Parallel I/O

From Wikipedia, the free encyclopedia
Jump to: navigation, search

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.


Scientific computing[edit]

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]


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]


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[edit]