[Perf] Linux/x64: 22 Regressions on 2/13/2025 12:40:20 AM +00:00

[performanceautofiler]

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	109c9469a7f76bdc98300bd9c7bb4eaf014be971
Compare	505e3171007810999a7f56672b9f70332609273f
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in IfStatements.IfStatements

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
And - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	27.13 μs	29.84 μs	1.10	0.02	False
Single - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	24.42 μs	29.84 μs	1.22	0.02	False

Test Report

Repro

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

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

IfStatements.IfStatements.And

ETL Files

Histogram

JIT Disasms

IfStatements.IfStatements.Single

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	109c9469a7f76bdc98300bd9c7bb4eaf014be971
Compare	505e3171007810999a7f56672b9f70332609273f
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.Perf_LengthBucketsFrozenDictionary

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
TryGetValue_False_FrozenDictionary - Duration of single invocation ADX - Test Multi Config Graph	1.01 μs	1.07 μs	1.06	0.02	False
TryGetValue_False_FrozenDictionary - Duration of single invocation ADX - Test Multi Config Graph	1.16 μs	1.27 μs	1.10	0.02	False

Test Report

Repro

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

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

System.Collections.Perf_LengthBucketsFrozenDictionary.TryGetValue_False_FrozenDictionary(Count: 1000, ItemsPerBucket: 5)

ETL Files

Histogram

JIT Disasms

System.Collections.Perf_LengthBucketsFrozenDictionary.TryGetValue_False_FrozenDictionary(Count: 1000, ItemsPerBucket: 1)

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	109c9469a7f76bdc98300bd9c7bb4eaf014be971
Compare	505e3171007810999a7f56672b9f70332609273f
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in PerfLabTests.LowLevelPerf

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
ObjectStringIsString - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	40.68 μs	54.26 μs	1.33	0.03	False
InterfaceInterfaceMethodLongHierarchy - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	271.18 μs	298.27 μs	1.10	0.02	False
ClassVirtualMethod - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	135.64 μs	162.74 μs	1.20	0.03	False
StructWithInterfaceInterfaceMethod - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	135.56 μs	162.74 μs	1.20	0.02	False

Test Report

Repro

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

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

PerfLabTests.LowLevelPerf.ObjectStringIsString

ETL Files

Histogram

JIT Disasms

PerfLabTests.LowLevelPerf.InterfaceInterfaceMethodLongHierarchy

ETL Files

Histogram

JIT Disasms

PerfLabTests.LowLevelPerf.ClassVirtualMethod

ETL Files

Histogram

JIT Disasms

PerfLabTests.LowLevelPerf.StructWithInterfaceInterfaceMethod

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	109c9469a7f76bdc98300bd9c7bb4eaf014be971
Compare	505e3171007810999a7f56672b9f70332609273f
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.IterateForEach<String>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
ImmutableDictionary - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	17.74 μs	25.16 μs	1.42	0.19	False
ConcurrentQueue - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	2.86 μs	3.03 μs	1.06	0.22	False

Test Report

Repro

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

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.IterateForEach<String>*'

System.Collections.IterateForEach<String>.ImmutableDictionary(Size: 512)

ETL Files

Histogram

JIT Disasms

System.Collections.IterateForEach<String>.ConcurrentQueue(Size: 512)

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	109c9469a7f76bdc98300bd9c7bb4eaf014be971
Compare	505e3171007810999a7f56672b9f70332609273f
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.TryGetValueFalse<SmallClass, SmallClass>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
SortedList - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	16.33 μs	17.56 μs	1.08	0.13	False

Test Report

Repro

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

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.TryGetValueFalse<SmallClass, SmallClass>*'

System.Collections.TryGetValueFalse<SmallClass, SmallClass>.SortedList(Size: 512)

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	109c9469a7f76bdc98300bd9c7bb4eaf014be971
Compare	505e3171007810999a7f56672b9f70332609273f
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.IterateForNonGeneric<Int32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
ArrayList - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	287.73 ns	353.15 ns	1.23	0.11	False

Test Report

Repro

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

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.IterateForNonGeneric<Int32>*'

System.Collections.IterateForNonGeneric<Int32>.ArrayList(Size: 512)

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	109c9469a7f76bdc98300bd9c7bb4eaf014be971
Compare	505e3171007810999a7f56672b9f70332609273f
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.MathBenchmarks.Double

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Exp - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	21.71 μs	23.08 μs	1.06	0.06	False

Test Report

Repro

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

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

System.MathBenchmarks.Double.Exp

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	109c9469a7f76bdc98300bd9c7bb4eaf014be971
Compare	505e3171007810999a7f56672b9f70332609273f
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in PerfLabTests.CastingPerf2.CastingPerf

