[EMAIL PROTECTED] wrote:
>
> Hi,
>
> ....
>
> FWIW if you have a dual CPU system (mine is running 2 * PIII-850
> on a Supermicro P6DBE m/b), running ECM on small exponents
> on one processor makes an ideal foil to running LL tests on the
> other.
Ditto on my dual PIII-1GHz.
> The ECM process uses so little memory that it runs
> practically in the L2 cache, except during Stage 2. The LL test will
> slow down a bit during ECM stage 2, but that's only about 30% of
> the time -
And the slow-down is not very significant--seems to be less than 10%.
> whereas running LL tests on both processors can slow
> both processes down quite substantially due to the loading on the
> memory bus.
Definitely. About 30% on each processor here. Meaning I used to have
about 1.4 processor-equivalents when both were doing LL. Now I have
close to 1.0 doing LL and another 1.0 helping to find factors. Seems
better overall.
Perhaps a Mersenne number I would have got will be shown to be prime. So
be it.
It is a thrill to be able to contribute to this effort.
Gerry
--
mailto:[EMAIL PROTECTED]
Gerry Snyder, AIS Symposium Chair, Region 15 RVP
Member San Fernando Valley, Southern California Iris Societies
in warm, winterless Los Angeles--USDA 9b-ish, Sunset 18-19
my work: helping generate data for: http://galileo.jpl.nasa.gov/
_________________________________________________________________________
Unsubscribe & list info -- http://www.scruz.net/~luke/signup.htm
Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
