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
- ^ "Parallel I/O" (PDF). Johns Hopkins University. Archived from the original (PDF) on 2015-06-30. Retrieved 2016-03-25.
- ^ "Introduction to Parallel I/O" (PDF). Oak Ridge National Laboratory.
- ^ "Introduction: The Parallel I/O Stack" (PDF). Cornell University.
- ^ "Introduction to Parallel I/O". The University of Texas at Austin.
- ^ "Parallel I/O". Scientific Computing Department. Archived from the original on 2016-04-11. Retrieved 2016-03-25.
- ^ "A Comprehensive Look at High Performance Parallel I/O". Berkeley Lab.
- ^ http://calcul.math.cnrs.fr/Documents/Manifestations/CIRA2011/2011-01_haefele_parallel_IO-workshop_Lyon.pdf [bare URL PDF]
- ^ https://www.olcf.ornl.gov/wp-content/uploads/2013/05/OLCF-Data-Intro-IO-Gerber-FINAL.pdf [bare URL PDF]
- ^ "A Comprehensive Look at High Performance Parallel I/O".
- ^ "Parallel I/O – Why, How, and Where to?". 2015-04-09.
- ^ 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. doi:10.1177/1094342015618017. S2CID 12067366.
- ^ Laghave, Nikhil; Sosonkina, Masha; Maris, Pieter; Vary, James P. (2009-05-25). "Benefits of Parallel I/O in Ab Initio Nuclear Physics Calculations". Computational Science – ICCS 2009. Lecture Notes in Computer Science. Vol. 5544. pp. 84–93. doi:10.1007/978-3-642-01970-8_9. ISBN 9783642019692. S2CID 28279330.
 | This computing article is a stub. You can help Wikipedia by expanding it. |