Closed performanceautofiler[bot] closed 1 year ago
Name | Value |
---|---|
Architecture | x64 |
OS | Windows 10.0.19042 |
Queue | OwlWindows |
Baseline | 7526a4c6a0a095670f1135d983a349b4e867f2e2 |
Compare | c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8 |
Diff | Diff |
Configs | CompilationMode:tiered, RunKind:micro |
Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
---|---|---|---|---|---|---|---|---|---|---|
[ICollection - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/System.Collections.ContainsTrue(String).ICollection(Size%3a%20512).html>) | 418.24 ÎĽs | 450.05 ÎĽs | 1.08 | 0.08 | True |
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.ContainsTrue<String>*'
Name | Value |
---|---|
Architecture | x64 |
OS | Windows 10.0.19042 |
Queue | OwlWindows |
Baseline | 7526a4c6a0a095670f1135d983a349b4e867f2e2 |
Compare | c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8 |
Diff | Diff |
Configs | CompilationMode:tiered, RunKind:micro |
Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
---|---|---|---|---|---|---|---|---|---|---|
[ScalarValueTypeObj - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/PerfLabTests.CastingPerf.ScalarValueTypeObj.html>) | 278.52 ÎĽs | 306.35 ÎĽs | 1.10 | 0.03 | False | |||||
[ObjrefValueTypeObj - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/PerfLabTests.CastingPerf.ObjrefValueTypeObj.html>) | 278.41 ÎĽs | 306.31 ÎĽs | 1.10 | 0.04 | False | |||||
[IntObj - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/PerfLabTests.CastingPerf.IntObj.html>) | 278.44 ÎĽs | 306.46 ÎĽs | 1.10 | 0.04 | False | |||||
[FooObjIsFoo - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/PerfLabTests.CastingPerf.FooObjIsFoo.html>) | 278.60 ÎĽs | 306.49 ÎĽs | 1.10 | 0.04 | False |
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'PerfLabTests.CastingPerf*'
Name | Value |
---|---|
Architecture | x64 |
OS | Windows 10.0.19042 |
Queue | OwlWindows |
Baseline | 7526a4c6a0a095670f1135d983a349b4e867f2e2 |
Compare | c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8 |
Diff | Diff |
Configs | CompilationMode:tiered, RunKind:micro |
Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
---|---|---|---|---|---|---|---|---|---|---|
[Hypot - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/System.MathBenchmarks.Single.Hypot.html>) | 15.32 ÎĽs | 16.72 ÎĽs | 1.09 | 0.02 | False | |||||
[Exp - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/System.MathBenchmarks.Single.Exp.html>) | 19.50 ÎĽs | 20.89 ÎĽs | 1.07 | 0.03 | False |
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.MathBenchmarks.Single*'
Name | Value |
---|---|
Architecture | x64 |
OS | Windows 10.0.19042 |
Queue | OwlWindows |
Baseline | 7526a4c6a0a095670f1135d983a349b4e867f2e2 |
Compare | c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8 |
Diff | Diff |
Configs | CompilationMode:tiered, RunKind:micro |
Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
---|---|---|---|---|---|---|---|---|---|---|
[FrozenDictionaryOptimized - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/System.Collections.TryGetValueFalse(Int32%2c%20Int32).FrozenDictionaryOptimized(Size%3a%20512).html>) | 2.02 ÎĽs | 2.30 ÎĽs | 1.14 | 0.03 | False |
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.TryGetValueFalse<Int32, Int32>*'
Name | Value |
---|---|
Architecture | x64 |
OS | Windows 10.0.19042 |
Queue | OwlWindows |
Baseline | 7526a4c6a0a095670f1135d983a349b4e867f2e2 |
Compare | c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8 |
Diff | Diff |
Configs | CompilationMode:tiered, RunKind:micro |
Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
