示例设备查询cuda程序

Question

我有一台配置了NVIDIA GeForce1080 GTX和CentOS 7作为操作系统的Intel Xeon机器。我已经安装了NVIDIA驱动程序410.93和cuda toolkit 10.0。编译完cuda示例后，我尝试运行/设备查询。但它是这样扔的

./deviceQuery Starting...

 CUDA Device Query (Runtime API) version (CUDART static linking)

cudaGetDeviceCount returned 30
-> unknown error
Result = FAIL

一些命令输出

lspci | grep VGA

01:00.0 VGA compatible controller: NVIDIA Corporation GP104 [GeForce GTX 1080] (rev a1)

nvidia-smi

Wed Feb 13 16:08:07 2019       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 410.93       Driver Version: 410.93       CUDA Version: 10.0     |
|-------------------------------+----------------------+----------------------+
| 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  On |                  N/A |
|  0%   54C    P0    46W / 240W |    175MiB /  8119MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|    0      6275      G   /usr/bin/X                                    94MiB |
|    0      7268      G   /usr/bin/gnome-shell                          77MiB |
+-----------------------------------------------------------------------------+

nvcc版本

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2018 NVIDIA Corporation
Built on Sat_Aug_25_21:08:01_CDT_2018
Cuda compilation tools, release 10.0, V10.0.13

路径

PATH =/usr/local/cuda-10.0/bin:/usr/local/cuda/bin:/usr/local/bin:/usr/local/sbin:
LD_LIBRARY_PATH = /usr/local/cuda-10.0/lib64:/usr/local/cuda/lib64:

LSAMD|grep nvidia

nvidia_drm             39819  3 
nvidia_modeset       1036573  6 nvidia_drm
nvidia              16628708  273 nvidia_modeset
drm_kms_helper        179394  1 nvidia_drm
drm                   429744  6 drm_kms_helper,nvidia_drm
ipmi_msghandler        56032  2 ipmi_devintf,nvidia

lsmod|grep nvidia-uvm无输出

dmesg | grep NVRM

[    8.237489] NVRM: loading NVIDIA UNIX x86_64 Kernel Module  410.93  Thu Dec 20 17:01:16 CST 2018 (using threaded interrupts)

这个问题与modprobe或nvidia uvm有关吗？我在NVIDIA devtalk论坛上问过这个问题，但还没有回复。请给出一些建议<提前感谢。

Answer 1

我调试了它。问题是nvidia驱动程序（410.93）和cuda（cuda运行文件附带了驱动程序410.48）之间的版本不匹配。自动删除所有驱动程序并从头重新安装。删除了/var/lib/dkms/nvidia/*中的所有链接文件。现在它工作得很好。和nvidia uvm也加载。

LSAMD|grep nvidia

nvidia_uvm            786031  0 
nvidia_drm             39819  3 
nvidia_modeset       1048491  6 nvidia_drm
nvidia              16805034  274 nvidia_modeset,nvidia_uvm
drm_kms_helper        179394  1 nvidia_drm
drm                   429744  6 drm_kms_helper,nvidia_drm
ipmi_msghandler        56032  2 ipmi_devintf,nvidia

nvidia-smi

Fri Feb 15 11:46:24 2019       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 410.48                 Driver Version: 410.48                    |
|-------------------------------+----------------------+----------------------+
| 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  On |                  N/A |
|  0%   45C    P8    10W / 240W |    242MiB /  8119MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|    0      6063      G   /usr/bin/X                                   120MiB |
|    0      7502      G   /usr/bin/gnome-shell                         119MiB |
+-----------------------------------------------------------------------------+

nvcc-V

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2018 NVIDIA Corporation
Built on Sat_Aug_25_21:08:01_CDT_2018
Cuda compilation tools, release 10.0, V10.0.130

./设备查询

./deviceQuery Starting...

 CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: "GeForce GTX 1080"
  CUDA Driver Version / Runtime Version          10.0 / 10.0
  CUDA Capability Major/Minor version number:    6.1
  Total amount of global memory:                 8119 MBytes (8513585152 bytes)
  (20) Multiprocessors, (128) CUDA Cores/MP:     2560 CUDA Cores
  GPU Max Clock rate:                            1797 MHz (1.80 GHz)
  Memory Clock rate:                             5005 Mhz
  Memory Bus Width:                              256-bit
  L2 Cache Size:                                 2097152 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
  Maximum Layered 1D Texture Size, (num) layers  1D=(32768), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(32768, 32768), 2048 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  2048
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 65535)
  Maximum memory pitch:                          2147483647 bytes
  Texture alignment:                             512 bytes
  Concurrent copy and kernel execution:          Yes with 2 copy engine(s)
  Run time limit on kernels:                     Yes
  Integrated GPU sharing Host Memory:            No
  Support host page-locked memory mapping:       Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        Disabled
  Device supports Unified Addressing (UVA):      Yes
  Device supports Compute Preemption:            Yes
  Supports Cooperative Kernel Launch:            Yes
  Supports MultiDevice Co-op Kernel Launch:      Yes
  Device PCI Domain ID / Bus ID / location ID:   0 / 1 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 10.0, CUDA Runtime Version = 10.0, NumDevs = 1
Result = PASS