# GPU Statistics

This function block provides a quick visual overview of the GPU currently available on the machine. It shows driver version, memory usage, temperature and usage values in a compact textual form inside the block UI.

## 📥 Inputs <a href="#inputs" id="inputs"></a>

`No input sockets`

## 📤 Outputs <a href="#outputs" id="outputs"></a>

`No output sockets`

## 🕹️ Controls <a href="#controls" id="controls"></a>

`GPU Info` A read-only text area that displays the current GPU information (name, driver, memory free/used/total, RAM utilization, temperature and usage).

## 🎨 Features <a href="#features" id="features"></a>

* Real-time textual summary of GPU state shown inside the block UI.
* Helpful for quick health checks when running compute-heavy workflows.
* Simple, distraction-free presentation suitable for monitoring while the scenario runs.

## 📝 Usage Instructions <a href="#usage" id="usage"></a>

1. Place the block into your scenario canvas.
2. Run the scenario — the block will update the `GPU Info` text with the latest GPU status.
3. Inspect the block regularly to check temperature, memory usage and overall GPU load.

## 📊 Evaluation <a href="#evaluation" id="evaluation"></a>

On each evaluation step the block refreshes the displayed GPU information so you always see the latest status in the block UI.

## 💡 Tips and Tricks <a href="#tips-and-tricks" id="tips-and-tricks"></a>

* To keep a historical log of GPU status, use `CSV Export` to save readings periodically (combine with a timer or logger flow).
* If you want visual trends, route numeric values into `Scope` (use intermediary blocks that extract numeric values from the textual summary if needed).
* Create simple alarms: combine `Number Input` to set thresholds and `Greater` to compare a numeric reading (temperature or usage) and trigger `Send Mail` or `Stop` to alert or halt a scenario when limits are exceeded.
* Use alongside `GPU Statistics` as a monitoring companion when running heavy workloads such as model inference (for example when using `Object Detection (D-FINE)` or `Depth Estimation (DepthAny. V2)`), to watch resource usage and avoid out-of-memory issues.

## 🛠️ Troubleshooting <a href="#troubleshooting" id="troubleshooting"></a>

* If the block shows placeholders (e.g., "-") verify that a GPU is installed and drivers are available on the system.
* If reported values look inconsistent, double-check your system GPU drivers and restart the application to refresh hardware queries.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.augelab.com/function-blocks/input-output/outputs-exports/gpu-statistics.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.