# tuneup.c

**Jason Moxham
**
J.L.Moxham@maths.soton.ac.uk

*Wed, 5 Mar 2003 19:42:16 +0000*

I writing a high and low part multiplication and as you are probably awar=
e the=20
benefit at very large sizes is very small , so I have a threshold to swit=
ch=20
over to normal mpn_mul . However the tuneup program can not detect this=20
crossover very well. Is there some sort of fudge factor (eg like=20
function_fudge in struct param_t ) so that I can tell the tuneup program =
to=20
switch over when mpn_mullowhalf is about within 1% of mpn_mul . I really =
need=20
something like this because for even larger sizes the speeds of the two=20
functions are always about the same , so no definite crossover can be=20
detected. This is more important for the highpart multiplication than the=
=20
lowpart , as the probability of a detectible error increases with size.
Note the "crossover" sizes are approx 16000 to 30000 limbs , ie well in f=
ft=20
ranges
thanks
Jason