| Re: [AD] Color convertors |
[ Thread Index |
Date Index
| More lists.liballeg.org/allegro-developers Archives
]
>How come the register permutation gave such a slow down? step2 should have
>been better than step 1 due to smaller code, or at worst, it should give the
>same numbers (within a reasonable range).
Frankly, I think the differences are small as it is. I'd like to see
numbers from two or three runs with the same code so we have a typical
range of what is to be expected for each piece of code.
>Same for step2->step3, step 3 should be faster (one less instruction!). The
>numbers are within the 1% margin of error though.
That's squareroot of #counts, right? From a first glance, I'd say most of
the different counts are within 1%. Like I said, I'd like to see two or
three independant measurements.
Evert