[Perf] Windows/x86: 38 Regressions on 8/25/2026 10:44:15 PM +00:00

Open

#78,693 opened on Sep 1, 2026 2 comments 0 reactions 0 assignees View on GitHub

arch-x86 branch-refs/heads/main compilationmode-tiered kind-micro Look Again os-windows perf-regression 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 | x86
OS | Windows 10.0.22631
Queue | ViperWindows
Baseline | [8baacb006f5615ebd705bdf9de98ca5df7bf1ba1](https://github.com/dotnet/runtime/commit/8baacb006f5615ebd705bdf9de98ca5df7bf1ba1)
Compare | [9f18a550aaa91ecd032ac024b67e03559df9e766](https://github.com/dotnet/runtime/commit/9f18a550aaa91ecd032ac024b67e03559df9e766)
Diff | [Diff](https://github.com/dotnet/runtime/compare/8baacb006f5615ebd705bdf9de98ca5df7bf1ba1...9f18a550aaa91ecd032ac024b67e03559df9e766)
Configs | CompilationMode:tiered, RunKind:micro

### Regressions in System.Buffers.Text.Tests.Utf8FormatterTests

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

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

| 106.90 ns | 169.40 ns | 1.58 | 0.03 | False | | |
|

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

| 30.12 ns | 38.32 ns | 1.27 | 0.01 | False | | |
|

[FormatterInt64 - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 19.26 ns | 24.13 ns | 1.25 | 0.01 | False | | |
|

[FormatterUInt64 - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 19.53 ns | 24.32 ns | 1.24 | 0.02 | False | | |
|

[FormatterInt32 - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 5.72 ns | 7.04 ns | 1.23 | 0.04 | False | | |
|

[FormatterUInt32 - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 5.71 ns | 6.92 ns | 1.21 | 0.03 | False | | |
|

[FormatterInt64 - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 22.44 ns | 26.19 ns | 1.17 | 0.01 | False | | |
|

[FormatterInt32 - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 10.10 ns | 11.30 ns | 1.12 | 0.02 | False | | |

![graph]()
![graph]()
![graph]()
![graph]()
![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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Buffers.Text.Tests.Utf8FormatterTests*'
```

### System.Buffers.Text.Tests.Utf8FormatterTests.FormatterDecimal(value: 123456.78900000000430736690760)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Buffers.Text.Tests.Utf8FormatterTests.FormatterDateTimeOffsetNow(value: 12/30/2017 3:45:22 AM -08:00)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Buffers.Text.Tests.Utf8FormatterTests.FormatterInt64(value: 9223372036854775807)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Buffers.Text.Tests.Utf8FormatterTests.FormatterUInt64(value: 18446744073709551615)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Buffers.Text.Tests.Utf8FormatterTests.FormatterInt32(value: 2147483647)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Buffers.Text.Tests.Utf8FormatterTests.FormatterUInt32(value: 4294967295)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Buffers.Text.Tests.Utf8FormatterTests.FormatterInt64(value: -9223372036854775808)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Buffers.Text.Tests.Utf8FormatterTests.FormatterInt32(value: -2147483648)

#### 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.Tests.Perf_Int64

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

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

| 10.50 ns | 19.47 ns | 1.85 | 0.49 | False | | |
|

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

| 22.78 ns | 28.46 ns | 1.25 | 0.01 | False | | |
|

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

| 28.04 ns | 33.73 ns | 1.20 | 0.01 | False | | |
|

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

| 20.08 ns | 23.94 ns | 1.19 | 0.03 | False | | |
|

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

| 23.90 ns | 27.79 ns | 1.16 | 0.02 | False | | |

![graph]()
![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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Tests.Perf_Int64*'
```

### System.Tests.Perf_Int64.ToString(value: 12345)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int64.TryFormat(value: -9223372036854775808)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int64.ToString(value: -9223372036854775808)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int64.TryFormat(value: 9223372036854775807)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int64.ToString(value: 9223372036854775807)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Tests.Perf_Int32

