There are occasional announcements about overclocking various processors, and I know
that some Mersenne contributors describe their clock speed as xxx@yyy where yyy>xxx
obviously.
However, surely this project is one where overclockers do more harm than good? When
you're running your favourite game, it doesn't matter if a couple of incorrect
calculations creep in, but the Mersenne project involves very long calculations with
basically a boolean answer at the end. One wrong result during this time could ruin
the answer. Now I know that the algorithms include a lot of error catching, but once
the processor is run to the point of instability there could easily be errors in the
error protection. (I'll try a probability analysis later... Basically we need the
probability of one error occurring within a certain number of instructions of a
previous error.)
My opinion is that it's better to have fewer correct results than to have the central
database poisoned by loads of "don't think it's prime, but the user was overclocking"
results, which of course cannot be distinguished from perfect answers. I'd trade two
unreliable answers for one honest result. (What ends up happening is even worse.
Mismatching checksums mean that the tests must be repeated until a consensus is
reached.)
A high score table is brilliant, and excites all contributors, but unfortunately a few
seem more interested in climbing the table than in what the project is about. If
people want to run overclocked, they should work on a project which isn't so sensitive
to noise, such as SETI (okay, hardly an original suggestion here). SETI takes a noisy
input to begin with, and introducing the odd bit of noise won't harm the results that
much.
People whose machines show any sign of instability at all should really stick to
factoring, although these are just the sort of people who'll be issued with primality
tests because of the apparently high performance. I'm tempted to say: go and find
another high score table to climb.
So after all that, here's a suggestion: How about an error counting system in
mprime/prime95? (Okay there might already be one but I haven't seen it mentioned
anywhere.) Every time an error is detected, a counter is incremented, and the final
result sent back to the server. An answer coming back with 200 errors might be
considered less reliable than one with no errors at all.
Yours,
======= Gareth Randall =======
_________________________________________________________________________
Unsubscribe & list info -- http://www.scruz.net/~luke/signup.htm
Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
