Re: branch guessing, Microarchitectural support for counting

John Levine <johnl@taugh.com> schrieb:

According to Michael S  <already5chosen@yahoo.com>:

Yes, compilers often generate such code.
When coding in asm, I typically know at least something about
probability of branches, so I tend to code it differently:

>
The first version of FORTRAN had a FREQUENCY statement which let you tell it the
relative likelihood of each of the results of a three-way IF, and the expected number of
iterations of a DO loop.  It turned out to be useless, because programmers usually
guessed wrong.
>
The final straw was a compiler where they realized FREQUENCY was implemented
backward and nobody noticed.
>
Unless you've profiled the code and you data to support your branch guesses,
just write it in the clearest way you can.

There is one partial expeption: Putting error handling, which
should occur very infrequently, in a cold partition can indeed
bring benefits, and the compiler can not always figure it out;
heuristics like "a NULL check is less likely to be taken" can
be wrong.

But then again, defining an "unlikely" macro and having code like

    if (unlikely (a>b))
      {
         /* Do some error handling.  */        
      }

probably increases the readability over the naked condition, so...