---|---|---|---|---|---|---|---|---|---|---|
[Span - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/System.Collections.ContainsFalse(String).Span(Size%3a%20512).html>) | 712.71 ÎĽs | 814.97 ÎĽs | 1.14 | 0.19 | False |
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.ContainsFalse<String>*'
Name | Value |
---|---|
Architecture | x64 |
OS | Windows 10.0.19042 |
Queue | OwlWindows |
Baseline | 7526a4c6a0a095670f1135d983a349b4e867f2e2 |
Compare | c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8 |
Diff | Diff |
Configs | CompilationMode:tiered, RunKind:micro |
Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
---|---|---|---|---|---|---|---|---|---|---|
[EmptyTakeSelectToArray - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/System.Linq.Tests.Perf_Enumerable.EmptyTakeSelectToArray.html>) | 17.54 ns | 19.10 ns | 1.09 | 0.12 | False |
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Linq.Tests.Perf_Enumerable*'
Name | Value |
---|---|
Architecture | x64 |
OS | Windows 10.0.19042 |
Queue | OwlWindows |
Baseline | 7526a4c6a0a095670f1135d983a349b4e867f2e2 |
Compare | c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8 |
Diff | Diff |
Configs | CompilationMode:tiered, RunKind:micro |
Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
---|---|---|---|---|---|---|---|---|---|---|
[IntObj - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/PerfLabTests.CastingPerf2.CastingPerf.IntObj.html>) | 111.38 ÎĽs | 167.04 ÎĽs | 1.50 | 0.02 | False |
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'PerfLabTests.CastingPerf2.CastingPerf*'
Name | Value |
---|---|
Architecture | x64 |
OS | Windows 10.0.19042 |
Queue | OwlWindows |
Baseline | 7526a4c6a0a095670f1135d983a349b4e867f2e2 |
Compare | c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8 |
Diff | Diff |
Configs | CompilationMode:tiered, RunKind:micro |
Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
---|---|---|---|---|---|---|---|---|---|---|
[FrozenDictionary - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/System.Collections.IterateForEach(String).FrozenDictionary(Size%3a%20512).html>) | 2.44 ÎĽs | 2.59 ÎĽs | 1.06 | 0.09 | False |
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.IterateForEach<String>*'
Name | Value |
---|---|
Architecture | x64 |
OS | Windows 10.0.19042 |
Queue | OwlWindows |
Baseline | 7526a4c6a0a095670f1135d983a349b4e867f2e2 |
Compare | c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8 |
Diff | Diff |
Configs | CompilationMode:tiered, RunKind:micro |
Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
---|---|---|---|---|---|---|---|---|---|---|
[GetFileNameWithoutExtension - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/System.IO.Tests.Perf_Path.GetFileNameWithoutExtension.html>) | 27.57 ns | 30.38 ns | 1.10 | 0.07 | False |
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.IO.Tests.Perf_Path*'
Name | Value |
---|---|
Architecture | x64 |
OS | Windows 10.0.19042 |
Queue | OwlWindows |
Baseline | 7526a4c6a0a095670f1135d983a349b4e867f2e2 |
Compare | c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8 |
Diff | Diff |
Configs | CompilationMode:tiered, RunKind:micro |
Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
---|---|---|---|---|---|---|---|---|---|---|
[TryParseSingle - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/System.Buffers.Text.Tests.Utf8ParserTests.TryParseSingle(value%3a%2012345).html>) | 31.07 ns | 32.98 ns | 1.06 | 0.01 | False |
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Buffers.Text.Tests.Utf8ParserTests*'
Name | Value |
---|---|
