You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
[.NET 10 vs main] WASM-Mono performance regression tracking
This issue tracks the actionable WASM-Mono results from the reviewed release/10.0 vs main windowed comparison. Draft generated 2026-08-17. GitHub issue/PR states refreshed from live metadata on 2026-08-17. User decisions and AI-attributed notes applied on 2026-08-17.
Use the checkboxes in place: leave an item unchecked while investigation, filing, ownership, or verification remains; check it when that work is finished. Feel free to edit or append status directly on the same checklist line as work progresses. There is intentionally no separate Completed section.
Within each section, items are ordered by worst reviewed percentage (largest first). Regression count is used only to break ties.
Excluded: fixed, acceptable, not-applicable, noise, improved, baseline-outlier, covered, and linked.
Actionable summary
Area
Items
Needs investigation (runtime + ungrouped missed)
4
Active tracked runtime regressions
0
Autofiling issues needing transfer/resolution
13
Missed regression date groups needing filing
7
Total checkboxes
24
Needs investigation
Show 4 items
Items requiring a second look before deciding whether to file, transfer, accept, or close them.
dotnet/runtime#131159 — acceptable; closed-completed; 81 WASM-Mono reviewed regressions; worst +105.4%; regression date 2026-07-14. Review note: Seems related to the same change, both CoreCLR and Wasm-Mono seem regressed. AI Note (user-approved): Closed as an accepted trade-off from scoping vectorization away from browser/WASM. (evidence) Representative chart.
dotnet/runtime#126361 — needs-investigation; closed-not-planned; 8 WASM-Mono reviewed regressions; worst +53.7%; regression date 2026-03-27. Review note: Marked acceptable as the impacts on CoreCLR were small. Still needs a Wasm-Mono-AOT look over. Representative chart.
dotnet/runtime#125514 — needs-investigation; PR-merged; 8 WASM-Mono reviewed regressions; worst +31.7%; regression date 2026-03-16. Review note: This is linked to a PR instead of an issue (need to investigate how this happened). Still seems to be regressed and doesn't seem to have recent work. Representative chart.
Active tracked regressions
No items selected by the current inclusion rules.
Autofiling issues needing transfer or resolution
Show 13 items
Uncorrelated autofiling issues that are unmarked or marked needs-investigation.
dotnet/perf-autofiling-issues#72117 — needs-investigation; open; 1 WASM-Mono reviewed regressions; worst +290.6%; regression date 2026-04-27. Review note: Issue is slightly before the actual regression, but the regression seems rule. Representative chart.
dotnet/perf-autofiling-issues#72789 — needs-investigation; open; 2 WASM-Mono reviewed regressions; worst +235.5%; regression date 2026-05-07. Review note: System.Collections.Tests.Perf_BitArray.BitArrayBoolArrayCtor(Size: 512) did regress here and is still regressed. Representative chart.
dotnet/perf-autofiling-issues#61045 — needs-investigation; closed-completed; 14 WASM-Mono reviewed regressions; worst +134.1%; regression date 2025-08-17. Review note: Marked as chrome update but still seems to be real for some (MathBenchmarks?), maybe worth investigation. (Such as System.MathBenchmarks.Single.Log10P1) Representative chart.
dotnet/perf-autofiling-issues#61311 — needs-investigation; closed-completed; 11 WASM-Mono reviewed regressions; worst +134.1%; regression date 2025-08-17. Review note: Marked as chrome update but still seems to be real for some (MathBenchmarks?), maybe worth investigation. Representative chart.
dotnet/perf-autofiling-issues#64542 — needs-investigation; open; 17 WASM-Mono reviewed regressions; worst +75.7%; regression date 2025-10-27. Review note: Most just should be double checked as this is still open. There is a mix of nearly fully un-regressed tests and improved tests. Representative chart.
dotnet/perf-autofiling-issues#76374 — needs-investigation; open; 1 WASM-Mono reviewed regressions; worst +65.2%; regression date 2026-07-13. Review note: AI Note: High-confidence attribution to Int128.CopySign PR #130563; no fix or follow-up yet. (evidence) Representative chart.
dotnet/perf-autofiling-issues#76373 — needs-investigation; open; 3 WASM-Mono reviewed regressions; worst +57.8%; regression date 2026-07-13. Review note: At least one of the tests is well regressed. Representative chart.
dotnet/perf-autofiling-issues#71475 — needs-investigation; open; 4 WASM-Mono reviewed regressions; worst +42.0%; regression date 2026-04-14. Review note: Not related to this date but one shortly after, seems uninvestigated. Representative chart.
dotnet/perf-autofiling-issues#70472 — needs-investigation; open; 9 WASM-Mono reviewed regressions; worst +31.7%; regression date 2026-03-16. Review note: Seems to have been missed (or original was already transferred if this is a dup). Representative chart.
Missed regression groups needing filing
Show 7 items
Dated groups containing at least one needs-investigation or truly-missed regression. The checkbox represents the group as one candidate public tracking issue.
