Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Perf] Changes at 3/17/2022 11:24:40 PM #4218

Closed
performanceautofiler bot opened this issue Mar 22, 2022 · 0 comments
Closed

[Perf] Changes at 3/17/2022 11:24:40 PM #4218

performanceautofiler bot opened this issue Mar 22, 2022 · 0 comments
Labels
arch-x64 branch-refs/heads/main kind-micro os-linux perf-improvement PGO Applied if there were any profile guided optimization updates in the observed interval. runtime-coreclr untriaged

Comments

@performanceautofiler
Copy link

performanceautofiler bot commented Mar 22, 2022 •
edited
Loading

Run Information

Architecture x64
OS ubuntu 18.04
Baseline c032e0d89f5fc90b596b67a37684ee3c05c6b3ea
Compare 5371203d5820a21922357e954e8c43eb4b76fd1d
Diff Diff

Improvements in System.Collections.ContainsTrueComparer<Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
HashSet - Duration of single invocation 4.69 μs 4.18 μs 0.89 0.21 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Collections.ContainsTrueComparer&lt;Int32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.ContainsTrueComparer<Int32>.HashSet(Size: 512)

Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 4.180895110408344 < 4.315811713357666.
IsChangePoint: Marked as a change because one of 2/10/2022 7:02:09 PM, 2/12/2022 12:07:16 PM, 3/17/2022 6:54:53 PM, 3/22/2022 2:14:22 AM falls between 3/13/2022 11:50:20 AM and 3/22/2022 2:14:22 AM.
IsImprovementStdDev: Marked as improvement because 20.63971664666077 (T) = (0 -4227.071542218082) / Math.Sqrt((72833.82537538528 / (299)) + (5164.171745799637 / (19))) is greater than 1.9674995188240387 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (19) - 2, .975) and 0.09978770311993203 = (4695.638525343583 - 4227.071542218082) / 4695.638525343583 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

### Run Information
Architecture x64
OS ubuntu 18.04
Baseline c032e0d89f5fc90b596b67a37684ee3c05c6b3ea
Compare 5371203d5820a21922357e954e8c43eb4b76fd1d
Diff Diff

Improvements in System.Text.Json.Tests.Perf_Reader

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ReadMultiSpanSequenceEmptyLoop - Duration of single invocation 58.49 μs 54.03 μs 0.92 0.00 True

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Text.Json.Tests.Perf_Reader*'

Payloads

Baseline
Compare

Histogram

System.Text.Json.Tests.Perf_Reader.ReadMultiSpanSequenceEmptyLoop(IsDataCompact: True, TestCase: Json40KB)

Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 54.03174194059976 < 55.685091026191024.
IsChangePoint: Marked as a change because one of 3/3/2022 10:59:13 PM, 3/17/2022 6:54:53 PM, 3/22/2022 2:14:22 AM falls between 3/13/2022 11:50:20 AM and 3/22/2022 2:14:22 AM.
IsImprovementStdDev: Marked as improvement because 50.291398571843054 (T) = (0 -53440.6206771865) / Math.Sqrt((547922.1396962462 / (299)) + (178858.2139337474 / (19))) is greater than 1.9674995188240387 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (19) - 2, .975) and 0.09074239600247935 = (58773.90570311054 - 53440.6206771865) / 58773.90570311054 is greater than 0.05.
IsChangeEdgeDetector: Marked as regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline c032e0d89f5fc90b596b67a37684ee3c05c6b3ea
Compare 5371203d5820a21922357e954e8c43eb4b76fd1d
Diff Diff

Improvements in System.Net.Primitives.Tests.CredentialCacheTests

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
GetCredential_Uri - Duration of single invocation 608.84 ns 552.95 ns 0.91 0.00 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Net.Primitives.Tests.CredentialCacheTests*'

Payloads

Baseline
Compare

Histogram

System.Net.Primitives.Tests.CredentialCacheTests.GetCredential_Uri(uriString: "http://notfound", uriCount: 10)

Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 552.948936272765 < 578.9638711291733.
IsChangePoint: Marked as a change because one of 3/17/2022 6:54:53 PM, 3/22/2022 2:14:22 AM falls between 3/13/2022 11:50:20 AM and 3/22/2022 2:14:22 AM.
IsImprovementStdDev: Marked as improvement because 51.07943613254676 (T) = (0 -557.7586601840494) / Math.Sqrt((42.76080495593513 / (299)) + (11.38107238836583 / (19))) is greater than 1.9674995188240387 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (19) - 2, .975) and 0.07311904688761899 = (601.7586814262901 - 557.7586601840494) / 601.7586814262901 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline c032e0d89f5fc90b596b67a37684ee3c05c6b3ea
Compare 5371203d5820a21922357e954e8c43eb4b76fd1d
Diff Diff

Improvements in System.Numerics.Tests.Perf_VectorOf<Int16>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
DivideBenchmark - Duration of single invocation 42.91 ns 38.10 ns 0.89 0.02 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Int16&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<Int16>.DivideBenchmark

Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 38.10417303318036 < 40.01222531426329.
IsChangePoint: Marked as a change because one of 3/17/2022 6:54:53 PM, 3/22/2022 2:14:22 AM falls between 3/13/2022 11:50:20 AM and 3/22/2022 2:14:22 AM.
IsImprovementStdDev: Marked as improvement because 11.021525868155441 (T) = (0 -38.71668146447877) / Math.Sqrt((0.2198849060578672 / (227)) + (1.9233838639554397 / (18))) is greater than 1.9697743954265454 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (227) + (18) - 2, .975) and 0.0854851541326367 = (42.335760473913666 - 38.71668146447877) / 42.335760473913666 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline c032e0d89f5fc90b596b67a37684ee3c05c6b3ea
Compare 5371203d5820a21922357e954e8c43eb4b76fd1d
Diff Diff

Improvements in System.Numerics.Tests.Perf_VectorOf<Byte>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
DivideBenchmark - Duration of single invocation 87.92 ns 76.59 ns 0.87 0.00 True

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Byte&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<Byte>.DivideBenchmark

Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 76.58797973688681 < 83.50385380175607.
IsChangePoint: Marked as a change because one of 3/17/2022 6:54:53 PM, 3/22/2022 2:14:22 AM falls between 3/13/2022 11:50:20 AM and 3/22/2022 2:14:22 AM.
IsImprovementStdDev: Marked as improvement because 476.20184970368933 (T) = (0 -76.40034199423667) / Math.Sqrt((0.030828026395456235 / (239)) + (0.00899018647502874 / (19))) is greater than 1.9692738896555546 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (239) + (19) - 2, .975) and 0.13265984180573986 = (88.0857888020505 - 76.40034199423667) / 88.0857888020505 is greater than 0.05.
IsChangeEdgeDetector: Marked as regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline c032e0d89f5fc90b596b67a37684ee3c05c6b3ea
Compare 5371203d5820a21922357e954e8c43eb4b76fd1d
Diff Diff

Improvements in System.Text.Json.Document.Tests.Perf_ParseThenWrite

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ParseThenWrite - Duration of single invocation 4.82 μs 4.51 μs 0.94 0.03 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Text.Json.Document.Tests.Perf_ParseThenWrite*'

Payloads

Baseline
Compare

Histogram

System.Text.Json.Document.Tests.Perf_ParseThenWrite.ParseThenWrite(IsDataIndented: False, TestCase: LotsOfNumbers)

Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 4.5080620325473655 < 4.632911729179898.
IsChangePoint: Marked as a change because one of 2/5/2022 11:25:50 PM, 3/17/2022 6:54:53 PM, 3/22/2022 2:14:22 AM falls between 3/13/2022 11:50:20 AM and 3/22/2022 2:14:22 AM.
IsImprovementStdDev: Marked as improvement because 24.937950566688222 (T) = (0 -4532.239085813868) / Math.Sqrt((10838.77310157084 / (299)) + (1547.493857707327 / (17))) is greater than 1.9675476980854363 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (17) - 2, .975) and 0.058448151857028924 = (4813.58418524995 - 4532.239085813868) / 4813.58418524995 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline c032e0d89f5fc90b596b67a37684ee3c05c6b3ea
Compare 5371203d5820a21922357e954e8c43eb4b76fd1d
Diff Diff

