kirin@xeon-E3:~$ nvidia-smi
Failed to initialize NVML: Driver/library version mismatch

kirin@xeon-e3:/work/cuda$ lsmod | grep nvidia
nvidia              35250176  1
drm                   491520  6 drm_kms_helper,nvidia,ttm,nouveau

kirin@xeon-E3:~$ sudo reboot

kirin@xeon-e3:~$ nvidia-smi
Mon Aug 15 18:14:17 2022
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 470.42.01    Driver Version: 470.42.01    CUDA Version: 11.4     |
|-------------------------------+----------------------+----------------------+
| 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 NVIDIA GeForce ...  On | 00000000:01:00.0  On |                  N/A |
| 46%   48C    P8    10W /  75W |    108MiB /  3909MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|    0   N/A  N/A      1073      G   /usr/lib/xorg/Xorg                 57MiB |
|    0   N/A  N/A      1116      G   /usr/bin/gnome-shell               48MiB |
+-----------------------------------------------------------------------------+

vi ~/.bashrc

# cuda
export PATH=/usr/local/cuda-11.4/bin/:$PATH
export LD_LIBRARY_PATH=/usr/local/cuda-11.4/lib64:$LD_LIBRARY_PATH

kirin@xeon-e3:~$ cat /proc/driver/nvidia/version
NVRM version: NVIDIA UNIX x86_64 Kernel Module  470.42.01  Tue Jun 15 21:26:37 UTC 2021
GCC version:  gcc version 7.5.0 (Ubuntu 7.5.0-3ubuntu1~18.04)

kirin@xeon-e3:~$ lspci | grep -i nvidia
01:00.0 VGA compatible controller: NVIDIA Corporation Device 1f82 (rev a1)
01:00.1 Audio device: NVIDIA Corporation Device 10fa (rev a1)

kirin@xeon-e3:~$  cat /usr/local/cuda-11.4/version.json  | egrep "(CUDA SDK|CUDA NVCC)" -A1
      "name" : "CUDA SDK",
      "version" : "11.4.0"
--
      "name" : "CUDA NVCC",
      "version" : "11.4.48"

kirin@xeon-e3:~$ nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2021 NVIDIA Corporation
Built on Wed_Jun__2_19:15:15_PDT_2021
Cuda compilation tools, release 11.4, V11.4.48
Build cuda_11.4.r11.4/compiler.30033411_0

sudo apt install git

cd $WORK_DIR/cuda/
git clone https://github.com/NVIDIA/cuda-samples.git -b v11.4 --depth 1
cd cuda-samples
time make -j8

kirin@xeon-e3:/work/cuda/cuda-samples$ cd bin/x86_64/linux/release/
kirin@xeon-e3:/work/cuda/cuda-samples/bin/x86_64/linux/release$ ./deviceQuery
./deviceQuery Starting...

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

Detected 1 CUDA Capable device(s)

Device 0: "NVIDIA GeForce GTX 1650"
  CUDA Driver Version / Runtime Version          11.4 / 11.4
  CUDA Capability Major/Minor version number:    7.5
  Total amount of global memory:                 3909 MBytes (4099276800 bytes)
  (014) Multiprocessors, (064) CUDA Cores/MP:    896 CUDA Cores
  GPU Max Clock rate:                            1665 MHz (1.66 GHz)
  Memory Clock rate:                             4001 Mhz
  Memory Bus Width:                              128-bit
  L2 Cache Size:                                 1048576 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 shared memory per multiprocessor:        65536 bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  1024
  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 3 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 Managed Memory:                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 = 11.4, CUDA Runtime Version = 11.4, NumDevs = 1
Result = PASS