Mail Archives: djgpp/1996/07/15/11:50:23
In article <4s4sue$qbc AT status DOT gen DOT nz>, Bruce Foley
<brucef AT central DOT co DOT nz> writes
>>Although I've never used setpixel routines, I was always under the impression
>>that (x + y << 8 + y << 6) is faster than (x + 320 * y).
>
>>.splitbung
>>--
>>* TQ 1.0 * The 'Just So Quotes'.
>>OJ's WWW address is http://////////
>
>I think this is true of older processors, but on a 486, a
>well designed mul instruction is just as fast (or faster?),
>depending on the value of the operands.
>Don't know about the Pentium though, since simple
>instructions can be useful for keeping both Pipes going.
>-Optimising is a hell of a thing...
>
An imul or mul op on P5 and lower is *slow* (13 clks). (A floating point
fmul is fast!)
However its actually irrelevant, just trust gcc to do the right thing
with *CONSTANT. For *320 it generates a 'lea eax,[eax+4*eax];sal eax,6'
pair, which is the same as the shift code above.
--
Paul Shirley
- Raw text -