--- In gbadev@y..., Martin Piper <martinp@a...> wrote:
> To accurately multiply two 16.16 number you shouldn't need to
split them up
> in to separate 16 bit multiplies, commonly known as "using the
highschool
> math" (sic) method for example.

Very true. Thanks guys... a small snippet

fmul32:
@ inputs are in r0 and r1, return in r0
smull r2,r3,r0,r1
mov r1,r2,lsr#16
orr r0,r1,r3,lsl#16
bx lr

Thats the entire function [with corrected orr]. I get 2.5x faster
in VBA [250k/sec].

I will also take your advice with the smula instruction.

Tom