Earth System Sciences. 9783642164040. ed. Springer International Publishing, 2013. p. 375-389 (Lecture Notes in Earth System Sciences; No. 9783642164040).

Research output: Chapter in Book/Report/Conference proceedingChapter

Okamoto, T, Takenaka, H, Nakamura, T & Aoki, T 2013, Accelerating large-scale simulation of seismic wave propagation by multi-GPUs and three-dimensional domain decomposition. in Lecture Notes in Earth System Sciences. 9783642164040 edn, Lecture Notes in Earth System Sciences, no. 9783642164040, Springer International Publishing, pp. 375-389. https://doi.org/10.1007/978-3-642-16405-7_24
Okamoto T, Takenaka H, Nakamura T, Aoki T. Accelerating large-scale simulation of seismic wave propagation by multi-GPUs and three-dimensional domain decomposition. In Lecture Notes in Earth System Sciences. 9783642164040 ed. Springer International Publishing. 2013. p. 375-389. (Lecture Notes in Earth System Sciences; 9783642164040). https://doi.org/10.1007/978-3-642-16405-7_24
Okamoto, Taro ; Takenaka, Hiroshi ; Nakamura, Takeshi ; Aoki, Takayuki. / Accelerating large-scale simulation of seismic wave propagation by multi-GPUs and three-dimensional domain decomposition. Lecture Notes in Earth System Sciences. 9783642164040. ed. Springer International Publishing, 2013. pp. 375-389 (Lecture Notes in Earth System Sciences; 9783642164040).
@inbook{631c285dbb9e4e248f836242ade2424a,
title = "Accelerating large-scale simulation of seismic wave propagation by multi-GPUs and three-dimensional domain decomposition",
abstract = "We adopted the GPU (graphics processing unit) to accelerate the large-scale finite-difference simulation of seismic wave propagation. We describe the main part of our implementation: the memory optimization, the three-dimensional domain decomposition, and overlapping communication and computation. With our GPU program, we achieved a very high single-precision performance of about 61 TFlops by using 1,200 GPUs and 1.5 TB of total memory, and a scalability nearly proportional to the number of GPUs on TSUBAME–2.0, the recently installed GPU supercomputer in Tokyo Institute of Technology, Japan. In a realistic application by using 400 GPUs, only a wall clock time of 2,068 s (including the times for the overhead of snapshot output) was required for a complex structure model with more than 13 billion unit cells and 20,000 time steps. We therefore conclude that GPU computing for large-scale simulation of seismic wave propagation is a promising approach.",
author = "Taro Okamoto and Hiroshi Takenaka and Takeshi Nakamura and Takayuki Aoki",
year = "2013",
month = "1",
day = "1",
doi = "10.1007/978-3-642-16405-7_24",
language = "English",
series = "Lecture Notes in Earth System Sciences",
publisher = "Springer International Publishing",
number = "9783642164040",
pages = "375--389",
booktitle = "Lecture Notes in Earth System Sciences",
edition = "9783642164040",

}

TY - CHAP

T1 - Accelerating large-scale simulation of seismic wave propagation by multi-GPUs and three-dimensional domain decomposition

AU - Okamoto, Taro

AU - Takenaka, Hiroshi

AU - Nakamura, Takeshi

AU - Aoki, Takayuki

PY - 2013/1/1

Y1 - 2013/1/1

N2 - We adopted the GPU (graphics processing unit) to accelerate the large-scale finite-difference simulation of seismic wave propagation. We describe the main part of our implementation: the memory optimization, the three-dimensional domain decomposition, and overlapping communication and computation. With our GPU program, we achieved a very high single-precision performance of about 61 TFlops by using 1,200 GPUs and 1.5 TB of total memory, and a scalability nearly proportional to the number of GPUs on TSUBAME–2.0, the recently installed GPU supercomputer in Tokyo Institute of Technology, Japan. In a realistic application by using 400 GPUs, only a wall clock time of 2,068 s (including the times for the overhead of snapshot output) was required for a complex structure model with more than 13 billion unit cells and 20,000 time steps. We therefore conclude that GPU computing for large-scale simulation of seismic wave propagation is a promising approach.

AB - We adopted the GPU (graphics processing unit) to accelerate the large-scale finite-difference simulation of seismic wave propagation. We describe the main part of our implementation: the memory optimization, the three-dimensional domain decomposition, and overlapping communication and computation. With our GPU program, we achieved a very high single-precision performance of about 61 TFlops by using 1,200 GPUs and 1.5 TB of total memory, and a scalability nearly proportional to the number of GPUs on TSUBAME–2.0, the recently installed GPU supercomputer in Tokyo Institute of Technology, Japan. In a realistic application by using 400 GPUs, only a wall clock time of 2,068 s (including the times for the overhead of snapshot output) was required for a complex structure model with more than 13 billion unit cells and 20,000 time steps. We therefore conclude that GPU computing for large-scale simulation of seismic wave propagation is a promising approach.

UR - http://www.scopus.com/inward/record.url?scp=84990312998&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84990312998&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-16405-7_24

DO - 10.1007/978-3-642-16405-7_24

M3 - Chapter

AN - SCOPUS:84990312998

T3 - Lecture Notes in Earth System Sciences

SP - 375

EP - 389

BT - Lecture Notes in Earth System Sciences

PB - Springer International Publishing

ER -