Setup M15R6 Nvidia for Data Science - Step-by-step

1.install-nvidia-manually.md

Install

Cuda

• Select the Xorg driver

sudo apt -y install unzip linux-headers-$(uname -r) 
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
sudo dpkg -i cuda-keyring_1.1-1_all.deb
sudo apt -y update && sudo apt -y install cuda
sudo reboot

• Update and source ~/.zshrc

export PATH=/usr/local/cuda/bin:$PATH
export PATH=/usr/local/cuda-12.3/bin${PATH:+:${PATH}}
export LD_LIBRARY_PATH=/usr/local/cuda-12.3/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
export LD_LIBRARY_PATH=/usr/local/cuda/lib64:$LD_LIBRARY_PATH
export CUDA_HOME=/usr/local/cuda

Test

nvcc --version
git clone https://github.com/nvidia/cuda-samples ~/cuda-samples
cd ~/cuda-samples && make
cd ~/cuda-samples/Samples/1_Utilities/deviceQuery && make && ./deviceQuery
cd ~/cuda-samples/Samples/1_Utilities/bandwidthTest && make && ./bandwidthTest

• Preinstall, Install All, Install LTS, PostIntall

cuDNN

sudo apt -y install cudnn-cuda-12

Test

sudo apt -y install libcudnn9-samples
sudo cp -r /usr/src/cudnn_samples_v9 ~/cudnn_samples_v9
cd ~/cudnn_samples_v9/mnistCUDNN && make clean && make && ./mnistCUDNN

• Install

Conda env

• Create the file bigd.yml and copy content

conda env create -f bigd.yml
conda activate bigd
conda env update --file bigd.yml --prune

• Start jupyter lab

import tensorrt as rt; print(rt.__version__); assert rt.Builder(rt.Logger())

import tensorflow as tf; print("Num GPUs Available: ", len(tf.config.list_physical_devices('GPU')))

import torch; import torchvision; print(torch.cuda.is_available())

import nvidia_smi
nvidia_smi.nvmlInit()
handle = nvidia_smi.nvmlDeviceGetHandleByIndex(0)
mem_res = nvidia_smi.nvmlDeviceGetMemoryInfo(handle)
print(f'mem: {mem_res.used / (1024**2)} (GiB)') # usage in GiB
print(f'mem: {100 * (mem_res.used / mem_res.total):.3f}%') # percentage usage

• TensorRt
• TensorFlow
• pyTorch

Remove conda env

conda deactivate
conda env remove -n bigd

Containers

NGC cli

mkdir -p ~/.local/bin
pushd ~/.local/bin
wget -O ngccli_cat_linux.zip https://ngc.nvidia.com/downloads/ngccli_cat_linux.zip && unzip -o ngccli_cat_linux.zip && chmod u+x ngc-cli/ngc && rm ngccli_cat_linux.zip ngc-cli.md5
echo "export PATH=\"\$PATH:$(pwd)/ngc-cli\"" >> ~/.zprofile && source ~/.zprofile
export PATH=$(pwd)/ngc-cli:$PATH
popd
ngc config set
which ngc

Containerd

sudo install -m 0755 -d /etc/apt/keyrings
sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
sudo chmod a+r /etc/apt/keyrings/docker.asc

echo \
  "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
  $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
  sudo tee /etc/apt/sources.list.d/docker.list > /dev/null

sudo apt -y update && sudo apt -y install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
sudo groupadd docker && sudo usermod -aG docker $USER && newgrp docker
sudo setfacl -m user:$USER:rw /var/run/docker.sock

• Logout

docker run hello-world
sudo systemctl enable docker.service
sudo systemctl enable containerd.service

Nvidia Container Toolkit

curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
  && curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
    sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
    sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
    
sudo apt -y update && sudo apt -y install nvidia-container-toolkit
sudo nvidia-ctk runtime configure --runtime=docker

• Modify /etc/docker/daemon.json

{
    "default-runtime": "nvidia",
    "default-shm-size": "2G",
    "runtimes": {
        "nvidia": {
            "path": "nvidia-container-runtime",
            "runtimeArgs": []
        }
    }
}

• Restart sudo systemctl restart docker
• Test docker run --rm --gpus all ubuntu nvidia-smi

Post

Intel IGP

• Get PCI ID lspci -d 8086::0300
• Create conf file sudo touch /etc/X11/xorg.conf
• Add content sudo vi /etc/X11/xorg.conf

Section "Device"
    Identifier "Device0"
    BusID "PCI:0:2:0"
    Driver "modesetting"
EndSection

Section "Screen"
    Identifier "Screen0"
    Device "Device0"
EndSection

GPU Power Management

• Create udev rules file sudo touch /lib/udev/rules.d/80-nvidia-pm.rules
• Add content sudo vi /lib/udev/rules.d/80-nvidia-pm.rules

# Remove NVIDIA USB xHCI Host Controller devices, if present
ACTION=="add", SUBSYSTEM=="pci", ATTR{vendor}=="0x10de", ATTR{class}=="0x0c0330", ATTR{remove}="1"

# Remove NVIDIA USB Type-C UCSI devices, if present
ACTION=="add", SUBSYSTEM=="pci", ATTR{vendor}=="0x10de", ATTR{class}=="0x0c8000", ATTR{remove}="1"

# Enable runtime PM for NVIDIA VGA controller devices
ACTION=="add", SUBSYSTEM=="pci", ATTR{vendor}=="0x10de", ATTR{class}=="0x030000", TEST=="power/control", ATTR{power/control}="auto"

# Enable runtime PM for NVIDIA Audio controller devices
ACTION=="add", SUBSYSTEM=="pci", ATTR{vendor}=="0x10de", ATTR{class}=="0x040300", TEST=="power/control", ATTR{power/control}="auto"

• Reboot sudo reboot

Disable a udev rule

sudo cp /lib/udev/rules.d/40-vm-hotadd.rules /etc/udev/rules.d
sudo sed -i '/SUBSYSTEM=="memory", ACTION=="add"/d' /etc/udev/rules.d/40-vm-hotadd.rules
sudo reboot

Next Steps

Configure Ubuntu