> From this I understand that it takes around about the same number of
> interations as the size of the exponent to establish primality.
Correct. See the FAQ at the end of this message for more info.
> I've got several UltraSPARCs I've pressed into service and currently
> have 7 exponents checked out being tested with MacLucasUNIX. When I
> filled out the manual checkout form I assumed, for lack of better
> information, that an UltraSPARC would perform like a Pentium. This
> doesn't appear to be at all close to the truth. My first assignment
> was for 7902277. The account details indicated this would take 600
> hours of CPU on a 270MHz Pentium.
It should perform aproximatly like a Pentium, if you check MacLucasUNIX
compiled on a pentium and a sparc. However, on intel chips, we have a
nice edge: George Woltman's highly optimized assembler version. I doubt
any C code could even aproach it.
-Lucas
_________________________________________________________________
Unsubscribe & list info -- http://www.scruz.net/~luke/signup.htm
Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
