Questions pertaining GPU (graphics processing unit), a specialized electronic circuit designed to rapidly manipulate and alter memory to accelerate the creation of images in a frame buffer intended for output to a display device
Questions tagged [gpu]
358 questions
408
votes
20 answers
GPU usage monitoring (CUDA)
I installed CUDA toolkit on my computer and started BOINC project on GPU. In BOINC I can see that it is running on GPU, but is there a tool that can show me more details about that what is running on GPU - GPU usage and memory usage?
pbm
- 24,747
- 6
- 36
- 51
53
votes
1 answer
How to verify if hardware acceleration is enabled?
How can I verify whether hardware acceleration is available and whether it is enabled for my video card.
Noah Goodrich
- 685
- 2
- 7
- 9
28
votes
6 answers
How to install CUDA Toolkit 7/8/9 on Debian 8 (Jessie) or 9 (Stretch)?
How to install Cuda Toolkit 7.0 or 8 on Debian 8?
I know that Debian 8 comes with the option to download and install CUDA Toolkit 6.0 using apt-get install nvidia-cuda-toolkit, but how do you do this for CUDA toolkit version 7.0 or 8?
I tried…
Greg
- 735
- 2
- 9
- 24
17
votes
3 answers
How to adjust NVIDIA GPU fan speed on a headless node?
How is it possible to control the fan speed of multiple consumer NVIDIA GPUs such as Titan and 1080 Ti on a headless node running Linux?
Aleksandr Dubinsky
- 694
- 1
- 5
- 15
14
votes
6 answers
How to automatically force full composition pipeline for Nvidia GPU driver?
I've installed Manjaro Linux. My graphics card is an Nvidia GTX 1050Ti.
When I boot my computer and try to watch videos, I notice harsh screen tearing. This problem is resolved when I go to the Nvidia X Server Settings and enable the option "Force…
Danieldrd
- 141
- 1
- 1
- 3
14
votes
1 answer
How do I interpret the output of intel-gpu-top and intel-gpu-overlay?
I have these commands compiled and running but their contents are a bit of a mystery to me.
The processes from intel-gpu-overlay read something like: 15R, 16B, 41ms waits. What is an R, what is a B, what does that wait time indicate?
It has CPU:…
mpr
- 1,064
- 3
- 15
- 24
14
votes
1 answer
User-based GPU priority
I have a computer running Linux (Kubuntu 14.04.3 LTS x64), where I use the CUDA toolkit to perform some computations on some Nvidia GPUs.
I share the computer with a few other users. How can I define which priority each user has for each…
Franck Dernoncourt
- 4,749
- 15
- 48
- 79
13
votes
2 answers
How to force the fan to always spin?
I am using ArchLinux on an HP Pavilion dv9000t which has overheating problems. I did all what I can do to get a better air flow in the laptop and put a better thermal paste but there is still a problem:
the fan stops spinning when the CPU…
antoyo
- 443
- 3
- 16
13
votes
1 answer
11 GB of GPU RAM used, and no process listed by nvidia-smi
In my GPU #0, 11341MiB of GPU RAM is used, and no process is listed by nvidia-smi. How is that possible, and how can I get my memory back?
Thu Aug 18 14:27:58 2016
+------------------------------------------------------+
| NVIDIA-SMI 352.63 …
Franck Dernoncourt
- 4,749
- 15
- 48
- 79
13
votes
5 answers
Multi Nvidia GPU overclocking for computations (CUDA)
I have seen in forums and manuals that you have to add
Option "Coolbits" "value"
to xorg.conf or similar files.
I have been able to get this working for the first GPU, the one rendering the display. I have not been able to get overclocking options…
Agade
- 233
- 1
- 2
- 7
12
votes
1 answer
nvidia-smi hangs indefinitely: what could be the issue?
I try to run nvidia-smi from the shell on a machine, but it hangs indefinitely: what could be the issue?
Update (2016-08-09): Since this question received no answer, I crossposted it:…
Franck Dernoncourt
- 4,749
- 15
- 48
- 79
11
votes
1 answer
How can I disable (and later re-enable) one of my NVIDIA GPUs?
I'm working on a system with multiple NVIDIA GPUs. I would like disable / make-disappear one of my GPUs, but not the others; without rebooting; and so that I can later re-enable it.
Is this possible?
Notes:
Assume I have root (though a non-root…
einpoklum
- 8,772
- 19
- 65
- 129
11
votes
3 answers
How to log GPU load?
I wonder how to log GPU load. I use Nvidia graphic cards with CUDA.
Not a duplicate: I want to log.
Franck Dernoncourt
- 4,749
- 15
- 48
- 79
11
votes
1 answer
GPU usage per process on a Linux machine (CUDA)
I use the CUDA toolkit to perform some computations on my Nvidia GPUs. How can I see the per-process GPU usage on a Linux machine (CUDA)?
nvidia-smi does list all processes for each GPU, but doesn't indicate the GPU utilization per process:
Franck Dernoncourt
- 4,749
- 15
- 48
- 79
9
votes
5 answers
How to kill all processes using a given GPU?
I use the CUDA toolkit to perform some computations on my Nvidia GPUs. How to kill all processes that use a given GPU? (killing at once, i.e. without having to manually type the PIDs behind kill -9.)
E.g. killing all processes using GPU 2:
Franck Dernoncourt
- 4,749
- 15
- 48
- 79