🧩 C++ CUDA Starter (Windows + WSL2)

A minimal, production-ready CUDA C++ starter project for learning and testing GPU kernels in Windows + WSL2 environments.
Designed for reproducible builds, clean debugging, and automated testing.

---

🚀 Key Features

• CUDA C++ example: src/vector_add.cu
• Cross-platform build via CMake
• GPU architecture targeting (Compute Capability 8.9, RTX 4070 SUPER)
• .vscode/launch.json for GDB debugging
• CTest integration for regression testing
• check_cuda_starter_status.sh for device info + benchmark

---

🧱 Project Structure

cuda-starter-windows-wsl/
├── src/
│   └── vector_add.cu
├── build/                # Auto-generated by CMake
├── .vscode/              # VS Code launch configuration
├── .gitignore
├── CMakeLists.txt
├── check_cuda_starter_status.sh
└── README.md

---

⚙️ Build & Run

From project root:

cmake -S . -B build -DCMAKE_BUILD_TYPE=Release
cmake --build build -j
./build/vector_add

You should see output similar to:

Success! All 1,048,576 elements added correctly.

---

🧪 Testing with CTest

Run the integrated test target:

cd build
ctest

Expected:

Test project /path/to/build
    Start 1: vector_add_run
1/1 Test #1: vector_add_run ...   Passed
100% tests passed, 0 tests failed out of 1

---

⚡ Status Check Script

A helper script validates your CUDA environment and runs a quick benchmark.

./check_cuda_starter_status.sh

Typical output:

GPU: NVIDIA GeForce RTX 4070 SUPER (Compute Capability 8.9)
Driver Version: 560.xx, CUDA 12.8
Vector Add completed in 0.5 ms

---

🧠 Environment

Component	Recommended Version
CUDA Toolkit	12.8+
CMake	≥ 3.24
Compiler	g++ or nvcc
GPU	RTX 4070 SUPER (SM 8.9)
OS	Windows 11 + WSL2 (Ubuntu 22.04)

---

🛠 VS Code Integration

Launch configuration is in .vscode/launch.json:

{
  "name": "Run vector_add",
  "type": "cppdbg",
  "request": "launch",
  "program": "${workspaceFolder}/build/vector_add",
  "cwd": "${workspaceFolder}",
  "MIMode": "gdb"
}

Run or debug directly with F5 inside VS Code.

---

📚 References

• CUDA by Example — Sanders & Kandrot
• NVIDIA CUDA Toolkit Docs
• CMake + CUDA Language Guide

---

© 2025 Samuel Huang — Toronto, ON
Clean CUDA template maintained for learning and professional use.