Parallel I/O

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search

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[edit]

Scientific computing[edit]

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[edit]

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[edit]

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[edit]

References[edit]

  1. ^ "Parallel I/O" (PDF). Johns Hopkins University.
  2. ^ "Introduction to Parallel I/O" (PDF). Oak Ridge National Laboratory.
  3. ^ "Introduction: The Parallel I/O Stack" (PDF). Cornell University.
  4. ^ "Introduction to Parallel I/O". The University of Texas at Austin.
  5. ^ "Parallel I/O". Scientific Computing Department.
  6. ^ "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. ^ http://cs.lbl.gov/news-media/news/2014/a-comprehensive-look-at-high-performance-parallel-i-o/
  10. ^ https://hdfgroup.org/wp/2015/04/parallel-io-why-how-and-where-to-hdf5/
  11. ^ Teng Wang; Kevin Vasko; Zhuo Liu; Hui Chen; Weikuan Yu (2016). "Enhance parallel input/output with cross-bundle aggregation". The International Journal of High Performance Computing Applications. 30 (2): 241–256.
  12. ^ "Benefits of Parallel I/O in Ab Initio Nuclear Physics Calculations". Lecture Notes in Computer Science: 84–93. doi:10.1007/978-3-642-01970-8_9.