Architecture | x64 |
OS | Windows 10.0.19042 |
Queue | OwlWindows |
Baseline | 7526a4c6a0a095670f1135d983a349b4e867f2e2 |
Compare | c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8 |
Diff | Diff |
Configs | CompilationMode:tiered, RunKind:micro |
Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
---|---|---|---|---|---|---|---|---|---|---|
[WriteAsciiCharArray - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/System.IO.Tests.BinaryWriterExtendedTests.WriteAsciiCharArray(StringLengthInChars%3a%202000000).html>) | 81.54 ÎĽs | 88.34 ÎĽs | 1.08 | 0.00 | True |
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.IO.Tests.BinaryWriterExtendedTests*'
Name | Value |
---|---|
Architecture | x64 |
OS | Windows 10.0.19042 |
Queue | OwlWindows |
Baseline | 7526a4c6a0a095670f1135d983a349b4e867f2e2 |
Compare | c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8 |
Diff | Diff |
Configs | CompilationMode:tiered, RunKind:micro |
Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
---|---|---|---|---|---|---|---|---|---|---|
[benchMonteCarlo - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/SciMark2.kernel.benchMonteCarlo.html>) | 732.58 ms | 776.09 ms | 1.06 | 0.01 | False |
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'SciMark2.kernel*'
Name | Value |
---|---|
Architecture | x64 |
OS | Windows 10.0.19042 |
Queue | OwlWindows |
Baseline | 7526a4c6a0a095670f1135d983a349b4e867f2e2 |
Compare | c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8 |
Diff | Diff |
Configs | CompilationMode:tiered, RunKind:micro |
Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
---|---|---|---|---|---|---|---|---|---|---|
[IterateTryGetArray - Duration of single invocation](<https://pvscmdupload.blob.core.windows.net/reports/allTestHistory/refs/heads/main_x64_Windows 10.0.19042/amd/System.Buffers.Tests.ReadOnlySequenceTests(Char).IterateTryGetArray.html>) | 6.89 ns | 7.97 ns | 1.16 | 0.01 | False |
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Buffers.Tests.ReadOnlySequenceTests<Char>*'
@cincuranet - can you check the commit range between 4/15 and 4/17 of when it regressed? @AndyAyersMS - most likely from https://github.com/dotnet/runtime/pull/84875.
@kunalspathak The regression first occurred between https://github.com/dotnet/runtime/compare/9c02b25f08c8f1aaf7811446325ac9f873efa451...e92289a03ef47cd3ea2ada2cfe1c0c3abd04f196 or possibly https://github.com/dotnet/runtime/compare/2d833f43d4158c39ff62e57bf0f8d58b93935ae4...e92289a03ef47cd3ea2ada2cfe1c0c3abd04f196 (taking System.Collections.Tests.Perf_BitArray.BitArraySetAll(Size: 512)
and System.Collections.Tests.Perf_BitArray.BitArrayOr(Size: 512)
).
Thanks @cincuranet for finding out. @AndyAyersMS - could this be from https://github.com/dotnet/runtime/pull/84817?
Tagging subscribers to this area: @JulieLeeMSFT, @jakobbotsch See info in area-owners.md if you want to be subscribed.
Author: | performanceautofiler[bot] |
---|---|
Assignees: | AndyAyersMS |
Labels: | `os-windows`, `arch-x64`, `area-CodeGen-coreclr`, `untriaged`, `runtime-coreclr`, `needs-area-label` |
Milestone: | - |
Note regression in System.Collections.Tests.Perf_BitArray.BitArraySetAll(Size: 512)
is amd64 (orange) only, not seeng this on intel (blue)
Similarly for System.Collections.Tests.Perf_BitArray.BitArrayOr(Size: 512)
Seems like this has also fixed itself (somewhat) at least the worst cases:
Will have to dig through some the others to see if there's anything that is not back to "normal" here.
Here's the full set, sorted from worst to least worst.
Note we are just evaluating the regression between 4/12 and 4/17 here.
