[Perf] Linux/arm64: 29 Regressions on 5/12/2025 3:12:34 PM +00:00

[performanceautofiler]

Run Information

Name	Value
Architecture	arm64
OS	ubuntu 22.04
Queue	AmpereUbuntu
Baseline	1e0a78b0de0247112a417475050931e7a042e044
Compare	fdbe38ce16671ae356e2bad21479e38b61d03340
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Net.Http.Tests.SocketsHttpHandlerPerfTest

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Get_EnumerateHeaders_Unvalidated - Duration of single invocation ADX - Test Multi Config Graph	63.35 μs	67.88 μs	1.07	0.48	False
Get_EnumerateHeaders_Validated - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	107.37 μs	133.16 μs	1.24	0.53	False
Get_EnumerateHeaders_Unvalidated - Duration of single invocation ADX - Test Multi Config Graph	99.37 μs	139.81 μs	1.41	0.55	False
Get_EnumerateHeaders_Unvalidated - Duration of single invocation ADX - Test Multi Config Graph	13.13 ms	16.15 ms	1.23	0.82	False
Get_EnumerateHeaders_Unvalidated - Duration of single invocation ADX - Test Multi Config Graph	95.64 μs	121.46 μs	1.27	0.40	False
Get - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	105.61 μs	123.37 μs	1.17	0.39	False
Get_EnumerateHeaders_Validated - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	103.23 μs	141.69 μs	1.37	0.44	False
Get - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	104.15 μs	129.93 μs	1.25	0.50	False
Get_EnumerateHeaders_Validated - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	101.56 μs	121.66 μs	1.20	0.47	False
Get_EnumerateHeaders_Unvalidated - Duration of single invocation ADX - Test Multi Config Graph	101.22 μs	123.04 μs	1.22	0.48	False
Get - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	96.89 μs	116.43 μs	1.20	0.41	False
Get_EnumerateHeaders_Validated - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	137.95 μs	171.22 μs	1.24	0.56	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.Net.Http.Tests.SocketsHttpHandlerPerfTest*'

System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get_EnumerateHeaders_Unvalidated(ssl: False, chunkedResponse: True, responseLength: 1)

ETL Files

Histogram

JIT Disasms

System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get_EnumerateHeaders_Validated(ssl: False, chunkedResponse: False, responseLength: 100000)

ETL Files

Histogram

JIT Disasms

System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get_EnumerateHeaders_Unvalidated(ssl: False, chunkedResponse: False, responseLength: 100000)

ETL Files

Histogram

JIT Disasms

System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get_EnumerateHeaders_Unvalidated(ssl: True, chunkedResponse: True, responseLength: 100000)

ETL Files

Histogram

JIT Disasms

System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get_EnumerateHeaders_Unvalidated(ssl: True, chunkedResponse: False, responseLength: 1)

ETL Files

Histogram

JIT Disasms

System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get(ssl: True, chunkedResponse: True, responseLength: 1)

ETL Files

Histogram

JIT Disasms

System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get_EnumerateHeaders_Validated(ssl: True, chunkedResponse: False, responseLength: 1)

ETL Files

Histogram

JIT Disasms

System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get(ssl: False, chunkedResponse: False, responseLength: 100000)

ETL Files

Histogram

JIT Disasms

System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get_EnumerateHeaders_Validated(ssl: True, chunkedResponse: True, responseLength: 1)

ETL Files

Histogram

JIT Disasms

System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get_EnumerateHeaders_Unvalidated(ssl: True, chunkedResponse: True, responseLength: 1)

ETL Files

Histogram

JIT Disasms

System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get(ssl: True, chunkedResponse: False, responseLength: 1)

ETL Files

Histogram

JIT Disasms

System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get_EnumerateHeaders_Validated(ssl: False, chunkedResponse: True, responseLength: 100000)

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	arm64
OS	ubuntu 22.04
Queue	AmpereUbuntu
Baseline	1e0a78b0de0247112a417475050931e7a042e044
Compare	fdbe38ce16671ae356e2bad21479e38b61d03340
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.IO.Tests.Perf_FileStream

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
CopyToFileAsync - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	99.32 μs	130.43 μs	1.31	0.43	False
CopyToFileAsync - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	100.85 μs	158.52 μs	1.57	0.41	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.IO.Tests.Perf_FileStream*'

System.IO.Tests.Perf_FileStream.CopyToFileAsync(fileSize: 1024, options: Asynchronous)

ETL Files

Histogram

JIT Disasms

System.IO.Tests.Perf_FileStream.CopyToFileAsync(fileSize: 1024, options: None)

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	arm64
OS	ubuntu 22.04
Queue	AmpereUbuntu
Baseline	1e0a78b0de0247112a417475050931e7a042e044
Compare	fdbe38ce16671ae356e2bad21479e38b61d03340
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.IO.Pipes.Tests.Perf_NamedPipeStream

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
ReadWriteAsync - Duration of single invocation ADX - Test Multi Config Graph	241.79 μs	297.79 μs	1.23	0.50	False
ReadWriteAsync - Duration of single invocation ADX - Test Multi Config Graph	235.33 μs	297.26 μs	1.26	0.51	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.IO.Pipes.Tests.Perf_NamedPipeStream*'

System.IO.Pipes.Tests.Perf_NamedPipeStream.ReadWriteAsync(size: 1000000, Options: None)

ETL Files

Histogram

JIT Disasms

System.IO.Pipes.Tests.Perf_NamedPipeStream.ReadWriteAsync(size: 1000000, Options: Asynchronous)

