Re: branch guessing, Microarchitectural support for counting

On Thu, 26 Dec 2024 19:11:01 +0000, John Levine wrote:

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.

There was a PHD Thesis CMU circa 1978 called the "maximal munching
method"
and was supposed to match the largest executable patterns to the DAG
corresponding to the VAX 11/780 instruction set. The method was
producing
fast dense code and everyone was happy until they figured out that a
comparison was backwards and they were actually matching the smallest
executable patterns; yet the code ran faster that way than before they
fixed it.

Unless you've profiled the code and you data to support your branch
guesses, just write it in the clearest way you can.