Ratio | Test | Notes | |
---|---|---|---|
3.19 | System.Collections.Tests.Perf_BitArray.BitArraySetAll(Size: 512) | Fixed itself | |
1.61 | System.Collections.Tests.Perf_BitArray.BitArrayNot(Size: 512) | Fixed itself | |
1.50 | PerfLabTests.CastingPerf2.CastingPerf.IntObj | Bistable | |
1.30 | System.Collections.Tests.Perf_BitArray.BitArrayOr(Size: 512) | Fixed itself | |
1.30 | System.Collections.Tests.Perf_BitArray.BitArrayAnd(Size: 512) | Fixed itself | |
1.22 | System.Numerics.Tests.Perf_BigInteger.Subtract(arguments: 16,16 bits) | Still regressed Analysis | |
1.20 | System.Collections.Tests.Perf_BitArray.BitArrayXor(Size: 512) | Fixed itself | |
1.18 | System.Text.Json.Tests.Perf_Deep.WriteDeepUtf16(Formatted: False, SkipValidation: True) | Fixed itself | |
1.16 | System.Tests.Perf_Enum.ToString_Flags(value: 32) | Still regressed | |
1.16 | System.Buffers.Tests.ReadOnlySequenceTests<Char>.IterateTryGetArray | Fixed itself | |
1.14 | System.Collections.TryGetValueFalse<Int32, Int32>.FrozenDictionaryOptimized(Size: 512) | Bistable | |
1.14 | System.Collections.ContainsFalse<String>.Span(Size: 512) | Still regressed | |
1.13 | System.Memory.Span<Int32>.EndsWith(Size: 512) | Multi-stable | |
1.13 | System.Tests.Perf_Single.ToStringWithFormat(value: -3.4028235E+38, format: "G17") | Fixed itself | |
1.11 | System.Text.Tests.Perf_Encoding.GetBytes(size: 16, encName: "utf-8") | Still regressed | |
1.10 | PerfLabTests.CastingPerf.ScalarValueTypeObj | bistable | |
1.10 | PerfLabTests.CastingPerf.ObjrefValueTypeObj | bistable | |
1.10 | PerfLabTests.CastingPerf.IntObj | bistable | |
1.10 | PerfLabTests.CastingPerf.FooObjIsFoo | bistable | |
1.10 | System.Tests.Perf_Single.ToStringWithFormat(value: 3.4028235E+38, format: "G17") | Fixed itself | |
1.10 | System.Tests.Perf_Double.ToStringWithFormat(value: -1.7976931348623157E+308, format: "G17") | Fixed itself | |
1.10 | System.IO.Tests.Perf_Path.GetFileNameWithoutExtension | Still regressed | |
1.09 | System.Tests.Perf_Enum.ToString_Flags(value: 36) | Still regressed | |
1.09 | System.MathBenchmarks.Single.Hypot | bistable | |
1.09 | System.Linq.Tests.Perf_Enumerable.EmptyTakeSelectToArray | Fixed itself | |
1.08 | System.Numerics.Tests.Perf_BigInteger.ToStringX(numberString: 123) | Fixed itself | |
1.08 | System.Collections.ContainsTrue<String>.ICollection(Size: 512) | Still regressed | |
1.08 | System.IO.Tests.BinaryWriterExtendedTests.WriteAsciiCharArray(StringLengthInChars: 2000000) | Fixed itself | |
1.07 | System.MathBenchmarks.Single.Exp | bistable | |
1.06 | System.Collections.IterateForEach<String>.FrozenDictionary(Size: 512) | [Fixed itself] | (https://github.com/dotnet/runtime/issues/85472#issuecomment-1548836769) |
1.06 | System.Buffers.Text.Tests.Utf8ParserTests.TryParseSingle(value: 12345) | Still regressed | |
1.06 | SciMark2.kernel.benchMonteCarlo | bistable | |
1.06 | System.Tests.Perf_Double.ToStringWithFormat(value: 1.7976931348623157E+308, format: "G") | Fixed itself | |
1.06 | System.Tests.Perf_Double.ToStringWithFormat(value: -1.7976931348623157E+308, format: "G") | Fixed itself | |
1.06 | System.Numerics.Tests.Perf_BitOperations.LeadingZeroCount_ulong | noisy |
8 benchmarks that are still regressed as of 5/15
More that are no longer regressed
More that are no longer regressed
The regression on 4/14 is amd64 only, about 2ns slowdown.
