Installation

Detailed installation instructions for different platforms.

System Requirements

Requirement	Minimum	Recommended
CUDA Toolkit	11.0	12.2+
CMake	3.18	3.25+
C++ Compiler	C++17	C++20
GPU Compute	sm_70	sm_80+
RAM	8GB	16GB+

Linux Installation

Ubuntu/Debian

# Install CUDA Toolkit (if not already installed)
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 update
sudo apt install cuda-toolkit-12-2

# Install CMake
sudo apt install cmake

# Verify installation
nvcc --version
cmake --version

CentOS/RHEL

# Add NVIDIA repository
sudo dnf config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel8/x86_64/cuda-rhel8.repo
sudo dnf install cuda-toolkit-12-2

# Install CMake
sudo dnf install cmake

Windows Installation

1. Install CUDA Toolkit from NVIDIA Developer

2. Install Visual Studio 2019 or later with C++ development tools

3. Install CMake from cmake.org

4. Build:

   cmake --preset release
   cmake --build --preset release --config Release

Verify Installation

# Check CUDA
nvcc --version

# Check CMake
cmake --version

# Check GPU
nvidia-smi

# Run quick test
git clone https://github.com/AICL-Lab/mini-image-pipe.git
cd mini-image-pipe
cmake --preset release
cmake --build --preset release
ctest --preset release

Docker (Optional)

FROM nvidia/cuda:12.2-devel-ubuntu22.04

RUN apt update && apt install -y cmake git
WORKDIR /app
COPY . .
RUN cmake --preset release && cmake --build --preset release

CMD ["./build/demo_pipeline"]

docker build -t mini-image-pipe .
docker run --gpus all mini-image-pipe