[Perf] Changes at 4/22/2022 8:14:55 AM

[performanceautofiler]

Run Information

Architecture	x64
OS	Windows 10.0.19042
Baseline	0d889f56d2c79f6ac73c218147e3a5a07883fb8e
Compare	4c667f113f1eeec9bdd5f62bd438cb3038f56d2d
Diff	Diff

Regressions in System.Text.Perf_Utf8Encoding

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
GetBytes - Duration of single invocation	98.18 μs	127.01 μs	1.29	0.00	True
GetBytes - Duration of single invocation	94.74 μs	107.17 μs	1.13	0.00	True

Test Report

Repro

git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Text.Perf_Utf8Encoding*'

Payloads

Baseline
Compare

Histogram

System.Text.Perf_Utf8Encoding.GetBytes(Input: Chinese)

Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 127.01065834367245 > 103.05216981132075.
IsChangePoint: Marked as a change because one of 4/22/2022 6:17:37 AM, 4/26/2022 6:18:08 AM falls between 4/17/2022 3:25:40 PM and 4/26/2022 6:18:08 AM.
IsRegressionStdDev: Marked as regression because -106.82190607093682 (T) = (0 -127793.03651323801) / Math.Sqrt((108355.23723434491 / (37)) + (1541678.5758426792 / (21))) is less than -2.0032407188469383 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (37) + (21) - 2, .025) and -0.30032024900751003 = (98278.12541624116 - 127793.03651323801) / 98278.12541624116 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked as regression because Edge Detector said so.

```#### System.Text.Perf_Utf8Encoding.GetBytes(Input: EnglishMostlyAscii)

```log

Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 107.16628401360546 > 99.6013868278825.
IsChangePoint: Marked as a change because one of 4/22/2022 6:17:37 AM, 4/26/2022 6:18:08 AM falls between 4/17/2022 3:25:40 PM and 4/26/2022 6:18:08 AM.
IsRegressionStdDev: Marked as regression because -96.70696394378226 (T) = (0 -106638.89891454128) / Math.Sqrt((196177.1341100715 / (37)) + (189255.7749748062 / (21))) is less than -2.0032407188469383 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (37) + (21) - 2, .025) and -0.12170400994995464 = (95068.6615797148 - 106638.89891454128) / 95068.6615797148 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked as regression because Edge Detector said so.

Docs

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

[AndyAyersMS]

Seems like a clear regression but only two unrelated looking commits: dotnet/runtime@a806647...3e3e14d

[AndyAyersMS]

The only real possibility is dotnet/runtime#67701 but I my only guess is that somehow perhaps that change is inhibiting PGO data uptake or something. If so we'd expect perf to return with a subsequent PGO update; that hasn't happened yet (last PGO update was apparently 4/16)?

Going to mark this as look again.

[AndyAyersMS]

Seems to be a dup of #4833.

cc @DrewScoggins you mentioned something about there being some dups?

[DrewScoggins]

Yeah, I tried to de-dupe as best I could but I may have missed some. Shouldn't happen again going forward.