CUDA #

# ubuntu 20.04, x86_64
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-keyring_1.0-1_all.deb
sudo dpkg -i cuda-keyring_1.0-1_all.deb
sudo apt-get update
sudo apt-get -y install cuda

apt install linux-headers-$(uname -r)

wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-ubuntu2004.pin
sudo mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-600
sudo apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub
sudo add-apt-repository "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/ /"
wget https://developer.download.nvidia.com/compute/cuda/12.0.0/local_installers/cuda-repo-ubuntu2004-12-0-local_12.0.0-525.60.13-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu2004-12-0-local_12.0.0-525.60.13-1_amd64.deb
sudo cp /var/cuda-repo-ubuntu2004-12-0-local/cuda-*-keyring.gpg /usr/share/keyrings/
sudo apt-get update
sudo apt-get -y install cuda

apt install nvidia-cuda-toolkit

# Deleting any NVIDIA/CUDA packages you may already have installed
sudo rm /etc/apt/sources.list.d/cuda*
sudo apt remove --autoremove nvidia-cuda-toolkit
sudo apt remove --autoremove nvidia-*

# Deleting any remaining Cuda files on /usr/local/
sudo rm -rf /usr/local/cuda*

# Purge any remaining NVIDIA configuration files
sudo apt-get purge nvidia*

# updating and deleting unnecessary dependencies.
sudo apt-get update
sudo apt-get autoremove
sudo apt-get autoclean

# For 18.04
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-ubuntu1804.pin
sudo mv cuda-ubuntu1804.pin /etc/apt/preferences.d/cuda-repository-pin-600
wget https://developer.download.nvidia.com/compute/cuda/11.4.0/local_installers/cuda-repo-ubuntu1804-11-4-local_11.4.0-470.42.01-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu1804-11-4-local_11.4.0-470.42.01-1_amd64.deb
sudo apt-key add /var/cuda-repo-ubuntu1804-11-4-local/7fa2af80.pub
sudo apt-get update
sudo apt-get -y install cuda

# For 20.04
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-ubuntu2004.pin
sudo mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-600
wget https://developer.download.nvidia.com/compute/cuda/11.4.0/local_installers/cuda-repo-ubuntu2004-11-4-local_11.4.0-470.42.01-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu2004-11-4-local_11.4.0-470.42.01-1_amd64.deb
sudo apt-key add /var/cuda-repo-ubuntu2004-11-4-local/7fa2af80.pub
sudo apt-get update
sudo apt-get -y install cuda

# 配置 path
cat << EOF >> ~/.zshrc

# set PATH for cuda 11.4 installation
if [ -d "/usr/local/cuda-11.4/bin/" ]; then
    export PATH=/usr/local/cuda-11.4/bin${PATH:+:${PATH}}
    export LD_LIBRARY_PATH=/usr/local/cuda-11.4/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
fi

EOF
zsh

# check
nvidia-smi

nvcc -V
# nvcc --version

vi kernel.cu

nvcc -o kernel kernel.cu
./kernel

# 输出
# Max error: 0.000000

#include <stdio.h>

__global__
void saxpy(int n, float a, float *x, float *y)
{
  int i = blockIdx.x*blockDim.x + threadIdx.x;
  if (i < n) y[i] = a*x[i] + y[i];
}

int main(void)
{
  int N = 1<<20;
  float *x, *y, *d_x, *d_y;
  x = (float*)malloc(N*sizeof(float));
  y = (float*)malloc(N*sizeof(float));

  cudaMalloc(&d_x, N*sizeof(float));
  cudaMalloc(&d_y, N*sizeof(float));

  for (int i = 0; i < N; i++) {
    x[i] = 1.0f;
    y[i] = 2.0f;
  }

  cudaMemcpy(d_x, x, N*sizeof(float), cudaMemcpyHostToDevice);
  cudaMemcpy(d_y, y, N*sizeof(float), cudaMemcpyHostToDevice);

  // Perform SAXPY on 1M elements
  saxpy<<<(N+255)/256, 256>>>(N, 2.0f, d_x, d_y);

  cudaMemcpy(y, d_y, N*sizeof(float), cudaMemcpyDeviceToHost);

  float maxError = 0.0f;
  for (int i = 0; i < N; i++)
    maxError = max(maxError, abs(y[i]-4.0f));
  printf("Max error: %f\n", maxError);

  cudaFree(d_x);
  cudaFree(d_y);
  free(x);
  free(y);
}

// This is the REAL "hello world" for CUDA!
// It takes the string "Hello ", prints it, then passes it to CUDA
// with an array of offsets. Then the offsets are added in parallel
// to produce the string "World!"
// By Ingemar Ragnemalm 2010

// nvcc hello-world.cu -L /usr/local/cuda/lib -lcudart -o hello-world

#include <stdio.h>

const int N = 16;
const int blocksize = 16;

__global__
void hello(char *a, int *b)
{
    a[threadIdx.x] += b[threadIdx.x];
}

int main()
{
    char a[N] = "Hello \0\0\0\0\0\0";
    int b[N] = {15, 10, 6, 0, -11, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};

    char *ad;
    int *bd;
    const int csize = N*sizeof(char);
    const int isize = N*sizeof(int);

    printf("%s", a);

    cudaMalloc( (void**)&ad, csize );
    cudaMalloc( (void**)&bd, isize );
    cudaMemcpy( ad, a, csize, cudaMemcpyHostToDevice );
    cudaMemcpy( bd, b, isize, cudaMemcpyHostToDevice );

    dim3 dimBlock( blocksize, 1 );
    dim3 dimGrid( 1, 1 );
    hello<<<dimGrid, dimBlock>>>(ad, bd);
    cudaMemcpy( a, ad, csize, cudaMemcpyDeviceToHost );
    cudaFree( ad );
    cudaFree( bd );

    printf("%s\n", a);
    sleep(1);
    return EXIT_SUCCESS;
}

# 查看cuDNN版本
cat /usr/local/cuda/include/cudnn.h | grep CUDNN_MAJOR -A 2

例如：
#define CUDNN_MAJOR 8
#define CUDNN_MINOR 2
#define CUDNN_PATCHLEVEL 4

表示当前使用的是cuDNN 8.2.4 版本