alexcrichton opened PR #2759 from fast-call2
to main
:
This continues https://github.com/bytecodealliance/wasmtime/pull/2757 a bit more by optimizing calls into WebAssembly. The first commit should affect all platforms, but is only a minor speedup. The second commit is a macOS-specific improvement but is a very large improvement for macOS. I believe after this all platforms should be again performing roughly on-par with one another.
alexcrichton updated PR #2759 from fast-call2
to main
.
bnjbvr submitted PR Review.
bnjbvr submitted PR Review.
bnjbvr created PR Review Comment:
nit: unregisters
bnjbvr created PR Review Comment:
Missing comment here.
bnjbvr created PR Review Comment:
There was a check in the unix implementation that the
jmp_buf
could be set to 1 (meaning a custom signal handler has run and the trap handler should return early). Is it not necessary anymore?
bnjbvr created PR Review Comment:
Missing comment here?
bnjbvr created PR Review Comment:
Can we check that the start is the same? And as a poor man's check for function, that the
functions.size()
match?
alexcrichton submitted PR Review.
alexcrichton created PR Review Comment:
Ah yeah I realized that it was no longer necessary since we don't run the custom trap handler on macOS, it's only run on Unix and Windows now.
alexcrichton submitted PR Review.
alexcrichton created PR Review Comment:
Weird I remember writing docs here... I guess I accidentally blew them away!
alexcrichton updated PR #2759 from fast-call2
to main
.
alexcrichton merged PR #2759.
Last updated: Dec 23 2024 at 12:05 UTC