How can I know from the terminal or something whether my hardware supports CUDA?
4 Answers
Using the browser to find CUDA
- Open
Chrome
browser - Goto the url
chrome://gpu
- Search for
cuda
and you should get the version detected (in my case, not enabled)

- 733
-
4If that shows 0, the hardware may still support CUDA, but the drivers simply are not installed/working. It shows 0 on my laptop, but GPU-Z says my hardware supports CUDA 1.2 – Pascal Sep 07 '21 at 17:30
-
it is almost useless answer ... "almost" cause chrome suggests you to install the latest official drivers :D https://askubuntu.com/a/1450399/652604 – madzohan Jan 15 '23 at 23:38
CUDA works with all Nvidia GPUs from the G8x series onwards, including GeForce, Quadro and the Tesla line. CUDA is compatible with most standard operating systems.
For a list of supported graphic cards, see Wikipedia.

- 36,264
- 56
- 94
- 147

- 526
- 3
- 7
-
-
You didn't tell me that earlier. What is your motherboard manufacturer and model? Does it have a Nvidia graphic processor? – LDC3 Jun 07 '15 at 17:50
-
-
A system diagnostic program called speccy is available that will tell you everything you need: http://www.piriform.com/speccy – LDC3 Jun 07 '15 at 19:25
-
-
These pages have system information programs for Ubuntu and other Linux OS: http://www.ubuntugeek.com/howto-get-your-system-information-with-sysinfo.html http://www.webupd8.org/2011/07/how-to-get-hardware-information-in.html – LDC3 Jun 07 '15 at 20:47
-
Thanks. I like
lshw
. From what I gather, I have a "Haswell-ULT Integrated Graphics Controller" from Intel. Will it support CUDA? – a06e Jun 07 '15 at 20:57 -
1
-
Thanks, that answers my question. Just one more: Will my chip support OpenCL? – a06e Jun 07 '15 at 21:11
-
Ask that in another question because I don't know the answer. The person who does will need to know which graphics controller you have. – LDC3 Jun 07 '15 at 21:17
(2021 update)
CUDA software API is supported on Nvidia GPUs, through the software drivers provided by Nvidia.
If your desktop has a Nvidia GPU, AND you have the Nvidia drivers installed (for ex from https://www.nvidia.com/Download/index.aspx), an executable that uses CUDA can be built using CUDA toolkit, as outlined at -
https://developer.nvidia.com/blog/even-easier-introduction-cuda/
- To compile a CUDA application specifically for your GPU, the compute capability of the specific GPU is required, and this can be obtained by following the steps outlined at
https://github.com/prabindh/mygpu
(I am the author of that web tool)
Manually, you could use nvidia-smi that is installed along with the driver
nvidia-smi --query-gpu=name --format=csv
Or use driver information to obtain GPU name and map it to Compute capability.

- 111
CUDA support is shown in official nvidia website, for example my geforce-gtx-1060
In case it is supported and you have LTS Ubuntu version:
- install nvidia-driver with CUDA support from official CUDA repository

- 257