Comparative evaluation of overlap strategies with study of I/O overlap in MPI-IO

Christina M. Patrick, Seungwoo Son, Mahmut Kandemir

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Many scientific applications use parallel I/O to meet the low latency and high bandwidth I/O requirement. Among many available parallel I/O operations, collective I/O is one of the most popular methods when the storage layouts and access patterns of data do not match. The implementation of collective I/O typically involves disk I/O operations followed by interprocessor communications. Also, in many I/O-intensive applications, parallel I/O operations are usually followed by parallel computations. This paper presents a comparative study of different overlap strategies in parallel applications. We have experimented with four different overlap strategies 1) Overlapping I/O and communication; 2) Overlapping I/O and computation; 3) Overlapping computation and communication; and 4) Overlapping I/O, communication, and computation. All experiments have been conducted on a Linux Cluster and the performance results obtained are very encouraging. On an average, we have enhanced the performance of a generic collective read call by 38%, the MxM benchmark by 26%, and the FFT benchmark by 34%.

Original languageEnglish (US)
Pages (from-to)43-49
Number of pages7
JournalOperating Systems Review (ACM)
Volume42
Issue number6
DOIs
StatePublished - Oct 1 2008

Fingerprint

Communication
Fast Fourier transforms
Bandwidth
Experiments
Linux

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

@article{acb9cb0cbc8341a299531429b2d135d9,
title = "Comparative evaluation of overlap strategies with study of I/O overlap in MPI-IO",
abstract = "Many scientific applications use parallel I/O to meet the low latency and high bandwidth I/O requirement. Among many available parallel I/O operations, collective I/O is one of the most popular methods when the storage layouts and access patterns of data do not match. The implementation of collective I/O typically involves disk I/O operations followed by interprocessor communications. Also, in many I/O-intensive applications, parallel I/O operations are usually followed by parallel computations. This paper presents a comparative study of different overlap strategies in parallel applications. We have experimented with four different overlap strategies 1) Overlapping I/O and communication; 2) Overlapping I/O and computation; 3) Overlapping computation and communication; and 4) Overlapping I/O, communication, and computation. All experiments have been conducted on a Linux Cluster and the performance results obtained are very encouraging. On an average, we have enhanced the performance of a generic collective read call by 38{\%}, the MxM benchmark by 26{\%}, and the FFT benchmark by 34{\%}.",
author = "Patrick, {Christina M.} and Seungwoo Son and Mahmut Kandemir",
year = "2008",
month = "10",
day = "1",
doi = "10.1145/1453775.1453784",
language = "English (US)",
volume = "42",
pages = "43--49",
journal = "Operating Systems Review (ACM)",
issn = "0163-5980",
publisher = "Association for Computing Machinery (ACM)",
number = "6",

}

Comparative evaluation of overlap strategies with study of I/O overlap in MPI-IO. / Patrick, Christina M.; Son, Seungwoo; Kandemir, Mahmut.

In: Operating Systems Review (ACM), Vol. 42, No. 6, 01.10.2008, p. 43-49.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Comparative evaluation of overlap strategies with study of I/O overlap in MPI-IO

AU - Patrick, Christina M.

AU - Son, Seungwoo

AU - Kandemir, Mahmut

PY - 2008/10/1

Y1 - 2008/10/1

N2 - Many scientific applications use parallel I/O to meet the low latency and high bandwidth I/O requirement. Among many available parallel I/O operations, collective I/O is one of the most popular methods when the storage layouts and access patterns of data do not match. The implementation of collective I/O typically involves disk I/O operations followed by interprocessor communications. Also, in many I/O-intensive applications, parallel I/O operations are usually followed by parallel computations. This paper presents a comparative study of different overlap strategies in parallel applications. We have experimented with four different overlap strategies 1) Overlapping I/O and communication; 2) Overlapping I/O and computation; 3) Overlapping computation and communication; and 4) Overlapping I/O, communication, and computation. All experiments have been conducted on a Linux Cluster and the performance results obtained are very encouraging. On an average, we have enhanced the performance of a generic collective read call by 38%, the MxM benchmark by 26%, and the FFT benchmark by 34%.

AB - Many scientific applications use parallel I/O to meet the low latency and high bandwidth I/O requirement. Among many available parallel I/O operations, collective I/O is one of the most popular methods when the storage layouts and access patterns of data do not match. The implementation of collective I/O typically involves disk I/O operations followed by interprocessor communications. Also, in many I/O-intensive applications, parallel I/O operations are usually followed by parallel computations. This paper presents a comparative study of different overlap strategies in parallel applications. We have experimented with four different overlap strategies 1) Overlapping I/O and communication; 2) Overlapping I/O and computation; 3) Overlapping computation and communication; and 4) Overlapping I/O, communication, and computation. All experiments have been conducted on a Linux Cluster and the performance results obtained are very encouraging. On an average, we have enhanced the performance of a generic collective read call by 38%, the MxM benchmark by 26%, and the FFT benchmark by 34%.

UR - http://www.scopus.com/inward/record.url?scp=70449684261&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449684261&partnerID=8YFLogxK

U2 - 10.1145/1453775.1453784

DO - 10.1145/1453775.1453784

M3 - Article

VL - 42

SP - 43

EP - 49

JO - Operating Systems Review (ACM)

JF - Operating Systems Review (ACM)

SN - 0163-5980

IS - 6

ER -