Skip to content

Conversation

@vargaz
Copy link
Contributor

@vargaz vargaz commented Oct 15, 2021

Previously, these were all implemented using a slowpath to a JIT
icall. Instead, use the normal calling sequence and add a gsharedvt
out wrapper at the end if needed.

Previously, these were all implemented using a slowpath to a JIT
icall. Instead, use the normal calling sequence and add a gsharedvt
out wrapper at the end if needed.
* Implement a fastpath for mrgctx fetches.
* Load some entries from the gsharedvt info struct instead of doing an rgctx fetch.
@vargaz vargaz changed the title [mono][llvmonly] Optimize virtual calls in gsharedvt methods. [mono][llvmonly] Optimize virtual calls/rgctx fetches in gsharedvt methods. Oct 16, 2021
@marek-safar
Copy link
Contributor

@SamMonoRT @lambdageek please review

@vargaz vargaz merged commit 62eafc1 into dotnet:main Oct 19, 2021
@vargaz vargaz deleted the llvmonly-gsharedvt-opt branch October 19, 2021 21:54
@ghost ghost locked as resolved and limited conversation to collaborators Nov 19, 2021
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.

3 participants