---
title: "GPU"
canonical: "https://www.thundercompute.com/glossary/gpu-hardware/gpu"
description: "Graphics Processing Unit — a processor designed for parallel computation"
sidebarTitle: "GPU"
icon: "microchip"
iconType: "solid"
---

A **Graphics Processing Unit (GPU)** is a specialized processor originally designed for rendering graphics, now widely used for general-purpose parallel computation including machine learning, scientific simulations, and data processing.

## Example

```python
import torch

# Check if a GPU is available
print(torch.cuda.is_available())       # True
print(torch.cuda.get_device_name(0))   # e.g. "NVIDIA RTX 4090"
```

## Key Characteristics

- **Thousands of cores** optimized for parallel workloads
- **High memory bandwidth** for moving large amounts of data
- **SIMT architecture** — Single Instruction, Multiple Threads

## See Also

- [VRAM](/gpu-hardware/vram)
- [CUDA Cores](/gpu-hardware/cuda-cores)
- [Tensor Cores](/gpu-hardware/tensor-cores)