[Perf] Linux/x64: 16 Regressions on 2/5/2024 1:05:09 PM

[performanceautofiler]

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.CtorFromCollection<Int32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Dictionary - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	1.34 μs	1.59 μs	1.19	0.01	False
SortedList - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	6.01 μs	7.29 μs	1.21	0.21	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.CtorFromCollection<Int32>*'

Payloads

Baseline
Compare

System.Collections.CtorFromCollection<Int32>.Dictionary(Size: 512)

ETL Files

Histogram

JIT Disasms

System.Collections.CtorFromCollection<Int32>.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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.Sort<BigStruct>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Array_ComparerClass - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	12.50 μs	15.82 μs	1.27	0.27	False
Array_Comparison - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	11.48 μs	15.15 μs	1.32	0.23	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.Sort<BigStruct>*'

Payloads

Baseline
Compare

System.Collections.Sort<BigStruct>.Array_ComparerClass(Size: 512)

ETL Files

Histogram

JIT Disasms

System.Collections.Sort<BigStruct>.Array_Comparison(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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Tests.Perf_Enum

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
TryParseGeneric_Flags - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	82.35 ns	91.92 ns	1.12	0.09	False
Parse_Flags - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	139.37 ns	149.67 ns	1.07	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.Tests.Perf_Enum*'

Payloads

Baseline
Compare

System.Tests.Perf_Enum.TryParseGeneric_Flags(text: "Red, Orange, Yellow, Green, Blue")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_Enum.Parse_Flags(text: "Red, Orange, Yellow, Green, Blue")

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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.Sort<IntStruct>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
List - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	7.14 μs	8.05 μs	1.13	0.50	False
Array - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	5.01 μs	7.62 μs	1.52	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.Collections.Sort<IntStruct>*'

Payloads

Baseline
Compare

System.Collections.Sort<IntStruct>.List(Size: 512)

ETL Files

Histogram

JIT Disasms

System.Collections.Sort<IntStruct>.Array(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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Buffers.Text.Tests.Utf8ParserTests

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
TryParseInt64 - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	14.40 ns	17.99 ns	1.25	0.10	True

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.Text.Tests.Utf8ParserTests*'

Payloads

Baseline
Compare

System.Buffers.Text.Tests.Utf8ParserTests.TryParseInt64(value: 9223372036854775807)

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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.Perf_Frozen<Int16>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
TryGetValue_True - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	184.83 ns	271.49 ns	1.47	0.28	False
TryGetValue_True - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	1.84 μs	2.17 μs	1.18	0.16	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_Frozen<Int16>*'

Payloads

Baseline
Compare

System.Collections.Perf_Frozen<Int16>.TryGetValue_True(Count: 64)

ETL Files

Histogram

JIT Disasms

System.Collections.Perf_Frozen<Int16>.TryGetValue_True(Count: 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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.Perf_DefaultFrozenDictionary

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
TryGetValue_True_FrozenDictionary - Duration of single invocation 📈 - ADX Test Multi Config Graph	937.72 ns	1.02 μs	1.09	0.01	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_DefaultFrozenDictionary*'

Payloads

Baseline
Compare

System.Collections.Perf_DefaultFrozenDictionary.TryGetValue_True_FrozenDictionary(Count: 100)

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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Numerics.Tests.Perf_BigInteger

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Divide - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	428.25 ns	586.51 ns	1.37	0.07	False
ToStringD - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	16.14 ns	18.14 ns	1.12	0.07	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.Numerics.Tests.Perf_BigInteger*'

Payloads

Baseline
Compare

System.Numerics.Tests.Perf_BigInteger.Divide(arguments: 1024,512 bits)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_BigInteger.ToStringD(numberString: 123)

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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.ContainsKeyFalse<Int32, Int32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
ConcurrentDictionary - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	1.83 μs	2.02 μs	1.11	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.Collections.ContainsKeyFalse<Int32, Int32>*'

Payloads

Baseline
Compare

System.Collections.ContainsKeyFalse<Int32, Int32>.ConcurrentDictionary(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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.CreateAddAndClear<Int32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Array - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	392.75 ns	551.57 ns	1.40	0.02	True

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.CreateAddAndClear<Int32>*'

Payloads

Baseline
Compare

System.Collections.CreateAddAndClear<Int32>.Array(Size: 512)

ETL Files

Histogram

JIT Disasms

Docs

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

[cincuranet]

Diff. Maybe #96843 or #97908. cc @jakobbotsch @EgorBo

[cincuranet]

Windows:

• [Perf] Windows/x64: 14 Regressions on 2/5/2024 1:05:09 PM perf-autofiling-issues#29066
• [Perf] Windows/x64: 5 Regressions on 2/5/2024 1:05:09 PM perf-autofiling-issues#29038

[EgorBo]

I confirmed locally that it's #96843 (doesn't repro on a commit before that change and reproduced before my change). cc @jakobbotsch the best example to take is dotnet/perf-autofiling-issues#29066 Windows-X64 Perf_decimal.Floor (at the bottom of that page).

ASM diffs: https://www.diffchecker.com/zcGeHkoF/ ("before" is on the left).

