.NET 7.0 Preview 3 Microbenchmarks Performance Study Report #67976
Labels
area-Meta
tenet-performance
Performance related issue
tracking
This issue is tracking the completion of other related issues.
Comments
adamsitnik
added
area-Meta
tenet-performance
dotnet-issue-labeler
bot
added
the
untriaged
|
Tagging subscribers to this area: @dotnet/area-meta Issue DetailsDataThis time we have covered following configs:
Most of the benchmarks were run on bare-metal machines, some were executed via WSL. This would not be possible without the help from: @AndyAyersMS @carlossanlop @danmoseley @dakersnar @janvorli @jeffhandley @kunalspathak and @sblom who contributed their results and time. The full report generated by the tool is available here. The full report contains also improvements, so if you read it from the end you can see the biggest perf improvements. There are plenty of them! Again, the full historical data turned out to be extremely useful. For details about methodology please read #41871. Preview2 report can be found here. RegressionsBy design
Investigation in progress
Already solved
Noise, flaky or multimodalThe following benchmarks showed up in the report generated by the tool, but were not actual regressions:
Statistics
Total: 105070 Statistics per Architecture
Statistics per Operating System
Statistics per Namespace
Big thanks to everyone involved!
|
adamsitnik
removed
the
untriaged
ghost
locked as resolved and limited conversation to collaborators
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Data
This time we have covered following configs:
Most of the benchmarks were run on bare-metal machines, some were executed via WSL.
This would not be possible without the help from: @AndyAyersMS @carlossanlop @danmoseley @dakersnar @janvorli @jeffhandley @kunalspathak and @sblom who contributed their results and time.
The full report generated by the tool is available here. The full report contains also improvements, so if you read it from the end you can see the biggest perf improvements. There are plenty of them!
Again, the full historical data turned out to be extremely useful. For details about methodology please read #41871. Preview2 report can be found here.
Stress bugs
Regressions
By design
System.Diagnostics.Perf_Process.GetProcessByIdSystem.Text.Json.Serialization.Tests.ReadJson<ArrayList>*Investigation in progress
BenchmarksGame.RegexRedux_1.RunBench,System.Text.RegularExpressions.Tests.Perf_Regex_Industry_Leipzig.Count(Pattern: ".{0,2}(Tom|Sawyer|Huckleberry|Finn)", Options: Compiled)BenchmarksGame.BinaryTrees*,ByteMark.BenchBitOps,System.Tests.Perf_GC<Byte>.NewOperator_Array(length: 1000)System.Text.Tests.Perf_StringBuilder.Append_Char_Capacity(length: 100000)System.IO.Tests.Perf_RandomAccess.ReadScatterAsyncand other async file IO benchmarks have regressed on WindowsSystem.Tests.Perf_Enum.EnumToString(value: Yellow)System.Tests.Perf_DateTime.GetNowPerfLabTests.LowLevelPerf.StaticDelegateLinqBenchmarks.Where00ForXPerfLabTests.StackWalk.WalkSystem.Threading.Tests.Perf_Timer.ScheduleManyThenDisposeManySystem.Tests.Perf_Int32.Parse,System.Tests.Perf_Int16.TryParse,System.Tests.Perf_SByte.TryParseAlready solved
System.Tests.Perf_GC<Char>.AllocateUninitializedArray(length: 10000, pinned: True)CrossLoaderAllocatorHashto not use the GC #67160 (comment)System.Buffers.Tests.ReadOnlySequenceTests<Byte>.IterateGetPositionTenSegmentsSystem.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get_EnumerateHeaders_Validated*,System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get*Noise, flaky or multimodal
The following benchmarks showed up in the report generated by the tool, but were not actual regressions:
System.Collections.Concurrent.Count<String>.Dictionary(Size: 512)System.Numerics.Tests.Perf_VectorOf<*>.*System.Collections.TryAddDefaultSize<String>.ConcurrentDictionary(Count: 512)PerfLabTests.CastingPerf.CheckArrayIsInterfaceNoStatistics
Total: 105070
Same: 74.24 %
Slower: 4.64 %
Faster: 10.13 %
Noise: 10.95 %
Unknown: 0.04 %
Statistics per Architecture
Statistics per Operating System
Statistics per Namespace
Big thanks to everyone involved!
The text was updated successfully, but these errors were encountered: