Hi,
Is houdini designed to use all the available cuda cores from all the available GPU cards on the system if these cards are not connected together (via nvlink or SLI connection)?
If yes, should we expect any performance improvements in OpenCL simulations if these GPUs are linked together?
OpenCL on Multiple Separate GPUs
2787 5 0- Belal
- Member
- 15 posts
- Joined: March 2014
- Offline
- jsmack
- Member
- 7741 posts
- Joined: Sept. 2011
- Offline
- Siavash Tehrani
- Member
- 710 posts
- Joined: July 2005
- Online
- Belal
- Member
- 15 posts
- Joined: March 2014
- Offline
In theory, from OpenCL development aspect, it's doable by making separate command queue for each device, then they would work as with multithreading, but my question here is if houdini was developed with this taken in account?
I wish to know to see if installing 4 cards in my server will make a difference.
I wish to know to see if installing 4 cards in my server will make a difference.
- christopherw
- Staff
- 48 posts
- Joined: Aug. 2016
- Offline
From the system requirements page [www.sidefx.com], at the bottom:
“GPU acceleration currently does NOT make use of multiple OpenCL devices (i.e. two or more graphics cards) but this may change at a future date.”
“GPU acceleration currently does NOT make use of multiple OpenCL devices (i.e. two or more graphics cards) but this may change at a future date.”
- Belal
- Member
- 15 posts
- Joined: March 2014
- Offline
christopherwThank you… That what I was looking for to know… I missed that info.
From the system requirements page [www.sidefx.com], at the bottom:
“GPU acceleration currently does NOT make use of multiple OpenCL devices (i.e. two or more graphics cards) but this may change at a future date.”
But one more question… If two cards are linked via NVLink, then is this will be supported due to the link that makes the two as one?
-
- Quick Links