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] Linux/x64: 7 Improvements on 4/25/2023 8:51:41 AM #17274

Closed
performanceautofiler bot opened this issue May 2, 2023 · 1 comment
Closed

[Perf] Linux/x64: 7 Improvements on 4/25/2023 8:51:41 AM #17274

performanceautofiler bot opened this issue May 2, 2023 · 1 comment
Assignees
@tannergooding
Labels
arch-x64 branch-refs/heads/main kind-micro os-linux perf-improvement runtime-coreclr untriaged

Comments

@performanceautofiler
Copy link

performanceautofiler bot commented May 2, 2023 •
edited
Loading

Run Information

Name Value
Architecture x64
OS ubuntu 18.04
Queue TigerUbuntu
Baseline 620b0db3a987bab2694a0043cacb3e2a86673df5
Compare 2e0033cf25cee5457ee326dc1eaff013b939d00d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

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
IterateGetPositionArray - Duration of single invocation 19.35 ns 15.76 ns 0.81 0.02 False
IterateGetPositionSingleSegment - Duration of single invocation 25.16 ns 22.23 ns 0.88 0.02 False

graph
Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Buffers.Tests.ReadOnlySequenceTests&lt;Char&gt;*'

Payloads

Baseline
Compare

Histogram

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

Description of detection logic

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.
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 15.759047618474698 < 18.403095659205384.
IsChangePoint: Marked as a change because one of 4/10/2023 1:33:42 PM, 4/25/2023 3:46:39 AM, 5/2/2023 10:35:24 AM falls between 4/23/2023 8:38:14 PM and 5/2/2023 10:35:24 AM.
IsImprovementStdDev: Marked as improvement because 34.616466547291914 (T) = (0 -15.939714971172867) / Math.Sqrt((0.23050940341986198 / (299)) + (0.15282038793137992 / (30))) is greater than 1.9672451058622664 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (30) - 2, .975) and 0.14259949278080772 = (18.590745908082276 - 15.939714971172867) / 18.590745908082276 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

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

Description of detection logic

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.
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 22.225108047770266 < 23.906833849483576.
IsChangePoint: Marked as a change because one of 4/10/2023 1:33:42 PM, 4/25/2023 3:46:39 AM, 5/2/2023 10:35:24 AM falls between 4/23/2023 8:38:14 PM and 5/2/2023 10:35:24 AM.
IsImprovementStdDev: Marked as improvement because 28.918677761330944 (T) = (0 -22.348228776386485) / Math.Sqrt((0.4328983352359828 / (299)) + (0.02815956529596122 / (30))) is greater than 1.9672451058622664 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (30) - 2, .975) and 0.05945561212545588 = (23.760950641457057 - 22.348228776386485) / 23.760950641457057 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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

Run Information

Name Value
Architecture x64
OS ubuntu 18.04
Queue TigerUbuntu
Baseline 620b0db3a987bab2694a0043cacb3e2a86673df5
Compare 2e0033cf25cee5457ee326dc1eaff013b939d00d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

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

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
IterateGetPositionSingleSegment - Duration of single invocation 25.01 ns 22.21 ns 0.89 0.02 False
IterateGetPositionArray - Duration of single invocation 19.75 ns 16.04 ns 0.81 0.02 False

graph
graph
Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Buffers.Tests.ReadOnlySequenceTests&lt;Byte&gt;*'

Payloads

Baseline
Compare

Histogram

System.Buffers.Tests.ReadOnlySequenceTests<Byte>.IterateGetPositionSingleSegment

Description of detection logic

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.
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 22.20670535622241 < 23.630924105635536.
IsChangePoint: Marked as a change because one of 4/10/2023 1:33:42 PM, 4/25/2023 3:46:39 AM, 5/2/2023 10:35:24 AM falls between 4/23/2023 8:38:14 PM and 5/2/2023 10:35:24 AM.
IsImprovementStdDev: Marked as improvement because 22.837389649811183 (T) = (0 -22.337784528472625) / Math.Sqrt((0.3153486408334653 / (299)) + (0.08787839203388043 / (30))) is greater than 1.9672451058622664 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (30) - 2, .975) and 0.06061856926866304 = (23.779248554106484 - 22.337784528472625) / 23.779248554106484 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

System.Buffers.Tests.ReadOnlySequenceTests<Byte>.IterateGetPositionArray

Description of detection logic

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.
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 16.03800351152388 < 18.1422788991644.
IsChangePoint: Marked as a change because one of 4/10/2023 1:33:42 PM, 4/25/2023 3:46:39 AM, 5/2/2023 10:35:24 AM falls between 4/23/2023 8:38:14 PM and 5/2/2023 10:35:24 AM.
IsImprovementStdDev: Marked as improvement because 26.493977319208792 (T) = (0 -15.965733232046256) / Math.Sqrt((0.19558947406809135 / (299)) + (0.26758752824081233 / (30))) is greater than 1.9672451058622664 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (30) - 2, .975) and 0.13968682487800704 = (18.55804803847425 - 15.965733232046256) / 18.55804803847425 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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

Run Information

Name Value
Architecture x64
OS ubuntu 18.04
Queue TigerUbuntu
Baseline 620b0db3a987bab2694a0043cacb3e2a86673df5
Compare 2e0033cf25cee5457ee326dc1eaff013b939d00d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in Burgers

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Test1 - Duration of single invocation 261.39 ms 167.30 ms 0.64 0.03 False

Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'Burgers*'

Payloads

Baseline
Compare

Histogram

Burgers.Test1

Description of detection logic

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.
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 167.29517126666667 < 248.32460247025642.
IsChangePoint: Marked as a change because one of 2/24/2023 8:06:06 PM, 4/6/2023 1:55:21 PM, 4/9/2023 11:04:55 PM, 4/25/2023 3:46:39 AM, 5/2/2023 10:35:24 AM falls between 4/23/2023 8:38:14 PM and 5/2/2023 10:35:24 AM.
IsImprovementStdDev: Marked as improvement because 9.360261765462296 (T) = (0 -167133256.8215507) / Math.Sqrt((1327816239979917.2 / (299)) + (1008332076760.7423 / (30))) is greater than 1.9672451058622664 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (30) - 2, .975) and 0.1059187423080976 = (186932960.94027317 - 167133256.8215507) / 186932960.94027317 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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

Run Information

Name Value
Architecture x64
OS ubuntu 18.04
Queue TigerUbuntu
Baseline 620b0db3a987bab2694a0043cacb3e2a86673df5
Compare 2e0033cf25cee5457ee326dc1eaff013b939d00d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Byte>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
GetHashCodeBenchmark - Duration of single invocation 54.01 ns 46.51 ns 0.86 0.18 False

graph
Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Runtime.Intrinsics.Tests.Perf_Vector128Of&lt;Byte&gt;*'

Payloads

Baseline
Compare

Histogram

System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Byte>.GetHashCodeBenchmark

Description of detection logic

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.
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 46.50702596871325 < 51.33236935784486.
IsChangePoint: Marked as a change because one of 2/14/2023 10:45:34 AM, 2/20/2023 10:31:48 AM, 3/3/2023 4:59:02 PM, 3/13/2023 2:14:21 PM, 4/25/2023 3:46:39 AM, 5/2/2023 10:35:24 AM falls between 4/23/2023 8:38:14 PM and 5/2/2023 10:35:24 AM.
IsImprovementStdDev: Marked as improvement because 15.417643076600415 (T) = (0 -48.203121027525846) / Math.Sqrt((3.7961601499585202 / (299)) + (3.260062452308277 / (30))) is greater than 1.9672451058622664 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (30) - 2, .975) and 0.10025559098571733 = (53.57423791089172 - 48.203121027525846) / 53.57423791089172 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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

Run Information

Name Value
Architecture x64
OS ubuntu 18.04
Queue TigerUbuntu
Baseline 620b0db3a987bab2694a0043cacb3e2a86673df5
Compare 2e0033cf25cee5457ee326dc1eaff013b939d00d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

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

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ConcurrentDictionary - Duration of single invocation 2.55 μs 2.37 μs 0.93 0.45 False

graph
Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.ContainsKeyTrue&lt;Int32, Int32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.ContainsKeyTrue<Int32, Int32>.ConcurrentDictionary(Size: 512)

Description of detection logic

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.
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 2.366325423571105 < 2.426412903920816.
IsChangePoint: Marked as a change because one of 3/25/2023 12:18:49 AM, 4/25/2023 3:46:39 AM, 5/2/2023 10:35:24 AM falls between 4/23/2023 8:38:14 PM and 5/2/2023 10:35:24 AM.
IsImprovementStdDev: Marked as improvement because 7.759485312606382 (T) = (0 -2304.0774449133046) / Math.Sqrt((47333.09557368393 / (299)) + (10344.97143163087 / (30))) is greater than 1.9672451058622664 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (30) - 2, .975) and 0.07023478928363143 = (2478.1282611532124 - 2304.0774449133046) / 2478.1282611532124 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

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

@tannergooding tannergooding

Labels
arch-x64 branch-refs/heads/main kind-micro os-linux perf-improvement runtime-coreclr untriaged
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@tannergooding @kunalspathak