Parallel I/O in a computer enables simultaneous input/output operations, such as outputting to storage and display devices at once, and is a key feature of modern operating systems. A common example is parallel writing to disk arrays like RAID, where data is distributed across multiple disks to increase write speeds. Parallel access methods also include advanced file systems like the Parallel Virtual File System, Lustre, and GFS, which optimize data handling by leveraging concurrent operations for improved performance and scalability.
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.891011
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. https://web.archive.org/web/20150630015051/http://hssl.cs.jhu.edu/~randal/419/lectures/L15.ParallelIO.pdf ↩
"Introduction to Parallel I/O" (PDF). Oak Ridge National Laboratory. https://www.olcf.ornl.gov/wp-content/uploads/2011/10/Fall_IO.pdf ↩
"Introduction: The Parallel I/O Stack" (PDF). Cornell University. http://www.cac.cornell.edu/education/training/ParallelMay2012/ParallelIOMay2012.pdf ↩
"Introduction to Parallel I/O". The University of Texas at Austin. Archived from the original on 2015-09-06. Retrieved 2016-03-25. https://web.archive.org/web/20150906152916/https://www.tacc.utexas.edu/documents/13601/900558/MPI-IO-Final.pdf/eea9d7d3-4b81-471c-b244-41498070e35d ↩
"Parallel I/O". Scientific Computing Department. Archived from the original on 2016-04-11. Retrieved 2016-03-25. https://web.archive.org/web/20160411160931/http://www.scd.stfc.ac.uk//support/44958.aspx ↩
"A Comprehensive Look at High Performance Parallel I/O". Berkeley Lab. 31 October 2014. http://cs.lbl.gov/news-media/news/2014/a-comprehensive-look-at-high-performance-parallel-i-o/ ↩
"Parallel I/O for High Performance Computing" (PDF). Archived from the original (PDF) on 2016-04-19. https://web.archive.org/web/20160419162030/http://calcul.math.cnrs.fr/Documents/Manifestations/CIRA2011/2011-01_haefele_parallel_IO-workshop_Lyon.pdf ↩
"Introduction to High Performance Parallel I/O" (PDF). Archived from the original (PDF) on 2016-04-15. https://web.archive.org/web/20160415075220/https://www.olcf.ornl.gov/wp-content/uploads/2013/05/OLCF-Data-Intro-IO-Gerber-FINAL.pdf ↩
"A Comprehensive Look at High Performance Parallel I/O". 31 October 2014. http://cs.lbl.gov/news-media/news/2014/a-comprehensive-look-at-high-performance-parallel-i-o/ ↩
"Parallel I/O – Why, How, and Where to?". 2015-04-09. https://hdfgroup.org/wp/2015/04/parallel-io-why-how-and-where-to-hdf5/ ↩
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. /wiki/Doi_(identifier) ↩
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. 9783642019692 ↩