Scheduler Support in Parallel Computing Toolbox and MATLAB Parallel Server

The scheduler interface provided by MathWorks parallel computing products is at the software level, providing engineers and scientists an interface to submit jobs to computation resources without having to be concerned with differences in operating systems, environments, and schedulers. The infrastructure allows administrators to integrate MathWorks parallel computing products with existing scheduler environments at the application layer.

MATLAB Parallel Server™ includes a MATLAB^® job scheduler and support for other schedulers. See the following table for details.

Scheduler	Out-of-the-box support	Plugin scripts and resources available on GitHub	Additional comments
MATLAB job scheduler	View documentation		Included with MATLAB Parallel Server
Slurm	View documentation	View repository
PBS family	View documentation	View repository	Supports PBS Professional^®, OpenPBS^®, and TORQUE
Grid Engine family	View documentation	View repository	Supports Univa, Altair^®, and others
IBM^® Spectrum LSF Suite	View documentation	View repository
Microsoft^® HPC Pack	View documentation*		Customizable via job templates
AWS^® Batch		View repository
HTCondor™	View documentation	View repository
Kubernetes	View documentation	View repository
Other schedulers	View documentation		Implement with generic scheduler interface

*Requires: 1) Shared file system between desktop and cluster, and 2) Pre-existing access to cluster submission tools from the desktop.