Forums before death by AOL, social media and spammers... "We can't have nice things"
|    comp.compilers    |    Compiler construction, theory, etc. (Mod    |    2,753 messages    |
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
|    Message 1,243 of 2,753    |
|    Tim Frink to All    |
|    Static branch prediction    |
|    03 Mar 08 10:37:54    |
      From: plfriko@yahoo.de              Hi,              Some processors use a static branch prediction. The predicted outcome       of a jump depends on the instruction, i.e. a 16-bit conditional jump       instruction is predicted as taken while a 32-bit instruction with a       forward displacement is predicted as not taken.              If the outcome of a jump would be known in advance, one could use the       appropriate jump instructions to avoid misprediction, thus       accelerating the program execution. I assume that profiling data could       be used for that to figure out the more probable jump behavior.              This idea is probably not new, so I wonder if you know any       compilers/optimizers that apply this technique? Do you have own       experiences or know any papers/reports where any results are       presented?              Regards,       Tim              --- SoupGate-Win32 v1.05        * Origin: you cannot sedate... all the things you hate (1:229/2)    |
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
(c) 1994, bbs@darkrealms.ca