Parallel I/O Explained

Parallel I/O, in the context of a computer, means the performance of multiple input/output operations at the same time, for instance simultaneously outputs to storage devices and display devices.[1] It is a fundamental feature of operating systems.[2]

One particular instance is parallel writing of data to disk; when file data is spread across multiple disks, for example in a RAID array, one can store multiple parts of the data at the same time, thereby achieving higher write speeds than with a single device.[3] [4]

Other ways of parallel access to data include: Parallel Virtual File System, Lustre, GFS etc.

Features

Scientific computing

It is used for scientific computing and not for databases. It breaks up support into multiple layers including High level I/O library, Middleware layer and Parallel file system.[5] Parallel File System manages the single view, maintains logical space and provides access to data files.[6]

Storage

A single file may be stripped across one or more object storage target, which increases the bandwidth while accessing the file and available disk space.[7] The caches are larger in Parallel I/O and shared through distributed memory systems.[8] [9] [10] [11]

Breakthroughs

Companies have been running Parallel I/O on their servers to achieve results with regard to price and performance. Parallel processing is especially critical for scientific calculations where applications are not only CPU but also are I/O bound.[12]

See also

Notes and References

  1. Web site: Parallel I/O . . 2016-03-25 . 2015-06-30 . https://web.archive.org/web/20150630015051/http://hssl.cs.jhu.edu/~randal/419/lectures/L15.ParallelIO.pdf . dead .
  2. Web site: Introduction to Parallel I/O . Oak Ridge National Laboratory.
  3. Web site: Introduction: The Parallel I/O Stack . Cornell University.
  4. Web site: Introduction to Parallel I/O . The University of Texas at Austin.
  5. Web site: Parallel I/O . Scientific Computing Department . 2016-03-25 . 2016-04-11 . https://web.archive.org/web/20160411160931/http://www.scd.stfc.ac.uk//support/44958.aspx . dead .
  6. Web site: A Comprehensive Look at High Performance Parallel I/O . Berkeley Lab.
  7. http://calcul.math.cnrs.fr/Documents/Manifestations/CIRA2011/2011-01_haefele_parallel_IO-workshop_Lyon.pdf
  8. https://www.olcf.ornl.gov/wp-content/uploads/2013/05/OLCF-Data-Intro-IO-Gerber-FINAL.pdf
  9. Web site: A Comprehensive Look at High Performance Parallel I/O.
  10. Web site: Parallel I/O – Why, How, and Where to?. 2015-04-09.
  11. Teng Wang. Kevin Vasko. Zhuo Liu. Hui Chen. Weikuan Yu. Enhance parallel input/output with cross-bundle aggregation. The International Journal of High Performance Computing Applications. 30. 2. 241–256. 2016. 10.1177/1094342015618017. 12067366.
  12. Book: 10.1007/978-3-642-01970-8_9 . 5544 . 84–93. 9783642019692 . 2009-05-25 . Laghave . Nikhil . Sosonkina . Masha . Maris . Pieter . Vary . James P. . Computational Science – ICCS 2009 . Benefits of Parallel I/O in Ab Initio Nuclear Physics Calculations . Lecture Notes in Computer Science . 28279330 .

This article is licensed under the GNU Free Documentation License. It uses material from the Wikipedia article "Parallel I/O".

Except where otherwise indicated, Everything.Explained.Today is © Copyright 2009-2024, A B Cryer, All Rights Reserved. Cookie policy.