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.{{cite web | url=http://hssl.cs.jhu.edu/~randal/419/lectures/L15.ParallelIO.pdf | title=Parallel I/O | publisher=Johns Hopkins University | access-date=2016-03-25 | archive-date=2015-06-30 | archive-url=https://web.archive.org/web/20150630015051/http://hssl.cs.jhu.edu/~randal/419/lectures/L15.ParallelIO.pdf | url-status=dead }} It is a fundamental feature of operating systems.{{cite web | url=https://www.olcf.ornl.gov/wp-content/uploads/2011/10/Fall_IO.pdf | title=Introduction to Parallel I/O | publisher=Oak Ridge National Laboratory}}
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.{{cite web | url=http://www.cac.cornell.edu/education/training/ParallelMay2012/ParallelIOMay2012.pdf | title=Introduction: The Parallel I/O Stack | publisher=Cornell University}}{{cite web | url=https://www.tacc.utexas.edu/documents/13601/900558/MPI-IO-Final.pdf/eea9d7d3-4b81-471c-b244-41498070e35d | title=Introduction to Parallel I/O | publisher=The University of Texas at Austin | access-date=2016-03-25 | archive-date=2015-09-06 | archive-url=https://web.archive.org/web/20150906152916/https://www.tacc.utexas.edu/documents/13601/900558/MPI-IO-Final.pdf/eea9d7d3-4b81-471c-b244-41498070e35d | url-status=dead }}
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.{{cite web | url=http://www.scd.stfc.ac.uk//support/44958.aspx | title=Parallel I/O | publisher=Scientific Computing Department | access-date=2016-03-25 | archive-date=2016-04-11 | archive-url=https://web.archive.org/web/20160411160931/http://www.scd.stfc.ac.uk//support/44958.aspx | url-status=dead }} Parallel File System manages the single view, maintains logical space and provides access to data files.{{cite web | url=http://cs.lbl.gov/news-media/news/2014/a-comprehensive-look-at-high-performance-parallel-i-o/ | title=A Comprehensive Look at High Performance Parallel I/O | date=31 October 2014 | publisher=Berkeley Lab}}
=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.{{Cite web| title=Parallel I/O for High Performance Computing | url=http://calcul.math.cnrs.fr/Documents/Manifestations/CIRA2011/2011-01_haefele_parallel_IO-workshop_Lyon.pdf | archive-url=https://web.archive.org/web/20160419162030/http://calcul.math.cnrs.fr/Documents/Manifestations/CIRA2011/2011-01_haefele_parallel_IO-workshop_Lyon.pdf | archive-date=2016-04-19}} The caches are larger in Parallel I/O and shared through distributed memory systems.{{Cite web| title=Introduction to High Performance Parallel I/O | url=https://www.olcf.ornl.gov/wp-content/uploads/2013/05/OLCF-Data-Intro-IO-Gerber-FINAL.pdf | archive-url=https://web.archive.org/web/20160415075220/https://www.olcf.ornl.gov/wp-content/uploads/2013/05/OLCF-Data-Intro-IO-Gerber-FINAL.pdf | archive-date=2016-04-15}}{{Cite web | url=http://cs.lbl.gov/news-media/news/2014/a-comprehensive-look-at-high-performance-parallel-i-o/ | title=A Comprehensive Look at High Performance Parallel I/O| date=31 October 2014}}{{Cite web | url=https://hdfgroup.org/wp/2015/04/parallel-io-why-how-and-where-to-hdf5/ | title=Parallel I/O – Why, How, and Where to?| date=2015-04-09}}{{cite journal|author1=Teng Wang|author2=Kevin Vasko|author3=Zhuo Liu|author4=Hui Chen|author5=Weikuan Yu|title=Enhance parallel input/output with cross-bundle aggregation|journal=The International Journal of High Performance Computing Applications|volume=30|issue=2|pages=241–256|date=2016|doi=10.1177/1094342015618017|s2cid=12067366}}
=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.{{cite book | doi=10.1007/978-3-642-01970-8_9 | volume=5544 | pages=84–93| isbn=9783642019692 | date=2009-05-25 | last1=Laghave | first1=Nikhil | last2=Sosonkina | first2=Masha | last3=Maris | first3=Pieter | last4=Vary | first4=James P. | title=Computational Science – ICCS 2009 | chapter=Benefits of Parallel I/O in Ab Initio Nuclear Physics Calculations | series=Lecture Notes in Computer Science | s2cid=28279330 }}