Regression group 2026-06-25 — 1 actionable of 1 related regressions; worst +76.4%; queues Ubuntu-x64-Viper. Review notes: Also baseline-outlier
[.NET 10 vs main] WASM-Mono performance regression tracking
This issue tracks the actionable
WASM-Monoresults from the reviewed release/10.0 vs main windowed comparison. Draft generated 2026-08-17. GitHub issue/PR states refreshed from live metadata on 2026-08-17. User decisions and AI-attributed notes applied on 2026-08-17.Use the checkboxes in place: leave an item unchecked while investigation, filing, ownership, or verification remains; check it when that work is finished. Feel free to edit or append status directly on the same checklist line as work progresses. There is intentionally no separate Completed section.
Within each section, items are ordered by worst reviewed percentage (largest first). Regression count is used only to break ties.
Inclusion rules
Included:
needs-investigation, confirmed runtime regressions, unmarked runtime/autofiling/missed items, and missed regressions markedtruly-missed.Excluded:
fixed,acceptable,not-applicable,noise,improved,baseline-outlier,covered, andlinked.Actionable summary
Needs investigation
Show 4 items
Items requiring a second look before deciding whether to file, transfer, accept, or close them.
dotnet/runtime#131159 — acceptable;
closed-completed; 81WASM-Monoreviewed regressions; worst +105.4%; regression date 2026-07-14. Review note: Seems related to the same change, both CoreCLR and Wasm-Mono seem regressed. AI Note (user-approved): Closed as an accepted trade-off from scoping vectorization away from browser/WASM. (evidence) Representative chart.dotnet/runtime#129860 — needs-investigation;
open; 55WASM-Monoreviewed regressions; worst +62.1%; regression date 2026-06-24. Review note: Need to double check it stays, but it seems fixed. (as stated in [Perf] Linux/arm64: 9 Regressions on 6/24/2026 7:31:32 AM +00:00 runtime#129860 (comment)) Representative chart.dotnet/runtime#126361 — needs-investigation;
closed-not-planned; 8WASM-Monoreviewed regressions; worst +53.7%; regression date 2026-03-27. Review note: Marked acceptable as the impacts on CoreCLR were small. Still needs a Wasm-Mono-AOT look over. Representative chart.dotnet/runtime#125514 — needs-investigation;
PR-merged; 8WASM-Monoreviewed regressions; worst +31.7%; regression date 2026-03-16. Review note: This is linked to a PR instead of an issue (need to investigate how this happened). Still seems to be regressed and doesn't seem to have recent work. Representative chart.Active tracked regressions
No items selected by the current inclusion rules.
Autofiling issues needing transfer or resolution
Show 13 items
Uncorrelated autofiling issues that are unmarked or marked
needs-investigation.dotnet/perf-autofiling-issues#76371 — needs-investigation;
open; 20WASM-Monoreviewed regressions; worst +730.1%; regression date 2026-07-10. Representative chart.dotnet/perf-autofiling-issues#72117 — needs-investigation;
open; 1WASM-Monoreviewed regressions; worst +290.6%; regression date 2026-04-27. Review note: Issue is slightly before the actual regression, but the regression seems rule. Representative chart.dotnet/perf-autofiling-issues#72789 — needs-investigation;
open; 2WASM-Monoreviewed regressions; worst +235.5%; regression date 2026-05-07. Review note: System.Collections.Tests.Perf_BitArray.BitArrayBoolArrayCtor(Size: 512) did regress here and is still regressed. Representative chart.dotnet/perf-autofiling-issues#61045 — needs-investigation;
closed-completed; 14WASM-Monoreviewed regressions; worst +134.1%; regression date 2025-08-17. Review note: Marked as chrome update but still seems to be real for some (MathBenchmarks?), maybe worth investigation. (Such as System.MathBenchmarks.Single.Log10P1) Representative chart.dotnet/perf-autofiling-issues#61311 — needs-investigation;
closed-completed; 11WASM-Monoreviewed regressions; worst +134.1%; regression date 2025-08-17. Review note: Marked as chrome update but still seems to be real for some (MathBenchmarks?), maybe worth investigation. Representative chart.dotnet/perf-autofiling-issues#73156 — needs-investigation;
open; 4WASM-Monoreviewed regressions; worst +134.1%; regression date 2026-05-14. Representative chart.dotnet/perf-autofiling-issues#64542 — needs-investigation;
open; 17WASM-Monoreviewed regressions; worst +75.7%; regression date 2025-10-27. Review note: Most just should be double checked as this is still open. There is a mix of nearly fully un-regressed tests and improved tests. Representative chart.dotnet/perf-autofiling-issues#72937 — needs-investigation;
