Support : Knowledge base

Knowledge Base

Welcome to OPAL-RT’s Knowledge Base

OPAL-RT offers a repository of support information for optimal use of its technology.

Loading…

Please note that OPAL-RT knowledge base is not fully optimized for mobile platforms.

For optimal experience, use a desktop computer.

Reference Number: AA-01350// Views: AA-01350// Created: 2017-12-05 21:45:42// Last Updated: 2020-04-01 15:26:59
Q&A
HYPERSIM : How can I determine what part of my model is causing Overruns in HYPERSIM?

Question

How can I determine what part of my model is causing Overruns in HYPERSIM?

Answer

Although it is not possible to know the time taken for calculation for a single block per Time-Step, it is possible to know the estimated/predicted time required for each process. This is done in the Task Mapping step. With the estimated/predicted time calculation time for each node, you will have a higher resolution picture of your model in terms of processing power needed for certain nodes. The process separation is done by HYPERSIM automatically and uses node names for referencing. (See 2nd picture for information about the nodes) 


To make sure you have overruns, look in the Streched Step box of this table in HyperView.


1. Start the simulation and go to Task Mapping in the Compilation View.

2. Depending on how many cores/processors you have enabled, processes will be assigned automatically by HYPERSIM and documented here.

3. Each node is given an estimated/predicted calculation time per Time-Step

4. Here is the total estimated/predicted calculation time for Processor #01

5. You can see that there is a node called WED7 that is on the model.

6. If unsure, you can find the node using Ctrl + f or by going to the Home Tab / Find / Quick Find