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]
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.[11]
See also
References
- ↑ "Parallel I/O" (PDF). Johns Hopkins University.
- ↑ "Introduction to Parallel I/O" (PDF). Oak Ridge National Laboratory.
- ↑ "Introduction: The Parallel I/O Stack" (PDF). Cornell University.
- ↑ "Introduction to Parallel I/O" (PDF). The University of Texas at Austin.
- ↑ "Parallel I/O". Scientific Computing Department.
- ↑ "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
- ↑ https://www.olcf.ornl.gov/wp-content/uploads/2013/05/OLCF-Data-Intro-IO-Gerber-FINAL.pdf
- ↑ http://cs.lbl.gov/news-media/news/2014/a-comprehensive-look-at-high-performance-parallel-i-o/
- ↑ https://hdfgroup.org/wp/2015/04/parallel-io-why-how-and-where-to-hdf5/
- ↑ "Benefits of Parallel I/O in Ab Initio Nuclear Physics Calculations". Lecture Notes in Computer Science: 84–93. doi:10.1007/978-3-642-01970-8_9.