【问题标题】:Nvidia GeForce 210 compute issue on Ubuntu 18.04Ubuntu 18.04 上的 Nvidia GeForce 210 计算问题
【发布时间】:2020-10-09 14:14:12
【问题描述】:

我使用的是 ubuntu 18.04(我有 ubuntu 18.04 的双启动窗口)。

nvidia-smi


这是我在 ubuntu(18.04) 终端上运行上述命令时得到的输出:

Fri Oct  9 09:33:56 2020       
+------------------------------------------------------+                       
| NVIDIA-SMI 340.108    Driver Version: 340.108        |                       
|-------------------------------+----------------------+----------------------+
| 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 210         Off  | 0000:01:00.0     N/A |                  N/A |
| 35%   52C    P8    N/A /  N/A |    368MiB /  1023MiB |     N/A      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Compute processes:                                               GPU Memory |
|  GPU       PID  Process name                                     Usage      |
|=============================================================================|
|    0            Not Supported                                               |
+-----------------------------------------------------------------------------+

在此之前,我按照以下步骤在我的系统上安装所需的驱动程序:

sudo add-apt-repository --remove ppa:graphics-drivers/ppa
sudo apt-get purge nvidia*
sudo apt autoremove
sudo add-apt-repository ppa:graphics-drivers/ppa
sudo apt update
sudo ubuntu-drivers devices
sudo ubuntu-drivers autoinstall
sudo shutdown -r now

当我尝试运行Geekbench5 计算基准测试时,输出在运行直方图均衡时停止。这是我在提取 geekbench5 的文件夹中运行 ./geekbench5 --compute OpenCL 时的输出:

[1009/092949:FATAL:src/halogen/cuda/cuda_library.cpp(1481)] Failed to load 

cuDevicePrimaryCtxRetain: /usr/lib/x86_64-linux-gnu/libcuda.so.1: undefined symbol: cuDevicePrimaryCtxRetain
[1009/092949:FATAL:src/halogen/cuda/cuda_library.cpp(1481)] Failed to load cuDevicePrimaryCtxRetain: /usr/lib/x86_64-linux-gnu/libcuda.so.1: undefined symbol: cuDevicePrimaryCtxRetain
Geekbench 5.2.4 Tryout : https://www.geekbench.com/

Geekbench 5 is in tryout mode.

Geekbench 5 requires an active Internet connection when in tryout mode, and 
automatically uploads test results to the Geekbench Browser. Other features 
are unavailable in tryout mode.

Buy a Geekbench 5 license to enable offline use and remove the limitations of 
tryout mode.

If you would like to purchase Geekbench you can do so online:

  https://store.primatelabs.com/v5

If you have already purchased Geekbench, enter your email address and license 
key from your email receipt with the following command line:

  ./geekbench5 -r <email address> <license key>

  Running Gathering system information
System Information
  Operating System              Ubuntu 18.04.5 LTS 4.15.0-118-generic x86_64
  Model                         To be filled by O.E.M. To be filled by O.E.M.
  Motherboard                   O.E.M Intel H81
  BIOS                          American Megatrends Inc. 4.6.5

Processor Information
  Name                          Intel Core i5-4460
  Topology                      1 Processor, 4 Cores
  Identifier                    GenuineIntel Family 6 Model 60 Stepping 3
  Base Frequency                3.20 GHz
  L1 Instruction Cache          32.0 KB x 2
  L1 Data Cache                 32.0 KB x 2
  L2 Cache                      256 KB x 2
  L3 Cache                      6.00 MB

Memory Information
  Size                          7.75 GB

OpenCL Information
  Platform Vendor               NVIDIA Corporation
  Platform Name                 NVIDIA CUDA
  Device Vendor                 NVIDIA Corporation
  Device Name                   GeForce 210
  Device Driver Version         340.108
  Maximum Frequency             1.23 GHz
  Compute Units                 2
  Device Memory                 1024 MB


OpenCL
  Running Sobel
  Running Canny
  Running Stereo Matching
  Running Histogram Equalization
[1009/093329:ERROR:src/interface/console/consolemain.cpp(808)] Geekbench encountered an internal error and cannot continue. Please contact support@primatelabs.com for assistance.

Internal error message: clCreateImage returned -40.

此外,当我尝试在 Windows 10(同一台机器,在 GUI 上)上运行 geekbench5 计算基准测试时,它在直方图均衡时暂停运行。

不知道为什么会这样.有人可以帮忙吗?

【问题讨论】:

  • 我只想知道为什么我的问题被否决了。它是否已过时或不清楚?我是这个平台的新手,并在发布此问题之前尝试搜索答案。

标签: gpu ubuntu-18.04 nvidia


【解决方案1】:

您的驱动程序安装正常,但您的 GPU 已经使用了 11 年,不支持 OpenCL 标准的一些最新功能。 geekbench 错误消息-40 表示您的 GPU 不支持 geekbench 用于其基准测试之一的图像大小。这会导致基准测试崩溃。也许旧版本的 geekbench 仍然有效。

【讨论】:

  • 谢谢!我将尝试使用旧版本的 geekbench 进行测试。另外,如果您不介意,您能否提出一些解释错误消息的方法?
  • 这里是 OpenCL 错误代码的列表:streamhpc.com/blog/2013-04-28/opencl-error-codes 不过其中一些有点不确定,并且与官方声明的原因不同。
猜你喜欢
  • 2014-07-25
  • 2020-08-02
  • 1970-01-01
  • 2019-05-03
  • 2020-06-26
  • 2019-04-30
  • 1970-01-01
  • 1970-01-01
  • 2020-07-21
相关资源
最近更新 更多