[Perf] Linux/arm64: 2 Regressions on 9/1/2026 12:38:34 PM +00:00

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [bdcba57531224815fbbc0fbb5ee23a1d3876d43a](https://github.com/dotnet/runtime/commit/bdcba57531224815fbbc0fbb5ee23a1d3876d43a)
Compare | [f00a5ba2dde9f648bcd9ac77411d1a8596449303](https://github.com/dotnet/runtime/commit/f00a5ba2dde9f648bcd9ac77411d1a8596449303)
Diff | [Diff](https://github.com/dotnet/runtime/compare/bdcba57531224815fbbc0fbb5ee23a1d3876d43a...f00a5ba2dde9f648bcd9ac77411d1a8596449303)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Regressions in System.IO.Compression.Zstandard

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

• [Compress - Duration of single invocation]()
• [ADX - Test Multi Config Graph]()

| 463.91 μs | 745.60 μs | 1.61 | 0.14 | False | | |

![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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.IO.Compression.Zstandard*'
```

### System.IO.Compression.Zstandard.Compress(level: Fastest, file: "alice29.txt")

#### 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)

---

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [bdcba57531224815fbbc0fbb5ee23a1d3876d43a](https://github.com/dotnet/runtime/commit/bdcba57531224815fbbc0fbb5ee23a1d3876d43a)
Compare | [f00a5ba2dde9f648bcd9ac77411d1a8596449303](https://github.com/dotnet/runtime/commit/f00a5ba2dde9f648bcd9ac77411d1a8596449303)
Diff | [Diff](https://github.com/dotnet/runtime/compare/bdcba57531224815fbbc0fbb5ee23a1d3876d43a...f00a5ba2dde9f648bcd9ac77411d1a8596449303)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Regressions in System.IO.Compression.ZLib

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

• [DecompressAsync - Duration of single invocation]()
• [ADX - Test Multi Config Graph]()

| 313.76 μs | 506.96 μs | 1.62 | 0.08 | False | | |

![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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.IO.Compression.ZLib*'
```

### System.IO.Compression.ZLib.DecompressAsync(level: Fastest, file: "TestDocument.pdf")

#### 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 by running the provided benchmarks_ci.py commands for System.IO.Compression.Zstandard and System.IO.Compression.ZLib, then compare the linked baseline and test reports on Linux/arm64. Use the linked performance and profiling workflow documentation to investigate the regressions; done means identifying the cause and restoring the affected benchmark results.

Written by the indexing model from the issue text.