mersenneforum.org  

Go Back   mersenneforum.org > Great Internet Mersenne Prime Search > PrimeNet

Reply
 
Thread Tools
Old 2008-05-19, 04:45   #1
ixfd64
Bemusing Prompter
 
ixfd64's Avatar
 
"Danny"
Dec 2002
California

93C16 Posts
Default how is the throughput calculated?

Does anyone know how the GIMPS throughput is calculated?

I'm asking this because the numbers don't seem to add up. It appears that the actual throughput is much higher than the figure listed on the PrimeNet page.

Here is an example:

It is reported that a 3.2 GHz Pentium 4 processor (with 512 kb L2 cache) can peak at 12 GFLOPs, but most benchmarks put it at around 6 GFLOPs, so I'll go with the latter figure. According to the benchmarks page, each iteration takes 0.0764 seconds for exponents that are between 39.5M and 49.1M (most exponents that are being tested right now are in this range). Therefore, a 40M exponent should take about 35 days on a Pentium 4, assuming that the test is run continuously. Since the PrimeNet server is synchronized every half month, we can mathematically expect a 3.2 GHz processor to clear 0.4 exponents during this half-month period. GIMPS' current throughput of 30 TFLOPs would be equivalent to 6,000 of those processors. This would mean that about 2,400 exponents are cleared (by Lucas-Lehmer testing) every half month. However, the actual number of exponents that are cleared by Lucas-Lehmer testing are much higher, often exceeding 10,000. This leads me to think that GIMPs' actual throughput is much higher than 30 TFLOPS. While there is no perfect correlation between the iteration time and the processor speed (there are many other factors that determine a processor's performance), something just seems wrong here.

I've noticed another thing. The PrimeNet page only lists processors up to the Pentium 4. The newer chips, such as the Xeon and Core 2 processors, are not included. Is it possible that GIMPS is not recognizing some of the newer processors, or even mistaking them for older ones? PrimeNet lists 98 "unspecified" processors, but I'm pretty sure that there are way more than 98 people that are using newer processors than the Pentium 4.

Last fiddled with by ixfd64 on 2008-05-19 at 04:46
ixfd64 is offline   Reply With Quote
Old 2008-05-19, 06:29   #2
davieddy
 
davieddy's Avatar
 
"Lucan"
Dec 2006
England

2×3×13×83 Posts
Default

According to my observations, Primenet suggests that
30 Tflops clears about ten tests per hour, which amounts
to 3600 tests in 15 days.
BTW the synchronization is performed monthly (on the 15th of
the month), not every half month.
This goes a long way towards accounting for your "discrepancy".

David
davieddy is offline   Reply With Quote
Old 2008-05-19, 07:24   #3
davieddy
 
davieddy's Avatar
 
"Lucan"
Dec 2006
England

2·3·13·83 Posts
Default

Quote:
Originally Posted by ixfd64 View Post
It is reported that a 3.2 GHz Pentium 4 processor (with 512 kb L2 cache) can peak at 12 GFLOPs, but most benchmarks put it at around 6 GFLOPs, so I'll go with the latter figure.
If the actual performance when doing an LLtest was 4 GFLOPs,
this would account for the remainder of your "discrepancy".
davieddy is offline   Reply With Quote
Old 2008-05-20, 22:11   #4
Uncwilly
6809 > 6502
 
Uncwilly's Avatar
 
"""""""""""""""""""
Aug 2003
101×103 Posts

248116 Posts
Default

Does not the throughput also measure double checks, TF, and P-1?
Uncwilly is online now   Reply With Quote
Old 2008-05-21, 12:43   #5
ATH
Einyen
 
ATH's Avatar
 
Dec 2003
Denmark

7·433 Posts
Default

If you use the formulas from these threads with the new FFT sizes cutoffs:

http://www.mersenneforum.org/showthread.php?t=10235

http://www.mersenneforum.org/showthread.php?t=3337

and remember from status page we can calculate 1 P90yr = 1,040,057 GFLOP (not GFLOP/s).

29.69M to 34.56M (1792K): p90yr=exp*1.113*5.5/31536000
so 1 LL-iteration = exp*1.113*5.5*1040057 / ( 31536000 * exp) = 0.201887 GFLOP (not GFLOP/s)

34.56M to 39.50M (2048K): p90=exp*1.226*5.5/31536000
1 LL-iteration = exp*1.226*5.5/ ( 31536000 * exp) = 0.222384 GFLOP

39.50M to 49.10M (2560K): p90=exp*1.640*5.5/31536000
1 LL-iteration = exp*1.640*5.5/ ( 31536000 * exp) = 0.297480 GFLOP

49.10M to 58.52M (3072K): p90=exp*1.990*5.5/31536000
1 LL-iteration = exp*1.990*5.5/ ( 31536000 * exp) = 0.360966 GFLOP

So if you test your average iteration time on exponents in each range you can see how many GFLOP/s that is, and I got fairly same number from the different FFT ranges.

From 2048K range for example my average iteration on my P4 Prescott 3.4 Ghz was 57.7ms so I got 0.222384 GFLOP / 0.0577s = 3.85 GFLOP/s. From 3 different FFT range I got 3.70-3.95 GFLOP/s so nowhere near 6 GFLOPs. On my Athlon XP 2200+ 1.8Ghz I got 1.23-1.25 GFLOP/s.
ATH is offline   Reply With Quote
Old 2008-05-21, 13:39   #6
Prime95
P90 years forever!
 
Prime95's Avatar
 
Aug 2002
Yeehaw, FL

162668 Posts
Default

Quote:
Originally Posted by ixfd64 View Post
It is reported that a 3.2 GHz Pentium 4 processor (with 512 kb L2 cache) can peak at 12 GFLOPs.
The theoretical maximum throughput for a single core of Pentium 4 is one add and one multiply per clock cycle. So a 3.2GHz CPU has a 6.4 GFLOPs theoretical max.
Prime95 is offline   Reply With Quote
Reply

Thread Tools


Similar Threads
Thread Thread Starter Forum Replies Last Post
Let y^2=xz-x^2+1, and if value of x is known, can y and z be directly calculated? Given all variable MARTHA Number Theory Discussion Group 11 2018-03-02 15:55
How are GHz-Days calculated? Unregistered Information & Answers 10 2013-05-17 14:26
Budget PC Throughput Rodrigo Hardware 14 2011-09-26 10:16
My throughput does not compute... petrw1 Hardware 9 2007-08-13 14:38
Curious how sieve points are calculated VJS Prime Sierpinski Project 9 2006-09-10 19:02

All times are UTC. The time now is 22:52.

Thu Feb 25 22:52:32 UTC 2021 up 84 days, 19:03, 0 users, load averages: 1.59, 1.58, 1.58

Powered by vBulletin® Version 3.8.11
Copyright ©2000 - 2021, Jelsoft Enterprises Ltd.

This forum has received and complied with 0 (zero) government requests for information.

Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation.
A copy of the license is included in the FAQ.