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	arm64
OS	ubuntu 22.04
Queue	AmpereUbuntu
Baseline	1e0a78b0de0247112a417475050931e7a042e044
Compare	fdbe38ce16671ae356e2bad21479e38b61d03340
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.IO.Tests.Perf_File

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
WriteAllBytesAsync - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	94.26 μs	110.60 μs	1.17	0.21	False
WriteAllBytesAsync - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	72.95 μs	91.84 μs	1.26	0.20	False
WriteAllBytesAsync - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	69.68 μs	79.51 μs	1.14	0.21	False
WriteAllTextAsync - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	92.16 μs	116.24 μs	1.26	0.35	False
WriteAllTextAsync - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	250.96 μs	319.49 μs	1.27	0.68	False
ReadAllLinesAsync - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	61.24 μs	72.42 μs	1.18	0.32	False
WriteAllTextAsync - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	74.79 μs	96.93 μs	1.30	0.29	False
AppendAllLinesAsync - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	34.34 μs	41.79 μs	1.22	0.49	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.IO.Tests.Perf_File*'

System.IO.Tests.Perf_File.WriteAllBytesAsync(size: 16384)

ETL Files

Histogram

JIT Disasms

System.IO.Tests.Perf_File.WriteAllBytesAsync(size: 4096)

ETL Files

Histogram

JIT Disasms

System.IO.Tests.Perf_File.WriteAllBytesAsync(size: 512)

ETL Files

Histogram

JIT Disasms

System.IO.Tests.Perf_File.WriteAllTextAsync(size: 10000)

ETL Files

Histogram

JIT Disasms

System.IO.Tests.Perf_File.WriteAllTextAsync(size: 100000)

ETL Files

Histogram

JIT Disasms

System.IO.Tests.Perf_File.ReadAllLinesAsync

ETL Files

Histogram

JIT Disasms

System.IO.Tests.Perf_File.WriteAllTextAsync(size: 100)

ETL Files

Histogram

JIT Disasms

System.IO.Tests.Perf_File.AppendAllLinesAsync

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	arm64
OS	ubuntu 22.04
Queue	AmpereUbuntu
Baseline	1e0a78b0de0247112a417475050931e7a042e044
Compare	fdbe38ce16671ae356e2bad21479e38b61d03340
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in CscBench

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
CompileTest - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	435.55 ms	531.32 ms	1.22	0.50	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 'CscBench*'

CscBench.CompileTest

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	arm64
OS	ubuntu 22.04
Queue	AmpereUbuntu
Baseline	1e0a78b0de0247112a417475050931e7a042e044
Compare	fdbe38ce16671ae356e2bad21479e38b61d03340
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Net.Sockets.Tests.SocketSendReceivePerfTest

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
ConnectAcceptAsync - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	81.03 μs	95.03 μs	1.17	0.43	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.Net.Sockets.Tests.SocketSendReceivePerfTest*'

System.Net.Sockets.Tests.SocketSendReceivePerfTest.ConnectAcceptAsync

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	arm64
OS	ubuntu 22.04
Queue	AmpereUbuntu
Baseline	1e0a78b0de0247112a417475050931e7a042e044
Compare	fdbe38ce16671ae356e2bad21479e38b61d03340
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Net.Security.Tests.SslStreamTests

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
LargeReadWriteAsync - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	60.21 μs	65.52 μs	1.09	0.27	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.Net.Security.Tests.SslStreamTests*'

System.Net.Security.Tests.SslStreamTests.LargeReadWriteAsync

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	arm64
OS	ubuntu 22.04
Queue	AmpereUbuntu
Baseline	1e0a78b0de0247112a417475050931e7a042e044
Compare	fdbe38ce16671ae356e2bad21479e38b61d03340
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in BenchmarksGame.Fasta_1

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
RunBench - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	370.20 μs	604.62 μs	1.63	0.48	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 'BenchmarksGame.Fasta_1*'

BenchmarksGame.Fasta_1.RunBench

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	arm64
OS	ubuntu 22.04
Queue	AmpereUbuntu
Baseline	1e0a78b0de0247112a417475050931e7a042e044
Compare	fdbe38ce16671ae356e2bad21479e38b61d03340
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Formats.Tar.Tests.Perf_TarFile

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
CreateFromDirectory_Stream_Async - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	122.44 μs	174.36 μs	1.42	0.81	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.Formats.Tar.Tests.Perf_TarFile*'

System.Formats.Tar.Tests.Perf_TarFile.CreateFromDirectory_Stream_Async

ETL Files

Histogram

JIT Disasms

Docs

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

[LoopedBard3]

Likely due to #115402 from range a 1e0a78b...fb7050d. Related Regressions:

• [Perf] Windows/arm64: 9 Regressions on 5/12/2025 3:12:34 PM +00:00 perf-autofiling-issues#55575
• [Perf] Linux/arm64: 1 Regression on 5/15/2025 12:29:38 AM +00:00 perf-autofiling-issues#55950
• [Perf] Windows/arm64: 4 Regressions on 5/13/2025 2:36:10 AM +00:00 perf-autofiling-issues#55942
• [Perf] Windows/arm64: 7 Regressions on 5/12/2025 3:12:34 PM +00:00 perf-autofiling-issues#55941

[LoopedBard3]

FYI, @EgorBo @mangod9

[mangod9]

If these are related to the spin wait change then it's expected. We havent seen any changes in macro benchmarks like TE