[JoheyDev888]

50x isn't reasonable, it's a cache disaster. Any perf win from avoiding JIT gets eaten alive.

[dzaima]

Only if it is all actually used at runtime; and presumably the vast majority of possible decoding starting points won't be.

[wmf]

This is a great case for link-time code reordering. You can put all the hot code together so the unused code will never be loaded.

[po1nt]

I wouldn't jump to conclusions. Instructions aren't so big anyways and they are optimized JIT by CPU.