October 10, 2022 at 12:18 pmrodriguezSubscriber
I am working with pretty big geometries/meshes in both SpaceClaim and in Fluent mesher standalone and are having trouble working fluently.
We have a GPU of 4 Gb dedicated memory and when it gets full, the program stops responding. Meanwhile the shared memory stays in zero.
Do you know if there is any setting or something that must be modified in order to properly work?
Thanks in advance.
October 10, 2022 at 8:15 pmpeteroznewmanSubscriber
Bigger models need bigger hardware capabilities. What is the make and model of the display adapter?
October 12, 2022 at 7:59 amrodriguezSubscriber
Yes, I understand that.
I guess I will have to buy one. Can anybody suggest me what I could buy? I mean. The GPU will not be used for simulating, "only" to render results.
Is the dedicated memory the only parameter I should care about? The GPU I currently have is a Nvidia Quadro, I don't really know if I could also use a GeForce, for example. RTX I understand is also an option, being also for professional use.
If the memory is the only important thing, I could also get a cheap Intel Arc...
Any input would be appreciated.
Also regarding the Nvidia control pannel settings. Any idea about what is the best performance settings for SpaceClaim and Fluent Standalone??
Thank you very much in advance. I don't have much knowledge about GPU world at all...
October 12, 2022 at 11:07 ampeteroznewmanSubscriber
Ansys divides GPUs into two categories, one for display and one for accelerating computation. Ansys tests a limited number of GPUs and lists the ones tested in a document.
Here is the pdf file that has the display adapters:
While a GeForce card will probably work for the display, it hasn’t been tested. In a professional environment, cards from the published list are recommended.
Here is the pdf file that has the list of GPU accelerator cards
In the past, these two lists had separate cards, but now I see the Nvidia RTX A4000 card is on both the display list and the accelerator list for Fluent! This card has 16GB of GPU memory, so that might be a better choice for your needs than the RTX 4000 which has 8GB of GPU memory.
October 12, 2022 at 12:30 pmrodriguezSubscriber
Thank you very much. Very useful information.
- You must be logged in to reply to this topic.
Simulation World 2022
Check out more than 70 different sessions now available on demand. Get inspired as you hear from visionary companies, leading researchers and educators from around the globe on a variety of topics from life-saving improvements in healthcare, to bold new realities of space travel. Take a leap of certainty and check out a session today here.
Earth Rescue – An Ansys Online Series
The climate crisis is here. But so is the human ingenuity to fight it. Earth Rescue reveals what visionary companies are doing today to engineer radical new ideas in the fight against climate change. Click here to watch the first episode.
Subscribe to the Ansys Blog to get great new content about the power of simulation delivered right to your email on a weekly basis. With content from Ansys experts, partners and customers you will learn about product development advances, thought leadership and trends and tips to better use Ansys tools. Sign up here.
- ANSYS Workbench Measuring within Design
- How to resolve Mesh Failure
- check element type
- The mesh file exporter could not resolve cyclic dependencies in overlapping contact regions error
- Meshing Error
- Error in meshing
- Conformal vs Non-Conformal Mesh
- Ansys 19.0 – will not create mesh
- Dealing with inflation layers around sharp corners in Ansys workbench meshing
- execution error inside the mesher. The process suffered an unhandled exception or ran out of memory
© 2022 Copyright ANSYS, Inc. All rights reserved.