amanusk's questions

I am running a headless server with an Nvidia GPU. Even when the GPU is not doing any work, it is consuming about 25 Watts of power:

+-----------------------------------------------------------------------------+
| NVIDIA-SMI 430.26       Driver Version: 430.26       CUDA Version: 10.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce GTX 950     Off  | 00000000:01:00.0 Off |                  N/A |
|  0%   61C    P0    26W / 110W |      0MiB /  2001MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+

Is there a way to completely turn off power delivery to the GPU when it is not in use?

I tried sudo prime-select intel Which does cause nvidia-smi to stop working, but a power meter connect to the wall shows exactly the same power consumption with either intel or nvidia selected.

Completely removing the GPU reduces the power consumption by about 30 Watts as expected.

The main purpose is to save power and costs during idle operations, with an option to spin up the GPU when it is needed (remotely via ssh).

According to this article a severe flaw in wpa2 protocol has been published making many systems using WiFi vulnerable to an attack. Should I be worried and has a patch been issued for Ubuntu?

I notice that when running a stress test in Ubuntu desktop, my laptop begins the throttle when temperatures reach ~90C. I have noticed that when Ubuntu-server was installed on the same laptop, throttling began at much higher temperatures. Only at about 100C. I was not able to recreate this in Ubuntu-desktop. How can I change the temperature at which throttling begins.

Is it possible to install openCL on 16.04 (CPU-Only)? I tried many guides, but still do not get a working box. I have a sandy-bridge second gen CPU, if this matters.

On Ubuntu 16.04. I have 2 Nvidia GPU's. How can I choose which one is being used for OpenGL rendering? lspci detects both GPU's, and both show up in Nvidia settings. When I run something like Unigen-Heavan, GPU 0 is used. How can I make it use GPU 1? (Only have one monitor) Thanks

Still looking for a better answer to actually switch GPU 0 and GPU 1, but what ended up working was turning off GPU 0 (the internal) in BIOS, connecting the external GPU, and connecting the screen to the external GPU. This actually improves performance slightly, I need to change the cable connected to the monitor.

I was looking into undervolting my laptop CPU. I could only find guides on phc that are said to be outdated. Is there a tool for that in the new version? Is it possible with TLP?