Technically, gang scheduling is based on a data structure called the Ousterhout matrix.

A specific algorithm is known as gang scheduling.

Gang scheduling is a stricter variant of coscheduling that disallows fragments completely.

Gang scheduling is stricter than coscheduling.

Preemptive and gang scheduling (time-slicing of parallel jobs)

Future work will include porting pserver to the AP3000 and modifying aprund as necessary to support our gang scheduling scheme.

In computer science, gang scheduling is a scheduling algorithm for parallel systems that schedules related threads or processes to run simultaneously on different processors.

Gang scheduling was implemented and used in production mode on several parallel machines, most notably the Connection Machine CM-5.

Currently, parallel programs must include the synchronising cell (cell 0) in the configuration in order for the gang scheduling mechanism to function.

However the use of gang scheduling under AP/Linux allows for efficient executions of several parallel programs using polling.

Gang scheduling is used so that if two or more threads or processes communicate with each other, they will all be ready to communicate at the same time.

Previous gang scheduling implementations on AP/Linux relied on having one node as a master node.

Currently this is only used by gang scheduling and task synchronisation code, but it is expected that these functions will be used extensively as the kernels become more tightly integrated.

Although true gang scheduling is not currently provided, PSE applications are able to execute at elevated execution priority using the -priority command-line option and gain a scheduling advantage over other processes in the system.

Another interesting possibility would be to adapt some of the scheduling code developed by Walsh et al. as described in chapter 2 for use inside aprund, to provide gang scheduling for parallel programs on the AP3000.

When processors are over-subscribed and gang scheduling is not used within a group of processes or threads which communicate with each other, it can lead to situations where each communication event suffers the overhead of a context switch.