MATLAB Parallel Server
Perform MATLAB and Simulink computations on clusters and clouds
MATLAB Parallel Server™ lets you scale MATLAB® programs and Simulink® simulations to clusters and clouds. You can prototype your programs and simulations on the desktop and then run them on clusters and clouds without recoding. MATLAB Parallel Server supports batch jobs, interactive parallel computations, and distributed computations with large matrices.
All cluster-side licensing is handled by MATLAB Parallel Server. Your desktop license profile is dynamically enabled on the cluster, so you do not need to supply MATLAB licenses for the cluster. The licensing model includes features to support unlimited scaling.
MATLAB Parallel Server runs your programs and simulations as scheduled applications on your cluster. You can use the MATLAB optimized scheduler provided with MATLAB Parallel Server or your own scheduler. A plugin framework enables direct communication with popular cluster scheduler submission clients.
Prior to R2019a, MATLAB Parallel Server was called MATLAB Distributed Computing Server.
Write Code Once, and Use It in Multiple Environments
Prototype and debug applications on the desktop with Parallel Computing Toolbox™, and easily scale to clusters or clouds without recoding. Develop interactively and move to production with batch workflows.
Run on Multiple Machines Without Algorithm Changes
Develop a prototype on your desktop, and scale to a compute cluster without recoding. Access different execution environments from your desktop just by changing your cluster profile.
Access CPUs and GPUs on Centralized Resources
Take advantage of high-end hardware in your organization’s cluster without leaving the MATLAB desktop environment.
Scale Up Computations
Run compute-intensive MATLAB applications and Simulink models on compute clusters and clouds. MATLAB Parallel Server supports batch processing, parallel applications, GPU computing, and distributed memory.
Automate Management of Multiple Simulink Simulations
Easily set up multiple runs and parameter sweeps, manage model dependencies and build folders, and transfer base workspace variables to cluster processes. Use the Simulation Manager user interface to visualize and manage multiple runs of Simulink models on a cluster.
Process Big Data from Windows, Mac, or Linux
Use the same MATLAB analytics on small or large volumes of data. From your Windows®, Mac®, or Linux® desktop, you can process big data on Spark™ enabled Hadoop® clusters or on traditional clusters with standard file systems.
Overcome Memory Barriers
Execute calculations that won’t fit in the memory of a single machine without needing to recode your algorithm or use a shared-memory architecture.
Manage Any Size Cluster with a Single License
End users are automatically licensed on the cluster for the products they use on the desktop. The cluster requires only a MATLAB Parallel Server license.
Use Your Desktop Toolboxes on the Cluster
MATLAB Parallel Server is the only license required on the cluster. Dynamic licensing enables each user’s specific desktop license profile on the cluster.
Use Your Existing Hardware and Infrastructure
Create a cluster from a few dedicated machines and manage jobs with MATLAB Job Scheduler, or integrate with your existing cluster and manage jobs with your third-party scheduler. Users can manage their jobs without leaving MATLAB.
Scale Applications to the Cloud
Integrate with public and private clouds. Access specialized and more powerful hardware in the cloud. Use preconfigured options from both MathWorks and MathWorks hosting providers, or build the infrastructure yourself.
See MATLAB Parallel Server in Action
Common Job Schedulers Performance
Improved performance of vectorized task creation for local and third-party schedulers
MATLAB Parallel Server with the MATLAB Job Scheduler now supports clusters up to 2000 workers; support for large parallel pools remains at 1024 workers
Personal Cloud Clusters
Set Cloud Center clusters for personal use
Batch Jobs Documentation
Explore batch workflows with new examples such as Run Batch Job and Access Files from Workers
Distributed Array Functionality
Use new and enhanced distributed array functionality, such as decomposition, mink,
topkrows, and more
NVIDIA CUDA Toolkit 10.1 Support
Update to NVIDIA CUDA Toolkit 10.1
gpuArray Data Loading on CPU
gpuArray data on CPU, when no GPU is present
Enhanced GPU Functionality for Sparse
Use new and enhanced
gpuArray functions, such as sparse diag, sparse trace, and others
mexcuda functions without installing the CUDA toolkit