Since then things have gotten even worse, the regression on 5/2 looks like it may be from https://github.com/dotnet/runtime/pull/85620 (see https://github.com/dotnet/perf-autofiling-issues/issues/17605) which was (hopefully) fixed by https://github.com/dotnet/runtime/pull/86246.
So we should check back in a day or two and see where this test has ended up.
00.70% 2.6E+05 ? Unknown
43.63% 1.624E+07 Tier-1 [System.Runtime.Numerics]BigInteger.Subtract(value class System.ReadOnlySpan`1<unsigned int32>,int32,value class System.ReadOnlySpan`1<unsigned int32>,int32)
28.10% 1.046E+07 Tier-1 [MicroBenchmarks]Perf_BigInteger.Subtract(class BigIntegers)
13.41% 4.99E+06 native coreclr.dll (mostly checked write barrier)
08.92% 3.32E+06 Tier-1 [System.Runtime.Numerics]BigInteger..ctor(int64)
04.67% 1.74E+06 Tier-1 [fbbfaa49-80f2-4fb3-b341-975678a5e8cd]Runnable_0.WorkloadActionUnroll(int64)
00.32% 1.2E+05 native clrjit.dll
00.11% 4E+04 native ntoskrnl.exe
00.05% 2E+04 native ntdll.dll
This seems to be largely fixed, indeed improved by PGO, but has recently back slid some.
The regression on 4/14 is amd64 only, about 4ns slowdown.
Collated and updated. First few are bimodal, remainder are small.
Notes | Recent Score | Orig Score | x64-win-amd | Benchmark |
---|---|---|---|---|
1.50 | 1.50 | 1.50 1.50 |
PerfLabTests.CastingPerf2.CastingPerf.IntObj | |
1.48 | 3.19 | 1.48 3.19 |
System.Collections.Tests.Perf_BitArray.BitArraySetAll(Size: 512) | |
1.48 | 1.61 | 1.48 1.61 |
System.Collections.Tests.Perf_BitArray.BitArrayNot(Size: 512) | |
1.25 | 1.13 | 1.25 1.13 |
System.Memory.Span(Int32).EndsWith(Size: 512) | |
1.25 | 1.22 | 1.25 1.22 |
System.Numerics.Tests.Perf_BigInteger.Subtract(arguments: 16,16 bits) | |
1.10 | 1.10 | 1.10 1.10 |
PerfLabTests.CastingPerf.FooObjIsFoo | |
1.10 | 1.10 | 1.10 1.10 |
PerfLabTests.CastingPerf.IntObj | |
1.10 | 1.10 | 1.10 1.10 |
PerfLabTests.CastingPerf.ObjrefValueTypeObj | |
1.10 | 1.10 | 1.10 1.10 |
PerfLabTests.CastingPerf.ScalarValueTypeObj | |
1.07 | 1.14 | 1.07 1.14 |
System.Collections.ContainsFalse(String).Span(Size: 512) | |
1.07 | 1.07 | 1.07 1.07 |
System.MathBenchmarks.Single.Exp | |
1.06 | 1.06 | 1.06 1.06 |
System.Collections.IterateForEach(String).FrozenDictionary(Size: 512) | |
1.04 | 1.30 | 1.04 1.30 |
System.Collections.Tests.Perf_BitArray.BitArrayOr(Size: 512) | |
1.03 | 1.06 | 1.03 1.06 |
System.Numerics.Tests.Perf_BitOperations.LeadingZeroCount_ulong | |
1.01 | 1.06 | 1.01 1.06 |
System.Buffers.Text.Tests.Utf8ParserTests.TryParseSingle(value: 12345) | |
0.99 | 1.08 | 0.99 1.08 |
System.Collections.ContainsTrue(String).ICollection(Size: 512) | |
0.97 | 1.08 | 0.97 1.08 |
System.IO.Tests.BinaryWriterExtendedTests.WriteAsciiCharArray(StringLengthInChars: 2000000) | |
0.94 | 1.30 | 0.94 1.30 |
System.Collections.Tests.Perf_BitArray.BitArrayAnd(Size: 512) | |
0.94 | 1.08 | 0.94 1.08 |
System.Numerics.Tests.Perf_BigInteger.ToStringX(numberString: 123) | |
