[Perf] Linux/x64: 17 Regressions on 9/11/2026 9:48:28 PM +00:00

Open

#79,391 opened on Sep 15, 2026 2 comments 0 reactions 0 assignees View on GitHub

arch-x64 branch-refs/heads/main compilationmode-tiered kind-micro Look Again os-linux perf-regression PGO runkind-micro runtime-coreclr untriaged

Dominant language: No language data
Stars: 10
Forks: 8
PR merge metrics: PR metrics pending

Description

### Run Information

Name | Value
-- | --
Architecture | x64
OS | ubuntu 22.04
Queue | ViperUbuntu
Baseline | [de29e26a4f69da5d446900a6ba9d68ba3ddc5ba9](https://github.com/dotnet/runtime/commit/de29e26a4f69da5d446900a6ba9d68ba3ddc5ba9)
Compare | [0fd08c887c1317055025965cbe829b732fbe942d](https://github.com/dotnet/runtime/commit/0fd08c887c1317055025965cbe829b732fbe942d)
Diff | [Diff](https://github.com/dotnet/runtime/compare/de29e26a4f69da5d446900a6ba9d68ba3ddc5ba9...0fd08c887c1317055025965cbe829b732fbe942d)
Configs | CompilationMode:tiered, RunKind:micro

### Regressions in System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Single>

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

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

| 9.03 ns | 15.74 ns | 1.74 | 0.71 | False | | |
|

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

| 11.35 ns | 15.55 ns | 1.37 | 0.58 | False | | |
|

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

| 13.10 ns | 16.37 ns | 1.25 | 0.61 | False | | |

![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 'System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives*'
```

### System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Single>.BitwiseAnd_Scalar(BufferLength: 128)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Single>.Max_Vector(BufferLength: 128)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Single>.AddMultiply_ScalarMultiplier(BufferLength: 128)

#### 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

### Regressions in System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Int32>

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

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

| 9.93 ns | 15.46 ns | 1.56 | 0.64 | False | | |
|

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

| 11.59 ns | 15.25 ns | 1.32 | 0.49 | False | | |
|

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

| 12.47 ns | 15.30 ns | 1.23 | 0.49 | False | | |

![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 'System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives*'
```

### System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Int32>.Max_Scalar(BufferLength: 128)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Int32>.Max_Vector(BufferLength: 128)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Int32>.BitwiseAnd_Vector(BufferLength: 128)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.IO.Tests.Perf_Path

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

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

| 739.80 ns | 821.85 ns | 1.11 | 0.09 | False | | |
|

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

| 389.72 ns | 412.77 ns | 1.06 | 0.19 | False | | |
|

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

| 81.99 ns | 86.31 ns | 1.05 | 0.02 | False | | |

![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 'System.IO.Tests.Perf_Path*'
```

### System.IO.Tests.Perf_Path.GetFullPathForReallyLongPath

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_Path.GetFullPathForTypicalLongPath

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_Path.GetFullPathNoRedundantSegments

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Numerics.Tensors.Tests.Perf_BinaryIntegerTensorPrimitives<Byte>

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

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

| 4.67 ns | 11.80 ns | 2.53 | 0.24 | False | | |
|

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

| 5.97 ns | 13.01 ns | 2.18 | 0.06 | False | | |

![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 'System.Numerics.Tensors.Tests.Perf_BinaryIntegerTensorPrimitives*'
```

### System.Numerics.Tensors.Tests.Perf_BinaryIntegerTensorPrimitives<Byte>.OnesComplement(BufferLength: 128)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Numerics.Tensors.Tests.Perf_BinaryIntegerTensorPrimitives<Byte>.PopCount(BufferLength: 128)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives<Single>

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

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

| 9.05 ns | 15.46 ns | 1.71 | 0.60 | False | | |
|

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

| 11.63 ns | 15.72 ns | 1.35 | 0.52 | False | | |

![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 'System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives*'
```

### System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives<Single>.Truncate(BufferLength: 128)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives<Single>.FusedMultiplyAdd_ScalarAddend(BufferLength: 128)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Text.Json.Tests.Perf_Base64

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

[WriteByteArrayAsBase64_HeavyEscaping - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 64.77 ns | 71.95 ns | 1.11 | 0.13 | 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
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Json.Tests.Perf_Base64*'
```

### System.Text.Json.Tests.Perf_Base64.WriteByteArrayAsBase64_HeavyEscaping(NumberOfBytes: 1000)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in Loops.StrengthReduction

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

[SumS3Span - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 2.74 μs | 4.36 μs | 1.59 | 0.20 | 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
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'Loops.StrengthReduction*'
```

### Loops.StrengthReduction.SumS3Span

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Tests.Perf_Environment

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

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

| 7.95 μs | 8.48 μs | 1.07 | 0.01 | 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
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Tests.Perf_Environment*'
```

### System.Tests.Perf_Environment.GetEnvironmentVariables

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Collections.Tests.Perf_BitArray

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

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

| 12.09 ns | 20.47 ns | 1.69 | 0.59 | 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
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.Tests.Perf_BitArray*'
```

### System.Collections.Tests.Perf_BitArray.BitArrayOr(Size: 512)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with the regression report and compare the listed baseline and compare commits, then reproduce the affected System.Numerics.Tensors benchmarks using the provided benchmarks_ci.py command. Read src/benchmarks/micro/libraries/System.Numerics.Tensors/Perf_NumberTensorPrimitives.cs at the cited lines and verify that the reported Linux/x64 regressions are explained and addressed, with the benchmark results returning to the expected range.

Written by the indexing model from the issue text.

Assessment

Tech stack: csharp, python, ubuntu
Domain: performance, testing-qa
Issue type: Bug
Difficulty: 4/5
Estimated time: 3-5 days
Activity status: Active
Clarity: Needs clarification
Newbie friendliness: 42/100

[Perf] Linux/x64: 17 Regressions on 9/11/2026 9:48:28 PM +00:00

Description

Contributor guide

Research direction

Assessment

Get new issues in your inbox