<<This brings up a very interesting question, what is the average speed of a
machine participating in GIMPS? Does PrimeNet have more data then the CPU
type?
I would assume so. Can we get a breakdown of the average CPU speed of a GIMPS
producer and track this over time to see if we are keeping up with Moore's
law?>>
Well, not only are our machines getting faster as people see the light and
upgrade for the good of the project (more likely because their copy of Duke
Quakem 64 won't run on old computers, hee hee), people may be leaving them on
longer/shorter, and we always have new people joining. So GIMPS has the
potential to run past Moore's Law, until a copy of GIMPS is on every computer
in the world! *cackle*
<<Can the average machine speed be tracked from previous data? Account for the
growth in the number of participating machines and come up with an average
machine speed from year to year?>>
One would need access to some sort of logs to do that calculation, but I'll
crunch some numbers I see on entropia.com right now.
<<Mersenne PrimeNet Server 4.0 (Build 4.0.017)
Status Summary Report 29 Jul 1999 18:00 (29 Jul 1999 11:00 Pacific)
------- Aggregate CPU Statistics, P90 Units* -------
Last 7 Days Average Cumulative Today
from 23 Jul 1999 06h from 29 Jul 1999 06h
Test Type CPU yr/day GFLOP/s CPU years CPU yr/day
------------ ---------- ---------- ---------- ----------
Lucas-Lehmer 59.773 719.524 27.914 55.912
Factoring 2.286 27.515 0.858 1.718
---------- ---------- ---------- ----------
TOTALS 62.058 747.039 28.772 57.630
------- Internet CPU and Server Resources -------
Machines Applied on 14033 Accounts Server Synchronization 07 May 1999
08:42
Intel Pentium PII/Pro : 10727 Total exponents merged : 211640
Intel Pentium : 6029 Updated only : 98047
AMD K6 : 1701 Added for testing : 109629
Intel 486 : 345 Retained in IPS cleared list : 4112
Cyrix : 495 Cleared IPS tests removed : 20384
Unspecified type : 3955 GIMPS tests removed / purged : 427
---------------------- -------
TOTAL : 23252 Total Cleared by IPS to date :
104385>>
So, the important things I'll be working with are:
Total machines: 23252. P90 CPU Years/day, 7 day average: 62.058.
However, years/day is an awkward unit to work with, so I'll convert it to P90
days/day (i.e. how many P90s we'd need running at full tilt [constantly on]
to produce the same work). I'll spare you the conversion and say it's
22,666.2 P90s. Let's be stupid and multiply that by 90: 2,039,958 P1s (what
has Intel been smoking?). And now let's bring the actual number of machines
we're running:
23252 * P_MegaHertz = 2,039,958 P1.
Solving, we see that the average GIMPSter runs a machine that is never used
for anything and is left constantly on for 24 hours a day with a P87.74
processor. (Obviously by the machine tabulation above, the average GIMPSter
runs a significantly faster computer, but doesn't leave it on for 24 hours a
day). Eh? This is different than the old figure I remember. However, I
calculated that BEFORE I knew how many computers GIMPS had. So, I'll redo the
calculation based on accounts.
14033 (accounts) * P_MegaHerta = 2,039,958 P1.
Solving here, we see that the average account is equivalent to a single
machine running at full tilt with a P145.37 processor. That's more like it.
If I've had a major brain drain in my calculations, feel free to correct my
error on the list.
S. "I want 2 million P1 processors!" L.
_________________________________________________________________
Unsubscribe & list info -- http://www.scruz.net/~luke/signup.htm
Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
