[Perf] Linux/x64: 4 Regressions on 8/4/2026 1:32:21 PM +00:00

### Run Information

Name | Value
-- | --
Architecture | x64
OS | ubuntu 22.04
Queue | ViperUbuntu
Baseline | [813f634ceb016018f5acc9bd3c2b16e17dff4686](https://github.com/dotnet/sdk/commit/813f634ceb016018f5acc9bd3c2b16e17dff4686)
Compare | [5da2de22f7c6e2ebe7ed4c16c614b00183145d3c](https://github.com/dotnet/sdk/commit/5da2de22f7c6e2ebe7ed4c16c614b00183145d3c)
Diff | [Diff](https://github.com/dotnet/sdk/compare/813f634ceb016018f5acc9bd3c2b16e17dff4686...5da2de22f7c6e2ebe7ed4c16c614b00183145d3c)
Configs | CompilationMode:tiered, RunKind:imagesharp

### Regressions in SixLabors.ImageSharp.Benchmarks.Codecs.DecodeFilteredPng

Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio
-- | -- | -- | -- | -- | -- | -- | -- | --
|

• [PngFilter0 - Duration of single invocation]()
• 📝 - [Benchmark Source]()
• [ADX - Test Multi Config Graph]()

| 17.96 μs | 20.62 μs | 1.15 | 0.00 | True | | |
|

• [PngFilter2 - Duration of single invocation]()
• 📝 - [Benchmark Source]()
• [ADX - Test Multi Config Graph]()

| 15.57 μs | 17.73 μs | 1.14 | 0.00 | True | | |
|

• [PngFilter1 - Duration of single invocation]()
• 📝 - [Benchmark Source]()
• [ADX - Test Multi Config Graph]()

| 15.31 μs | 17.00 μs | 1.11 | 0.00 | True | | |
|

• [PngFilter3 - Duration of single invocation]()
• 📝 - [Benchmark Source]()
• [ADX - Test Multi Config Graph]()

| 15.15 μs | 16.76 μs | 1.11 | 0.00 | True | | |

![graph]()
![graph]()
![graph]()
![graph]()
[Test Report]()

### Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

```cmd
git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'SixLabors.ImageSharp.Benchmarks.Codecs.DecodeFilteredPng*'
```

### SixLabors.ImageSharp.Benchmarks.Codecs.DecodeFilteredPng.PngFilter0

#### ETL Files

#### Histogram

#### JIT Disasms

### SixLabors.ImageSharp.Benchmarks.Codecs.DecodeFilteredPng.PngFilter2

#### ETL Files

#### Histogram

#### JIT Disasms

### SixLabors.ImageSharp.Benchmarks.Codecs.DecodeFilteredPng.PngFilter1

#### ETL Files

#### Histogram

#### JIT Disasms

### SixLabors.ImageSharp.Benchmarks.Codecs.DecodeFilteredPng.PngFilter3

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

[Profiling workflow for dotnet/runtime repository](https://github.com/dotnet/performance/blob/master/docs/profiling-workflow-dotnet-runtime.md)
[Benchmarking workflow for dotnet/runtime repository](https://github.com/dotnet/performance/blob/master/docs/benchmarking-workflow-dotnet-runtime.md)

Start with src/benchmarks/real-world/ImageSharp/Codecs/DecodeFilteredPng.cs and the reported baseline and comparison commits. Run scripts/benchmarks_ci.py with the DecodeFilteredPng filter, compare the four reported results, and use the linked reports to identify the regression. Done means the four PNG filter benchmarks no longer regress and the results are verified.

Written by the indexing model from the issue text.