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
IntObj - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	54.26 μs	108.54 μs	2.00	0.03	False
ScalarValueTypeObj - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	81.38 μs	162.79 μs	2.00	0.02	False

Test Report

Repro

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

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'PerfLabTests.CastingPerf2.CastingPerf*'

PerfLabTests.CastingPerf2.CastingPerf.IntObj

ETL Files

Histogram

JIT Disasms

PerfLabTests.CastingPerf2.CastingPerf.ScalarValueTypeObj

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	109c9469a7f76bdc98300bd9c7bb4eaf014be971
Compare	505e3171007810999a7f56672b9f70332609273f
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in Benchstone.BenchI.BenchE

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Test - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	226.41 ms	290.33 ms	1.28	0.02	False

Test Report

Repro

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

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

Benchstone.BenchI.BenchE.Test

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	109c9469a7f76bdc98300bd9c7bb4eaf014be971
Compare	505e3171007810999a7f56672b9f70332609273f
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Tests.Perf_String

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
IndexerCheckPathLength - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	96.58 ns	115.85 ns	1.20	0.02	False
IndexerCheckLengthHoisting - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	20.09 ns	38.79 ns	1.93	0.03	False
IndexerCheckBoundCheckHoist - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	19.56 ns	38.79 ns	1.98	0.03	False

Test Report

Repro

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

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

System.Tests.Perf_String.IndexerCheckPathLength

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_String.IndexerCheckLengthHoisting

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_String.IndexerCheckBoundCheckHoist

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	109c9469a7f76bdc98300bd9c7bb4eaf014be971
Compare	505e3171007810999a7f56672b9f70332609273f
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Buffers.Binary.Tests.BinaryReadAndWriteTests

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
MeasureReverseUsingNtoH - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	410.99 ns	546.24 ns	1.33	0.05	False

Test Report

Repro

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

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Buffers.Binary.Tests.BinaryReadAndWriteTests*'

System.Buffers.Binary.Tests.BinaryReadAndWriteTests.MeasureReverseUsingNtoH

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	109c9469a7f76bdc98300bd9c7bb4eaf014be971
Compare	505e3171007810999a7f56672b9f70332609273f
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Linq.Tests.Perf_Enumerable

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
SelectToArray - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	57.96 ns	84.50 ns	1.46	0.04	False

Test Report

Repro

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

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

System.Linq.Tests.Perf_Enumerable.SelectToArray(input: Range)

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	109c9469a7f76bdc98300bd9c7bb4eaf014be971
Compare	505e3171007810999a7f56672b9f70332609273f
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.IterateForEachNonGeneric<String>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Stack - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	1.13 μs	1.25 μs	1.10	0.13	False

Test Report

Repro

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

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.IterateForEachNonGeneric<String>*'

System.Collections.IterateForEachNonGeneric<String>.Stack(Size: 512)

ETL Files

Histogram

JIT Disasms

Docs

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

[LoopedBard3]

Likely due to #112060. Most of the regressions appear to be noise/bimodal while the System.Collections.IterateForEach test regressions seem potentially real. FYI @EgorBo

Related Regressions

• [Perf] Windows/x64: 28 Regressions on 2/13/2025 12:40:20 AM +00:00 perf-autofiling-issues#50424
• [Perf] Windows/x64: 16 Regressions on 2/13/2025 12:40:20 AM +00:00 perf-autofiling-issues#50414
• [Perf] Linux/x64: 22 Regressions on 2/13/2025 7:33:10 PM +00:00 perf-autofiling-issues#50418
• [Perf] Linux/arm64: 8 Regressions on 2/12/2025 6:39:37 AM +00:00 perf-autofiling-issues#50651
• [Perf] Windows/arm64: 1 Regression on 2/12/2025 12:56:48 AM +00:00 perf-autofiling-issues#51054
• [Perf] Windows/arm64: 3 Regressions on 2/12/2025 6:39:37 AM +00:00 perf-autofiling-issues#51055

[EgorBo]

@EgorBot -amd -intel -commit b1ab309 vs previous --filter System.Collections.IterateForEach*

[EgorBo]

Looks like there are only a few benchmarks regressed from #112060, the rest are just bi-modal noise

Overall, it was expected that #112060 would have regressed some things, it's listed here: #112060 (comment)

Glad that there are more improvements than regressions

[dotnet-policy-service]

Tagging subscribers to this area: @JulieLeeMSFT, @jakobbotsch
See info in area-owners.md if you want to be subscribed.

[JulieLeeMSFT]

@EgorBo, is it ok to close this issue because it is expected to have some regressions?

Looks like there are only a few benchmarks regressed from #112060, the rest are just bi-modal noise

Overall, it was expected that #112060 would have regressed some things, it's listed here: #112060 (comment)

Glad that there are more improvements than regressions