open; 2WASM-Monoreviewed regressions; worst +72.0%; regression date 2026-05-12. Representative chart.dotnet/perf-autofiling-issues#75292 — needs-investigation;
open; 9WASM-Monoreviewed regressions; worst +70.3%; regression date 2026-06-25. Review note: Likely due to Upgrade Emscripten to 5.0.6 & LLVM to 23 runtime#129299 but no obvious regression investigation. AI Note: Attributed to toolchain-upgrade PR #129299; no fix, revert, or acceptance recorded. (evidence) Representative chart.dotnet/perf-autofiling-issues#76374 — needs-investigation;
open; 1WASM-Monoreviewed regressions; worst +65.2%; regression date 2026-07-13. Review note: AI Note: High-confidence attribution to Int128.CopySign PR #130563; no fix or follow-up yet. (evidence) Representative chart.dotnet/perf-autofiling-issues#76373 — needs-investigation;
open; 3WASM-Monoreviewed regressions; worst +57.8%; regression date 2026-07-13. Review note: At least one of the tests is well regressed. Representative chart.dotnet/perf-autofiling-issues#71475 — needs-investigation;
open; 4WASM-Monoreviewed regressions; worst +42.0%; regression date 2026-04-14. Review note: Not related to this date but one shortly after, seems uninvestigated. Representative chart.dotnet/perf-autofiling-issues#70472 — needs-investigation;
open; 9WASM-Monoreviewed regressions; worst +31.7%; regression date 2026-03-16. Review note: Seems to have been missed (or original was already transferred if this is a dup). Representative chart.Missed regression groups needing filing
Show 7 items
Dated groups containing at least one
needs-investigationortruly-missedregression. The checkbox represents the group as one candidate public tracking issue.Regression group 2026-06-25 — 1 actionable of 1 related regressions; worst +76.4%; queues
Ubuntu-x64-Viper. Review notes: Also baseline-outlierSystem.Linq.Tests.Perf_ImmutableArrayExtensions.SequenceEqual(input: ICollection)—Ubuntu-x64-Viper; +76.4%; 7,542 → 13,306; mark needs-investigation; note: Also baseline-outlierRegression group 2026-02-25 — 1 actionable of 1 related regressions; worst +76.4%; queues
Ubuntu-x64-Viper. Review notes: Also baseline-outlierSystem.Linq.Tests.Perf_ImmutableArrayExtensions.SequenceEqual(input: ICollection)—Ubuntu-x64-Viper; +76.4%; 7,542 → 13,306; mark needs-investigation; note: Also baseline-outlierRegression group 2025-12-13 — 4 actionable of 4 related regressions; worst +5.8%; queues
Ubuntu-x64-Viper. Review notes: 09/15/25, 11/03/25, 12/13/25 | 12/13/25PerfLabTests.CastingPerf.CheckObjIsInterfaceYes—Ubuntu-x64-Viper; +5.8%; 659,735 → 698,296; mark needs-investigation; note: 09/15/25, 11/03/25, 12/13/25PerfLabTests.CastingPerf.CheckIsInstAnyIsInterfaceYes—Ubuntu-x64-Viper; +5.8%; 659,727 → 698,194; mark needs-investigation; note: 09/15/25, 11/03/25, 12/13/25System.Numerics.Tests.Perf_VectorConvert.Convert_float_int—Ubuntu-x64-Viper; +5.2%; 2,778 → 2,924; mark needs-investigation; note: 12/13/25System.Tests.Perf_Array.ArrayCopy3D—Ubuntu-x64-Viper; +5.2%; 2,147 → 2,258; mark needs-investigation; note: 12/13/25Regression group 2025-11-03 — 2 actionable of 2 related regressions; worst +5.8%; queues
Ubuntu-x64-Viper. Review notes: 09/15/25, 11/03/25, 12/13/25PerfLabTests.CastingPerf.CheckObjIsInterfaceYes—Ubuntu-x64-Viper; +5.8%; 659,735 → 698,296; mark needs-investigation; note: 09/15/25, 11/03/25, 12/13/25PerfLabTests.CastingPerf.CheckIsInstAnyIsInterfaceYes—Ubuntu-x64-Viper; +5.8%; 659,727 → 698,194; mark needs-investigation; note: 09/15/25, 11/03/25, 12/13/25Regression group 2025-09-15 — 2 actionable of 2 related regressions; worst +5.8%; queues
Ubuntu-x64-Viper. Review notes: 09/15/25, 11/03/25, 12/13/25PerfLabTests.CastingPerf.CheckObjIsInterfaceYes—Ubuntu-x64-Viper; +5.8%; 659,735 → 698,296; mark needs-investigation; note: 09/15/25, 11/03/25, 12/13/25PerfLabTests.CastingPerf.CheckIsInstAnyIsInterfaceYes—Ubuntu-x64-Viper; +5.8%; 659,727 → 698,194; mark needs-investigation; note: 09/15/25, 11/03/25, 12/13/25Regression group 2026-03-02 — 1 actionable of 1 related regressions; worst +5.4%; queues
Ubuntu-x64-Viper.Loops.StrengthReduction.SumLongsArrayStrengthReduced—Ubuntu-x64-Viper; +5.4%; 17,958 → 18,929; mark truly-missedRegression group 2026-01-22 — 1 actionable of 1 related regressions; worst +5.4%; queues
Ubuntu-x64-Viper.Loops.StrengthReduction.SumLongsArrayStrengthReduced—Ubuntu-x64-Viper; +5.4%; 17,958 → 18,929; mark truly-missed