----- Original Message -----
From: "Vincent Trouilliez" <[EMAIL PROTECTED]>


> > There's for sure a lot of potential for improvement, but declaring
> > something "top-priority" because that's your opinion won't do
> > anything.  There are many similar minor improvements that could be
> > made, they probably sum up to maybe 10...20 % of possible savings if
> > really *all* of them were sorted out
>
> Really ? Sorry didn't realise that the H/W multiplier was of so little
> benefit when doing calculations... maybe Atmel could just remove it from
> their chip to sell them cheaper and/or free the space for some more
> useful peripheral then... :-)
> What could they replace it with mmmmm.... a few D/A converters would be
> fine... :-)
>

The hardware multiplier makes a difference when doing mulitplication, which
take a very small percentage of the run time of most real programs -
therefore, overall, it's a small issue.  Obviously the hardware multiplier
is a lot faster than a software routine at the actual multiply, it's just
that it makes little difference to most programs as a whole.





_______________________________________________
AVR-GCC-list mailing list
[email protected]
http://lists.nongnu.org/mailman/listinfo/avr-gcc-list

Reply via email to