如何在集成GPU上运行Xorg服务器？

Question

我有2个Nvidia GTX1080专用GPU和1个英特尔集成GPU安装在我的机器上。我只想使用nvidia GPU进行科学计算。尽管我将监视器插入主板，Xorg服务器使用nvidia GPU之一并分配了将近700 MB的内存。

如何强制Xorg服务器只使用Intel GPU？

lspci | grep 'VGA'输出：

00:02.0 VGA compatible controller: Intel Corporation Device 5912 (rev 04)
01:00.0 VGA compatible controller: NVIDIA Corporation Device 1b80 (rev a1)
02:00.0 VGA compatible controller: NVIDIA Corporation Device 1b80 (rev a1)

nvidia-smi输出：

Tue Jan  2 15:24:18 2018       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 384.98                 Driver Version: 384.98                    |
|-------------------------------+----------------------+----------------------+
| 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 1080    Off  | 00000000:01:00.0 Off |                  N/A |
| 32%   59C    P5    16W / 180W |   1322MiB /  8114MiB |      4%      Default |
+-------------------------------+----------------------+----------------------+
|   1  GeForce GTX 1080    Off  | 00000000:02:00.0 Off |                  N/A |
| 33%   60C    P2    56W / 180W |   7858MiB /  8114MiB |     27%      Default |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|    0     12818      G   /usr/lib/xorg/Xorg                           638MiB |
|    0     13476      G   compiz                                       278MiB |
|    0     14230      G   ...-token=A9CF4CD99B5947DB32E9E4B117997A68   404MiB |
|    1     25764      C   python                                      7847MiB |
+-----------------------------------------------------------------------------+

Answer 1

1. 在NVIDIA X服务器设置中将素数配置文件更改为Intel(节电模式)
2. 注销/登录
3. add LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/cuda-8.0/lib64:/usr/lib/nvidia-xxx (我的是nvidia-384)到~/..bashrc文件
4. 运行nvidia-smi

如果它不能工作，请确保在UEFI设置中禁用安全引导。