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. It is a fundamental feature of operating systems.
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.
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. Parallel File System manages the single view, maintains logical space and provides access to data files.
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. The caches are larger in Parallel I/O and shared through distributed memory systems.
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.
- "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.
- "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.
|This computing article is a stub. You can help Wikipedia by expanding it.|