IR interpreter: Use threaded dispatch with GCC and Clang

Browse Source

Every op ended with a break back to one shared indirect jump, which the
CPU has to predict for every op in the program. With labels as values,
each op jumps through a table from its own site instead, which predicts
much better: an integer-heavy benchmark runs about 13% faster on an M1.
Other compilers keep the switch, and ops missing from the table fall back
to it.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

...

This commit is contained in:

Henrik RydgårdandClaude Opus 5.5 committed 2026-09-25 11:47:17 -06:00

1 parent 7eb371b231

commit d1c04d70a6

1 file changed

+570 -365

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

Core/MIPS/IR/IRInterpreter.cpp

+570 -365

File diff suppressed because it is too large. Load diff