Improve Benchmark Accuracy #2336
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This was referenced Aug 9, 2023
This comment was marked as outdated.
This comment was marked as outdated.
tests/BenchmarkDotNet.IntegrationTests.ManualRunning/ExpectedBenchmarkResultsTests.cs
Outdated
Show resolved
Hide resolved
timcassell
force-pushed
the
fair-types
branch
2 times, most recently
from
48266cd to
4abbb1f
Compare
timcassell
force-pushed
the
fair-types
branch
from
213549a to
7080e63
Compare
Merged
timcassell
force-pushed
the
fair-types
branch
from
3e4f122 to
e3e774b
Compare
Collaborator
Author
|
Unfortunately, I no longer have an Intel CPU to test this, but I think the new results from this PR should address the issues you had in #2334 @AndreyAkinshin (results look good on my AMD 9800X3D CPU in .Net 8). |
timcassell
force-pushed
the
fair-types
branch
from
e3e774b to
f1a89ed
Compare
Don't fail silently. Remove unused property. Embed the weaver into BenchmarkDotNet.Annotations package instead of another package dependency.
Member
|
@dotnet/jit-contrib any thoughts on this? |
Fixed formatting.
# Conflicts: # build/common.props
Write to MemoryStream first for efficiency.
# Conflicts: # BenchmarkDotNet.sln # NuGet.Config # build/common.props # src/BenchmarkDotNet.Annotations/BenchmarkDotNet.Annotations.csproj # src/BenchmarkDotNet/Code/CodeGenerator.cs # src/BenchmarkDotNet/Templates/BenchmarkType.txt # src/BenchmarkDotNet/Toolchains/InProcess/Emit/Implementation/Emitters/RunnableEmitter.cs # tests/BenchmarkDotNet.Tests/Running/RunningEmptyBenchmarkTests.cs
timcassell
force-pushed
the
fair-types
branch
from
06602c7 to
39817d3
Compare
Collaborator
Author
|
Interestingly, on Apple M3, an empty method is measured at 0.9ns while a method that increments a field is measured at 0.66ns, which results in the overhead measurement looking "wrong". I don't know if this is specific to M chips or Arm in general, but it doesn't happen on xArch. There does not seem to be a good way for BDN to account for this μarch quirk. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes #1133
Fixes #2305
Fixes #1802
Fixes #2530
voidfor a fair baseline for all benchmark return types.Consumeror aNoInliningmethod.MethodImplOptions.NoInliningto benchmark methods.