What happens if I create a parpool with 64 workers even when MATLAB is restricted by OS to just use 16 cores?

I submitted a job to our internal LSF cluster requesting for a 64-core "xterm" session instance. After my job got processed, I received the requested "xterm" session. I then opened a VNC connection to this session through which I access MATLAB. 

Problem:

When I execute the following command on my MATLAB Command Window, I see that MATLAB is restricted to only use 16 cores:

>> feature('numcores')

MATLAB detected: 64 physical cores.

MATLAB detected: 128 logical cores.

MATLAB was assigned: 16 logical cores by the OS.

MATLAB is using: 16 logical cores.

MATLAB is not using all logical cores because hyper-threading is enabled.

MATLAB is not using all logical cores because Operating System restricted the number of cores to: 16.


ans =

16

Questions:

1. Is there a way to force MATLAB to use all the available cores on the machine?
2. Can I assume that if I create a "parpool" of 64 workers, they will use all the 64 cores of the machine not just the 16 allocated to MATLAB process?

Answer 1

[MathWorks Support Team]

1. The given output indicates that the OS is restricting MATLAB from using all available cores on the machine. As this is a restriction from the OS, MATLAB cannot control this behavior. However, you can remove any restrictions by updating your environment (docker/ cluster/ scheduler) settings that are restricting the number of cores allocated to a process.
2. Since the MATLAB process is restricted to use only 16 cores, a "parpool" of 64 workers will only be able to see those 16 cores that are allocated to MATLAB process.