Re: Reordering of functions

> Aren't "with branch prediction" and "caches are disabled" somewhat
> mutually exclusive statements?


Depends. When you think of a branch target buffer then you are correct.
This buffer is a small cache which holds branch targets previously
computed. But there are also static branch predictions which just
rely on the instruction and the jump direction. For example,
conditional jumps with a backward displacement might be always predicted
as taken. Here the buffering of the branch target might be omitted.


> Function reordering might help also in situations where the processor
> supports jumps that are differently encoded depending on the jump length
> (such as the bra/brl opcodes on 65c816, or similar on x86). If a tailcall
> occurs to a function that is located within a short distance, it might
> be faster with than a tailcall with a larger distance, because the opcodes
> differ.


OK, I agree, that's a good point.

Return to the comp.compilers page.
Search the comp.compilers archives again.