Improvements in System.Memory.ReadOnlySequence

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Slice_Start_And_Length - Duration of single invocation 5.71 ns 4.44 ns 0.78 0.10 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Memory.ReadOnlySequence*'

Payloads

Baseline
Compare

Histogram

System.Memory.ReadOnlySequence.Slice_Start_And_Length(Segment: Single)

Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 4.43726819473486 < 5.307940608849598.
IsChangePoint: Marked as a change because one of 2/4/2022 1:40:45 AM, 3/17/2022 6:54:53 PM, 3/22/2022 2:14:22 AM falls between 3/13/2022 11:50:20 AM and 3/22/2022 2:14:22 AM.
IsImprovementStdDev: Marked as improvement because 24.215139028515697 (T) = (0 -4.246351586884894) / Math.Sqrt((0.11859256430348898 / (299)) + (0.03211063136850006 / (19))) is greater than 1.9674995188240387 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (19) - 2, .975) and 0.20666007289742913 = (5.352499529922038 - 4.246351586884894) / 5.352499529922038 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline c032e0d89f5fc90b596b67a37684ee3c05c6b3ea
Compare 5371203d5820a21922357e954e8c43eb4b76fd1d
Diff Diff

Improvements in System.Collections.IterateForEach<Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Stack - Duration of single invocation 1.69 μs 1.47 μs 0.87 0.10 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Collections.IterateForEach&lt;Int32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.IterateForEach<Int32>.Stack(Size: 512)

Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 1.4675077664159697 < 1.6057225504629287.
IsChangePoint: Marked as a change because one of 1/25/2022 2:47:22 PM, 2/8/2022 3:28:17 PM, 3/9/2022 10:22:25 AM, 3/17/2022 6:54:53 PM, 3/22/2022 2:14:22 AM falls between 3/13/2022 11:50:20 AM and 3/22/2022 2:14:22 AM.
IsImprovementStdDev: Marked as improvement because 28.13995812341157 (T) = (0 -1476.025382622646) / Math.Sqrt((2986.485786270234 / (299)) + (131.46037992020126 / (18))) is greater than 1.9675235316906419 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (18) - 2, .975) and 0.07345380588324092 = (1593.0402520617813 - 1476.025382622646) / 1593.0402520617813 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline c032e0d89f5fc90b596b67a37684ee3c05c6b3ea
Compare 5371203d5820a21922357e954e8c43eb4b76fd1d
Diff Diff

Improvements in System.Collections.AddGivenSize<String>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
IDictionary - Duration of single invocation 13.02 μs 11.24 μs 0.86 0.02 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Collections.AddGivenSize&lt;String&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.AddGivenSize<String>.IDictionary(Size: 512)

Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 11.238923596570395 < 12.535246841274713.
IsChangePoint: Marked as a change because one of 2/3/2022 10:14:29 PM, 3/17/2022 6:54:53 PM, 3/22/2022 2:14:22 AM falls between 3/13/2022 11:50:20 AM and 3/22/2022 2:14:22 AM.
IsImprovementStdDev: Marked as improvement because 17.93353788026687 (T) = (0 -11518.175173306983) / Math.Sqrt((271894.4131655773 / (299)) + (102438.71912730271 / (17))) is greater than 1.9675476980854363 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (17) - 2, .975) and 0.11477890314662222 = (13011.636543965895 - 11518.175173306983) / 13011.636543965895 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline c032e0d89f5fc90b596b67a37684ee3c05c6b3ea
Compare 5371203d5820a21922357e954e8c43eb4b76fd1d
Diff Diff

Improvements in System.Tests.Perf_Version

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
TryParse3 - Duration of single invocation 45.78 ns 42.32 ns 0.92 0.03 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Tests.Perf_Version*'

Payloads

Baseline
Compare

Histogram

System.Tests.Perf_Version.TryParse3

Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 42.31662137780571 < 43.7159239237716.
IsChangePoint: Marked as a change because one of 1/26/2022 10:02:18 PM, 3/7/2022 10:45:01 PM, 3/17/2022 6:54:53 PM, 3/22/2022 2:14:22 AM falls between 3/13/2022 11:50:20 AM and 3/22/2022 2:14:22 AM.
IsImprovementStdDev: Marked as improvement because 43.704975473920015 (T) = (0 -42.699262725261306) / Math.Sqrt((2.2123257644177117 / (299)) + (0.06678235194314329 / (19))) is greater than 1.9674995188240387 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (19) - 2, .975) and 0.0966008668812725 = (47.26511367999026 - 42.699262725261306) / 47.26511367999026 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline c032e0d89f5fc90b596b67a37684ee3c05c6b3ea
Compare 5371203d5820a21922357e954e8c43eb4b76fd1d
Diff Diff