0.93 | 1.16 | 0.93 1.16 |
System.Tests.Perf_Enum.ToString_Flags(value: 32) | |
0.93 | 1.09 | 0.93 1.09 |
System.Tests.Perf_Enum.ToString_Flags(value: 36) | |
0.93 | 1.11 | 0.93 1.11 |
System.Text.Tests.Perf_Encoding.GetBytes(size: 16, encName: "utf-8") | |
0.92 | 1.16 | 0.92 1.16 |
System.Buffers.Tests.ReadOnlySequenceTests(Char).IterateTryGetArray | |
0.88 | 1.06 | 0.88 1.06 |
SciMark2.kernel.benchMonteCarlo | |
0.87 | 1.06 | 0.87 1.06 |
System.Tests.Perf_Double.ToStringWithFormat(value: 1.7976931348623157E+308, format: "G") | |
0.87 | 1.20 | 0.87 1.20 |
System.Collections.Tests.Perf_BitArray.BitArrayXor(Size: 512) | |
0.86 | 1.06 | 0.86 1.06 |
System.Tests.Perf_Double.ToStringWithFormat(value: -1.7976931348623157E+308, format: "G") | |
0.86 | 1.18 | 0.86 1.18 |
System.Text.Json.Tests.Perf_Deep.WriteDeepUtf16(Formatted: False, SkipValidation: True) | |
0.83 | 1.10 | 0.83 1.10 |
System.Tests.Perf_Double.ToStringWithFormat(value: -1.7976931348623157E+308, format: "G17") | |
0.82 | 1.09 | 0.82 1.09 |
System.MathBenchmarks.Single.Hypot | |
0.80 | 1.10 | 0.80 1.10 |
System.Tests.Perf_Single.ToStringWithFormat(value: 3.4028235E+38, format: "G17") | |
0.78 | 1.09 | 0.78 1.09 |
System.Linq.Tests.Perf_Enumerable.EmptyTakeSelectToArray | |
0.76 | 1.10 | 0.76 1.10 |
System.IO.Tests.Perf_Path.GetFileNameWithoutExtension | |
0.74 | 1.13 | 0.74 1.13 |
System.Tests.Perf_Single.ToStringWithFormat(value: -3.4028235E+38, format: "G17") | |
0.66 | 1.14 | 0.66 1.14 |
System.Collections.TryGetValueFalse(Int32, Int32).FrozenDictionaryOptimized(Size: 512) |
Run Information
Regressions in System.Collections.Tests.Perf_BitArray
Test Report
Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
Payloads
Baseline Compare
Run Information
Regressions in System.Tests.Perf_Double
Test Report
Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
Payloads
Baseline Compare
Run Information
Regressions in System.Tests.Perf_Enum
Test Report
Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
Payloads
Baseline Compare
Run Information
Regressions in System.Numerics.Tests.Perf_BitOperations
Test Report
Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
Payloads
Baseline Compare
Run Information
Regressions in System.Text.Json.Tests.Perf_Deep
Test Report
Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
Payloads
Baseline Compare
Run Information
Regressions in System.Memory.Span<Int32>
Test Report
Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
Payloads
Baseline Compare
Run Information
Regressions in System.Numerics.Tests.Perf_BigInteger
Test Report
Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
Payloads
Baseline Compare
Run Information
Regressions in System.Text.Tests.Perf_Encoding
Test Report
Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
Payloads
Baseline Compare
Run Information
Regressions in System.Tests.Perf_Single
Test Report
Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
Payloads
Baseline Compare