Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[wasm] Enable System.Numerics vectors SIMD #78068

Merged

Conversation

radekdoulik
Copy link
Member

@radekdoulik radekdoulik commented Nov 8, 2022

This helps in cases where there's only S.N.Vector path in the BCL code, like SpanHelpers.IndexOfChar(ref char searchSpace, char value, int length). In this case the Span:IndexOf char measurement improves from 0.0143ms to 0.0114ms.

@ghost ghost closed this Dec 8, 2022
@ghost
Copy link

ghost commented Dec 8, 2022

Draft Pull Request was automatically closed for 30 days of inactivity. Please let us know if you'd like to reopen it.

@radekdoulik radekdoulik reopened this Dec 12, 2022
@radekdoulik radekdoulik marked this pull request as ready for review December 12, 2022 13:48
@radekdoulik
Copy link
Member Author

runtime (Build Browser wasm Linux Release LibraryTests_AOT) fails on main too, for example in this CI run https://github.com/dotnet/runtime/runs/9978728829

@radekdoulik radekdoulik merged commit b33aede into dotnet:main Dec 12, 2022
radekdoulik added a commit to radekdoulik/runtime that referenced this pull request Dec 14, 2022
This should fix size regression introduce with dotnet#78068

The untrimmed S.N.Vector class added few kilobytes to the assemblies
of the bench sample. That wasn't that bad, OTOH the code produced
by the aot compiler was much larger, 5MB in this case.

So this will case default non-SIMD case. In the case of SIMD build we
will need more investigation.
radical pushed a commit that referenced this pull request Dec 14, 2022
This should fix size regression introduce with #78068

The untrimmed S.N.Vector class added few kilobytes to the assemblies
of the bench sample. That wasn't that bad, OTOH the code produced
by the aot compiler was much larger, 5MB in this case.

So this will case default non-SIMD case. In the case of SIMD build we
will need more investigation.
@ghost ghost locked as resolved and limited conversation to collaborators Jan 12, 2023
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants