Page History

ubuntu@gputest:~$ lspci | grep NVIDIA 
00:05.0 VGA compatible3D controller: NVIDIA Corporation GV100GL [Tesla V100 PCIe 32GB]Device 20f1 (rev a1)

ubuntu@gputest:~$ journalctl -u nvidia-gridd | tail
 .... 
JunJan 3005 0807:3744:1457 gputest nvidia-gridd[1159694]: Acquiring license. for GRID vGPU Edition.
Jun 30 08:37:14(Info: http://openstack-nvidia.lisens.ntnu.no:7070/request; NVIDIA Virtual Compute Server)
Jan 05 07:44:57 gputest nvidia-gridd[1159694]: Calling load_byte_array(tra)
JunJan 3005 0807:3744:1759 gputest nvidia-gridd[1159694]: License acquired successfully. (Info: http://openstack-nvidia.lisens.ntnu.no:7070/request; NVIDIA Quadro-Virtual-DWS,5.0Virtual Compute Server)

ubuntu@gputest:~$ nvidia-smi
TueThu Jan Jun 305 0807:5746:1310 20202023       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 418.130  470.82.01    Driver Version: 418.130  470.82.01    CUDA Version: 1011.14     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|==========================                               |                      |               MIG M. |
|=========+======================+======================+=======|
|   0  GRID V100D-8Q       On   | 00000000:00:05.0 Off |==================|
|   0  GRID A100-4C        On   | 00000000:00:05.0 Off |                    0 |
| N/A   N/A    P0    N/A /  N/A |    407MiB /  4091MiB |      0%      Default |
|                           N/A |
| N/A  | N/A    P0    N/A /  N/A  |    528MiB /  8192MiB |       0%      DefaultDisabled |
+-------------------------------+----------------------+----------------------+
                                                                               
+-------------------------------------------------------------------------------------+
| Processes:+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID        GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+

ubuntu@gputest:~$ sudo su -
root@gputest:~# cd NVIDIA_CUDA-1011.14_Samples/1_Utilities/deviceQuery
root@gputest:~/NVIDIA_CUDA-1011.14_Samples/1_Utilities/deviceQuery# make
 ... lots-of-text-from-make ...
root@gputest:~/NVIDIA_CUDA-1011.14_Samples/1_Utilities/deviceQuery# ./deviceQuery 
./deviceQuery Starting...

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

Detected 1 CUDA Capable device(s)

Device 0: "GRID V100DA100-8Q4C"
  CUDA Driver Version / Runtime Version          1011.14 / 1011.14
  CUDA Capability Major/Minor version number:    78.0
  Total amount of global memory:                 81924092 MBytes (85899345924290641920 bytes)
  (80108) Multiprocessors, ( 64064) CUDA Cores/MP:     51206912 CUDA Cores
  GPU Max Clock rate:                            13801410 MHz (1.3841 GHz)
  Memory Clock rate:                             8771215 Mhz
  Memory Bus Width:                              40965120-bit
  L2 Cache Size:                                 629145641943040 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:       6553649152 bytes
  Total amount of shared memory per blockmultiprocessor:        49152167936 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 73 copy engine(s)
  Run time limit on kernels:                     No
  Integrated GPU sharing Host Memory:            No
  Support host page-locked memory mapping:       Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        DisabledEnabled
  Device supports Unified Addressing (UVA):      Yes
  Device supports Managed Memory:                No
  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 / 0 / 5
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 1011.14, CUDA Runtime Version = 1011.14, NumDevs = 1
Result = PASS

# Enable the repositories
distribution=$(. /etc/os-release;echo $ID$VERSION_ID) \
   && curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add - \
   && curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list

# Install the package
sudo apt update && sudo apt -y install nvidia-docker2

# Restart the docker daemon
sudo systemctl restart docker

# Run a test to verifiy that it works
sudo docker run --rm --gpus all nvidia/cuda:11.4.0-base nvidia-smi

# Optionally run a test with Tensorflow that actually runs a bit of code on the GPU via docker
sudo docker run --gpus all -it --rm tensorflow/tensorflow:latest-gpu \
   python -c "import tensorflow as tf; print(tf.reduce_sum(tf.random.normal([1000, 1000])))"