PS: there is no real perf difference in that decimal benchmark on my cpu, but there are diffs. At the same time I was able to repro a perf regression on Perf_Enun benchmark there

[ghost]

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

Issue Details

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.CtorFromCollection<Int32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Dictionary - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	1.34 μs	1.59 μs	1.19	0.01	False
SortedList - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	6.01 μs	7.29 μs	1.21	0.21	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.CtorFromCollection<Int32>*'

Payloads

Baseline
Compare

System.Collections.CtorFromCollection<Int32>.Dictionary(Size: 512)

ETL Files

Histogram

JIT Disasms

System.Collections.CtorFromCollection<Int32>.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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.Sort<BigStruct>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Array_ComparerClass - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	12.50 μs	15.82 μs	1.27	0.27	False
Array_Comparison - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	11.48 μs	15.15 μs	1.32	0.23	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.Sort<BigStruct>*'

Payloads

Baseline
Compare

System.Collections.Sort<BigStruct>.Array_ComparerClass(Size: 512)

ETL Files

Histogram

JIT Disasms

System.Collections.Sort<BigStruct>.Array_Comparison(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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Tests.Perf_Enum

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
TryParseGeneric_Flags - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	82.35 ns	91.92 ns	1.12	0.09	False
Parse_Flags - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	139.37 ns	149.67 ns	1.07	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.Tests.Perf_Enum*'

Payloads

Baseline
Compare

System.Tests.Perf_Enum.TryParseGeneric_Flags(text: "Red, Orange, Yellow, Green, Blue")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_Enum.Parse_Flags(text: "Red, Orange, Yellow, Green, Blue")

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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.Sort<IntStruct>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
List - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	7.14 μs	8.05 μs	1.13	0.50	False
Array - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	5.01 μs	7.62 μs	1.52	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.Collections.Sort<IntStruct>*'

Payloads

Baseline
Compare

System.Collections.Sort<IntStruct>.List(Size: 512)

ETL Files

Histogram

JIT Disasms

System.Collections.Sort<IntStruct>.Array(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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Buffers.Text.Tests.Utf8ParserTests

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
TryParseInt64 - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	14.40 ns	17.99 ns	1.25	0.10	True

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.Text.Tests.Utf8ParserTests*'

Payloads

Baseline
Compare

System.Buffers.Text.Tests.Utf8ParserTests.TryParseInt64(value: 9223372036854775807)

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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.Perf_Frozen<Int16>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
TryGetValue_True - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	184.83 ns	271.49 ns	1.47	0.28	False
TryGetValue_True - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	1.84 μs	2.17 μs	1.18	0.16	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_Frozen<Int16>*'

Payloads

Baseline
Compare

System.Collections.Perf_Frozen<Int16>.TryGetValue_True(Count: 64)

ETL Files

Histogram

JIT Disasms

System.Collections.Perf_Frozen<Int16>.TryGetValue_True(Count: 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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.Perf_DefaultFrozenDictionary

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
TryGetValue_True_FrozenDictionary - Duration of single invocation 📈 - ADX Test Multi Config Graph	937.72 ns	1.02 μs	1.09	0.01	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_DefaultFrozenDictionary*'

Payloads

Baseline
Compare

System.Collections.Perf_DefaultFrozenDictionary.TryGetValue_True_FrozenDictionary(Count: 100)

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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Numerics.Tests.Perf_BigInteger

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Divide - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	428.25 ns	586.51 ns	1.37	0.07	False
ToStringD - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	16.14 ns	18.14 ns	1.12	0.07	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.Numerics.Tests.Perf_BigInteger*'

Payloads

Baseline
Compare

System.Numerics.Tests.Perf_BigInteger.Divide(arguments: 1024,512 bits)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_BigInteger.ToStringD(numberString: 123)

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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.ContainsKeyFalse<Int32, Int32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
ConcurrentDictionary - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	1.83 μs	2.02 μs	1.11	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.Collections.ContainsKeyFalse<Int32, Int32>*'

Payloads

Baseline
Compare

System.Collections.ContainsKeyFalse<Int32, Int32>.ConcurrentDictionary(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	TigerUbuntu
Baseline	c3940f603a42e5c78f888ba2cbab76fbfda29d83
Compare	7c90c578310f0071374878d002871418533ec005
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.CreateAddAndClear<Int32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Array - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	392.75 ns	551.57 ns	1.40	0.02	True

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.CreateAddAndClear<Int32>*'

Payloads

Baseline
Compare

System.Collections.CreateAddAndClear<Int32>.Array(Size: 512)

ETL Files

Histogram

JIT Disasms

Docs

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

Author:	performanceautofiler[bot]
Assignees:	jakobbotsch
Labels:	os-linux, arch-x64, area-CodeGen-coreclr, untriaged, runtime-coreclr
Milestone:	-

[jakobbotsch]

Thanks @EgorBo. That change was supposed to give preheaders sane block weights (previously they just downright didn't make sense in some cases). I'll double check that the block weights on the preheaders make more sense now than before. If they do it's probably something to come back to later in .NET 9 since we are expecting several more rounds of churn around the block layout algorithm and the problem might be in there.

[jakobbotsch]

It does look like a bug in the new weight logic.