Hi,

Is there a way to submit a wedge TOP to simulate across multiple machines so that each simulation is happening on a single farm machine.

For example

- I have a wedge TOP that has a wedge count of 8, the wedge is processing a FLIP simulation. The wedge is connected to a ROP geometry output

- Currently, when this simulation goes to hqueue, a single machine is processing all 8 variations of the simulation, however it would be more efficient if it were broken up across the machines as the simulations take a long time. I also see this as an issue for large scale simulations that require a lot of memory, I wouldn't want one machine processing 8 simulations at once

- My hqueue scheduler “assign to” is set to any

Is there a way to tell the ROP geometry output how many simultaneous wedges it can process, and as a result move the remaining simulations to other machines?

Cheers,
Glenn

Yes, there are two options. You can add a ‘Tag’ to the job so a machine can only run one of them, or you can increase the ‘CPUs per Job’ so that each job consumes more ‘CPU’ slots, thus running fewer jobs at once. Both of these are offered as Job Parms:

https://www.sidefx.com/docs/houdini/nodes/top/hqueuescheduler.html#job-parms [www.sidefx.com]


Which can be set on the ROP Geometry node by installing the corresponding properties:

https://www.sidefx.com/docs/houdini/tops/schedulers.html#jobparms [www.sidefx.com]

Thanks Chris, much appreciated, I'll give that a go.