---
title: "CUDA"
canonical: "https://www.thundercompute.com/glossary/cuda-programming/cuda"
description: "NVIDIA's parallel computing platform and API"
sidebarTitle: "CUDA"
icon: "code"
iconType: "solid"
---

**CUDA (Compute Unified Device Architecture)** is NVIDIA's parallel computing platform and programming model that lets developers run general-purpose code on NVIDIA GPUs.

## Example

```cpp
// CUDA C++ kernel — adds two arrays element-wise
__global__ void add(float *a, float *b, float *c, int n) {
    int i = blockIdx.x * blockDim.x + threadIdx.x;
    if (i < n) c[i] = a[i] + b[i];
}

// Launch with 256 threads per block
add<<<(n + 255) / 256, 256>>>(a, b, c, n);
```

## Key Concepts

- **Host** — the CPU and its memory
- **Device** — the GPU and its memory
- **Kernel** — a function that runs on the GPU
- **CUDA Toolkit** — compiler (`nvcc`), libraries, and profiling tools

## See Also

- [Kernel](/cuda-programming/kernel)
- [Thread, Block, Grid](/cuda-programming/thread-block-grid)