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

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

| 7.44 ns | 11.57 ns | 1.55 | 0.25 | False | | |
|

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

| 9.81 ns | 11.74 ns | 1.20 | 0.09 | False | | |
|

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

| 12.20 ns | 14.50 ns | 1.19 | 0.01 | False | | |
|

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

| 10.13 ns | 11.30 ns | 1.12 | 0.01 | False | | |

![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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Tests.Perf_Int32*'
```

### System.Tests.Perf_Int32.ToString(value: 12345)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int32.ToString(value: 2147483647)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int32.ToString(value: -2147483648)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int32.TryFormat(value: -2147483648)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Tests.Perf_UInt64

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

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

| 7.92 ns | 17.58 ns | 2.22 | 0.44 | False | | |
|

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

| 23.57 ns | 29.61 ns | 1.26 | 0.01 | False | | |
|

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

| 20.35 ns | 24.19 ns | 1.19 | 0.06 | 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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Tests.Perf_UInt64*'
```

### System.Tests.Perf_UInt64.ToString(value: 12345)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_UInt64.ToString(value: 18446744073709551615)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_UInt64.TryFormat(value: 18446744073709551615)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

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

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

[WriteBasicUtf8 - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 1.27 ms | 1.41 ms | 1.11 | 0.01 | False | | |
|

[WriteBasicUtf16 - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 1.27 ms | 1.35 ms | 1.06 | 0.01 | 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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Json.Tests.Perf_Basic*'
```

### System.Text.Json.Tests.Perf_Basic.WriteBasicUtf8(Formatted: False, SkipValidation: True, DataSize: 100000)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Tests.Perf_Basic.WriteBasicUtf16(Formatted: False, SkipValidation: True, DataSize: 100000)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Buffers.Text.Tests.Utf8ParserTests

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

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

| 107.03 ns | 117.76 ns | 1.10 | 0.03 | False | | |
|

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

| 32.13 ns | 33.94 ns | 1.06 | 0.01 | 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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Buffers.Text.Tests.Utf8ParserTests*'
```

### System.Buffers.Text.Tests.Utf8ParserTests.TryParseDecimal(value: 123456.78900000000430736690760)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Buffers.Text.Tests.Utf8ParserTests.TryParseDouble(value: 12345)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Tests.Perf_Version

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

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

| 29.24 ns | 34.18 ns | 1.17 | 0.02 | False | | |
|

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

| 39.47 ns | 44.06 ns | 1.12 | 0.03 | 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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Tests.Perf_Version*'
```

### System.Tests.Perf_Version.TryFormatL

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Version.ToStringL

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Tests.Perf_Int16

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

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

| 8.18 ns | 11.08 ns | 1.35 | 0.18 | False | | |
|

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

| 9.38 ns | 11.65 ns | 1.24 | 0.03 | 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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Tests.Perf_Int16*'
```

### System.Tests.Perf_Int16.ToString(value: 32767)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int16.ToString(value: -32768)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Tests.Perf_UInt32

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

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

| 7.09 ns | 10.75 ns | 1.52 | 0.15 | False | | |
|

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

| 9.80 ns | 11.63 ns | 1.19 | 0.08 | 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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Tests.Perf_UInt32*'
```

### System.Tests.Perf_UInt32.ToString(value: 12345)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_UInt32.ToString(value: 4294967295)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with the linked System.Buffers.Text.Tests.Utf8FormatterTests benchmark source in dotnet/performance, especially Utf8FormatterTests.cs lines 19-49, and compare the listed baseline and test commits. Reproduce the reported Windows x86 tiered microbenchmark regressions and inspect the linked histories and graphs. Done means the regressions are explained and the benchmark results confirm the outcome.

Written by the indexing model from the issue text.

Assessment

Domain: performance
Issue type: Bug
Difficulty: 4/5
Estimated time: 3-5 days
Activity status: Active
Clarity: Needs clarification
Newbie friendliness: 35/100

[Perf] Windows/x86: 38 Regressions on 8/25/2026 10:44:15 PM +00:00

Description

Contributor guide

Research direction

Assessment

Get new issues in your inbox