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
References
- ^ "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. |
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
References
- ^ "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. |