Parallel I/O

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

• Converged infrastructure
• Dynamic infrastructure

References

1. "Parallel I/O" (PDF). Johns Hopkins University. Archived from the original (PDF) on 2015-06-30. Retrieved 2016-03-25.
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. Archived from the original on 2015-09-06. Retrieved 2016-03-25.
5. "Parallel I/O". Scientific Computing Department. Archived from the original on 2016-04-11. Retrieved 2016-03-25.
6. "A Comprehensive Look at High Performance Parallel I/O". Berkeley Lab. 31 October 2014.
7. "Parallel I/O for High Performance Computing" (PDF). Archived from the original (PDF) on 2016-04-19.
8. "Introduction to High Performance Parallel I/O" (PDF). Archived from the original (PDF) on 2016-04-15.
9. "A Comprehensive Look at High Performance Parallel I/O". 31 October 2014.
10. "Parallel I/O – Why, How, and Where to?". 2015-04-09.
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. doi:10.1177/1094342015618017. S2CID   12067366.
12. 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.