Improvements in System.Buffers.Tests.ReadOnlySequenceTests<Char>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
SliceMemory - Duration of single invocation 8.49 ns 6.86 ns 0.81 0.03 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Buffers.Tests.ReadOnlySequenceTests&lt;Char&gt;*'

Payloads

Baseline
Compare

Histogram

System.Buffers.Tests.ReadOnlySequenceTests<Char>.SliceMemory

Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 6.861159189728481 < 8.06154886638971.
IsChangePoint: Marked as a change because one of 2/4/2022 3:19:13 PM, 3/17/2022 6:54:53 PM, 3/22/2022 2:14:22 AM falls between 3/13/2022 11:50:20 AM and 3/22/2022 2:14:22 AM.
IsImprovementStdDev: Marked as improvement because 29.19868222552355 (T) = (0 -6.922449114198339) / Math.Sqrt((0.17523061958302644 / (299)) + (0.012151319129049409 / (19))) is greater than 1.9674995188240387 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (19) - 2, .975) and 0.12866560911805727 = (7.944652692052715 - 6.922449114198339) / 7.944652692052715 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline c032e0d89f5fc90b596b67a37684ee3c05c6b3ea
Compare 5371203d5820a21922357e954e8c43eb4b76fd1d
Diff Diff

Improvements in System.Collections.TryGetValueTrue<Int32, Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ImmutableDictionary - Duration of single invocation 18.60 μs 17.56 μs 0.94 0.02 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Collections.TryGetValueTrue&lt;Int32, Int32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.TryGetValueTrue<Int32, Int32>.ImmutableDictionary(Size: 512)

Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 17.563634419676447 < 17.630245972897164.
IsChangePoint: Marked as a change because one of 1/31/2022 1:37:35 PM, 3/17/2022 6:54:53 PM, 3/22/2022 2:14:22 AM falls between 3/13/2022 11:50:20 AM and 3/22/2022 2:14:22 AM.
IsImprovementStdDev: Marked as improvement because 27.167847398632684 (T) = (0 -17048.994213766924) / Math.Sqrt((329971.6225986415 / (299)) + (57913.12364451031 / (19))) is greater than 1.9674995188240387 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (19) - 2, .975) and 0.09311481450253895 = (18799.506802412812 - 17048.994213766924) / 18799.506802412812 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline c032e0d89f5fc90b596b67a37684ee3c05c6b3ea
Compare 5371203d5820a21922357e954e8c43eb4b76fd1d
Diff Diff

Improvements in System.Collections.Tests.Perf_PriorityQueue<String, String>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Enumerate - Duration of single invocation 543.40 ns 481.40 ns 0.89 0.21 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Collections.Tests.Perf_PriorityQueue&lt;String, String&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.Tests.Perf_PriorityQueue<String, String>.Enumerate(Size: 100)

Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 481.398622936912 < 526.9843514695369.
IsChangePoint: Marked as a change because one of 3/1/2022 1:15:47 PM, 3/7/2022 10:58:04 AM, 3/17/2022 6:54:53 PM, 3/22/2022 2:14:22 AM falls between 3/13/2022 11:50:20 AM and 3/22/2022 2:14:22 AM.
IsImprovementStdDev: Marked as improvement because 27.33867623581682 (T) = (0 -493.4683981903391) / Math.Sqrt((511.14472978408384 / (299)) + (99.76459396958376 / (19))) is greater than 1.9674995188240387 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (19) - 2, .975) and 0.12752223857270692 = (565.5942420619069 - 493.4683981903391) / 565.5942420619069 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
arch-x64 branch-refs/heads/main kind-micro os-linux perf-improvement PGO Applied if there were any profile guided optimization updates in the observed interval. runtime-coreclr untriaged
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@kunalspathak