[timmisiak]

My point is the smaller encoding is what gives you the performance benefit. When done across an entire function/module, you can get a measurable increase in hit rate for the instruction cache. Not that the instruction itself is faster. Apologies if that wasn't clear.

[FullyFunctional]

No, I got that point and it's vanishingly small. It _only_ affects miss rate (ie. does nothing if you are hitting in the cache) and the effect on miss rate is minuscule.