Performance Evaluation of Large-Scale Parallel Image Compositing on a T2K Open Supercomputer

Jorji Nonaka, Kenji Ono, Hideo Miyachi

Research output: Contribution to journalArticle

Abstract

This paper presents a performance evaluation of large-scale parallel image compositing on a T2K Open Supercomputer. Traditional image compositing algorithms were not primarily designed for exploiting the combined message passing and the shared address space parallelism provided by systems such as T2K Open Supercomputer. In this study, we investigate the <i>Binary-Swap</i> image compositing method because of its promising potential for scalability. We propose some improvements to the <i>Binary-Swap</i> method aiming to fully exploit the hybrid programming model. We obtained encouraging results from the performance evaluation conducted on <i>Todai Combined Cluster</i>, a T2K Open Supercomputer at the University of Tokyo. The proposed improvements have also shown a high potential to tackle the large-scale image compositing problem on leading-edge HPC systems where an ever increasing number of processing cores is involved.
Original languageEnglish
Pages (from-to)780-788
Number of pages9
JournalInformation and Media Technologies
Volume4
Issue number4
DOIs
Publication statusPublished - 2009

Fingerprint

Supercomputers
Binary images
Message passing
Scalability
Processing

Cite this

Performance Evaluation of Large-Scale Parallel Image Compositing on a T2K Open Supercomputer. / Nonaka, Jorji; Ono, Kenji; Miyachi, Hideo.

In: Information and Media Technologies, Vol. 4, No. 4, 2009, p. 780-788.

Research output: Contribution to journalArticle

@article{6f1ee8dc06704b8f82c8f0833cf29ef3,
title = "Performance Evaluation of Large-Scale Parallel Image Compositing on a T2K Open Supercomputer",
abstract = "This paper presents a performance evaluation of large-scale parallel image compositing on a T2K Open Supercomputer. Traditional image compositing algorithms were not primarily designed for exploiting the combined message passing and the shared address space parallelism provided by systems such as T2K Open Supercomputer. In this study, we investigate the Binary-Swap image compositing method because of its promising potential for scalability. We propose some improvements to the Binary-Swap method aiming to fully exploit the hybrid programming model. We obtained encouraging results from the performance evaluation conducted on Todai Combined Cluster, a T2K Open Supercomputer at the University of Tokyo. The proposed improvements have also shown a high potential to tackle the large-scale image compositing problem on leading-edge HPC systems where an ever increasing number of processing cores is involved.",
author = "Jorji Nonaka and Kenji Ono and Hideo Miyachi",
year = "2009",
doi = "10.11185/imt.4.780",
language = "English",
volume = "4",
pages = "780--788",
journal = "Information and Media Technologies",
publisher = "Information and Media Technologies Editorial Board",
number = "4",

}

TY - JOUR

T1 - Performance Evaluation of Large-Scale Parallel Image Compositing on a T2K Open Supercomputer

AU - Nonaka, Jorji

AU - Ono, Kenji

AU - Miyachi, Hideo

PY - 2009

Y1 - 2009

N2 - This paper presents a performance evaluation of large-scale parallel image compositing on a T2K Open Supercomputer. Traditional image compositing algorithms were not primarily designed for exploiting the combined message passing and the shared address space parallelism provided by systems such as T2K Open Supercomputer. In this study, we investigate the Binary-Swap image compositing method because of its promising potential for scalability. We propose some improvements to the Binary-Swap method aiming to fully exploit the hybrid programming model. We obtained encouraging results from the performance evaluation conducted on Todai Combined Cluster, a T2K Open Supercomputer at the University of Tokyo. The proposed improvements have also shown a high potential to tackle the large-scale image compositing problem on leading-edge HPC systems where an ever increasing number of processing cores is involved.

AB - This paper presents a performance evaluation of large-scale parallel image compositing on a T2K Open Supercomputer. Traditional image compositing algorithms were not primarily designed for exploiting the combined message passing and the shared address space parallelism provided by systems such as T2K Open Supercomputer. In this study, we investigate the Binary-Swap image compositing method because of its promising potential for scalability. We propose some improvements to the Binary-Swap method aiming to fully exploit the hybrid programming model. We obtained encouraging results from the performance evaluation conducted on Todai Combined Cluster, a T2K Open Supercomputer at the University of Tokyo. The proposed improvements have also shown a high potential to tackle the large-scale image compositing problem on leading-edge HPC systems where an ever increasing number of processing cores is involved.

U2 - 10.11185/imt.4.780

DO - 10.11185/imt.4.780

M3 - Article

VL - 4

SP - 780

EP - 788

JO - Information and Media Technologies

JF - Information and Media Technologies

IS - 4

ER -