> ## Documentation Index
> Fetch the complete documentation index at: https://docs.rightnowai.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Benchmarking

> Measure and compare CUDA kernel performance.

# Benchmarking

Test your CUDA kernel performance and compare different implementations.

## Quick Start

<Steps>
  <Step title="Open Benchmark Panel">
    Click "Benchmark" in the bottom panel or use command palette: "CUDA: Open Benchmark View".
  </Step>

  <Step title="Configure Benchmark">
    Set iterations, warmup runs, and data sizes in the configuration view.
  </Step>

  <Step title="Run Benchmark">
    Click "Run Benchmark" button and watch results appear in real-time.
  </Step>

  <Step title="Compare Kernels">
    Select two benchmarked kernels to see side-by-side performance comparison.
  </Step>
</Steps>

## How to Use

<Frame>
  <img src="https://mintcdn.com/rightnowai/MyRQ6ILCdazu_XAM/images/benchmark-configuration.webp?fit=max&auto=format&n=MyRQ6ILCdazu_XAM&q=85&s=389804f27567579b6adaa18ce2df9a5c" alt="Benchmark Configuration" width="2347" height="1256" data-path="images/benchmark-configuration.webp" />
</Frame>

### Configuration View

Set your benchmark parameters:

* **Iterations**: Number of times to run (e.g., 100)
* **Warmup Runs**: Initial runs to stabilize GPU (e.g., 10)
* **Data Sizes**: Small, medium, large test configurations

### Running Benchmark

1. Configure your settings
2. Click "Run Benchmark" button
3. Watch progress bar as results stream in
4. See live metrics updating

### During Execution

<Frame>
  <img src="https://mintcdn.com/rightnowai/MyRQ6ILCdazu_XAM/images/benchmark-running.webp?fit=max&auto=format&n=MyRQ6ILCdazu_XAM&q=85&s=b464641a6d8632da89441c792a055ad1" alt="Benchmark Running" width="2235" height="1243" data-path="images/benchmark-running.webp" />
</Frame>

* Progress indicator shows completion percentage
* Results appear in real-time
* Current iteration displayed
* Stop button available to cancel

## What You See

### Live Results

* **Running**: Shows current iteration (e.g., "Running 45/100")
* **Time Graph**: Real-time performance visualization
* **Statistics**: Live mean, min, max updates

### Final Results

* **Execution Time**: Average kernel runtime
* **Statistical Analysis**: Mean, median, standard deviation
* **Performance Metrics**: Throughput, efficiency
* **Export Button**: Save results

## Comparing Kernels

<Frame>
  <img src="https://mintcdn.com/rightnowai/MyRQ6ILCdazu_XAM/images/benchmark-comparison.webp?fit=max&auto=format&n=MyRQ6ILCdazu_XAM&q=85&s=14c4e423ed6af83c13a7bee96b5af443" alt="Benchmark Comparison" width="2262" height="1281" data-path="images/benchmark-comparison.webp" />
</Frame>

1. Benchmark your original kernel
2. Benchmark your optimized version
3. Click "Compare" button
4. View comparison:
   * **Side-by-side metrics**
   * **Speedup percentage** (e.g., "2.3x faster")
   * **Winner highlighted** in green

## Tips

<Check>
  **Best Practices**

  * Use at least 100 iterations for accuracy
  * Always include warmup runs
  * Keep data sizes consistent for comparison
  * Benchmark before and after optimization
</Check>

<Warning>
  **Important**

  * Close other GPU applications for accurate results
  * Let GPU stabilize between tests
  * Use same configuration when comparing kernels
</Warning>

## Screenshots Needed

1. **Benchmark configuration view** - Shows settings panel
2. **Benchmark running** - Progress bar and live results
3. **Kernel comparison** - Side-by-side performance metrics

## Next Steps

* [GPU Emulation](/gpu-emulation) - Test on different GPUs
* [Remote GPU Execution](/remote-gpu-execution) - Benchmark on cloud GPUs
* [Core Features](/core-features) - AI optimization suggestions