mersenneforum.org  

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

Reply
 
Thread Tools
Old 2003-06-24, 01:15   #1
chrow
 
Jun 2003

17 Posts
Default Primality test - 0,03% in 105 minutes. It is too much....

When I initiate PRIME95 appears. "Resuming primality test of 33518297".
In the course of time he goes giving the status "Per iteration team: 0.629 sec."
Every 105 minutes he prosecutes 0,03%, in other words, 0,01% every 35 minutes
I did the accounts and saw that were continuing in this ritimo he should carry 243 days. However in the site "http://www.mersenne.org/bench.htm" tells that he should carry 116 days.
I have been accompanying the program, he is running to himself (24 hours a day) in the machine, with MBM5 and with the tasks manager of W2K. In the tasks manager realize that PRIME95 always is using 99% of the CPU.

Can anybody tell because this do it carry so much time? what Can I do to accelerate that???

I apologize by my bad English.

Moises Deangelo
lewris@ig.com.br
ICQ:89529510
chrow is offline   Reply With Quote
Old 2003-06-24, 03:59   #2
cheesehead
 
cheesehead's Avatar
 
"Richard B. Woods"
Aug 2002
Wisconsin USA

22·3·641 Posts
Default Re: Primality test - 0,03% in 105 minutes. It is too much...

Quote:
Originally Posted by chrow
When I initiate PRIME95 appears. "Resuming primality test of 33518297".
In the course of time he goes giving the status "Per iteration team: 0.629 sec."
Every 105 minutes he prosecutes 0,03%, in other words, 0,01% every 35 minutes
I did the accounts and saw that were continuing in this ritimo he should carry 243 days.
33518296 iterations * 0.629 second/iteration = 21,083,000 seconds = about 244 days, which agrees well with 35 minutes * 100 * 100 = 350,000 minutes = 21,000,000 seconds = about 243 days, so that seems like a reasonable time estimate.

Quote:
However in the site "http://www.mersenne.org/bench.htm" tells that he should carry 116 days.
You have a AMD Duron 1.0GHz, right?

The benchmark page allows selecting CPU Type Athlon, but it doesn't offer a choice of Duron. I guess either:
1) Durons are slower than Athlons, and what would take 116 days for a 1.0GHz Athlon takes 243 days for a 1.0GHz Duron, or
2) the benchmark page calculator's estimate for a 1.0GHz Athlon is too fast.
cheesehead is offline   Reply With Quote
Old 2003-06-24, 06:44   #3
Dresdenboy
 
Dresdenboy's Avatar
 
Apr 2003
Berlin, Germany

5518 Posts
Default

The difference between Duron and Athlon is that L2 cache is only 64k (exclusive - so you can add it to the L1 size). And Durons with older core (Morgan) have a 100MHz FSB, the newer ones have 133MHz and even SSE (like Athlon XP).

Prime95 depends heavily on cache size and mem bandwidth. If it's SDR then it would have a serious impact I assume.

Matthias
Dresdenboy is offline   Reply With Quote
Old 2003-06-26, 06:01   #4
chrow
 
Jun 2003

17 Posts
Default

I understand that in the calculations of the site does not consist DURON, but in the table soon below, FFT 1792K, DURON 950MHZ, RAM 133 (speed), consists 0,426, because is my it so high? 0,628.
In OPTIONS/CPU, the prime95 tells, CPU INFORMATION.
I do not know FSB of the processor, but MATHER BOARD accepted of 100 to 200 MHz.

AMD DURON PROCESSOR
CPU SPEED: 996,18 MHz
CPU FEATURES: RDTSC, CMOV, PREFETCH, MMX, SSE
L1 CACHE SIZE: 64KB
L2 CACHE SIZE: 64KB

Does anybody know to tell if is this delay same correct???

:( :( :(

Moises Deangelo
chrow is offline   Reply With Quote
Old 2003-06-26, 09:59   #5
hyh1048576
 
Jun 2003

26 Posts
Default

Maybe you should change your resolution when you do not use your computer(for example,640*480 256colours),it can be 37% faster on my computer when the resolution changes from the highest to the lowest.
See also:http://www.mersenneforum.org/viewtopic.php?t=739
hyh1048576 is offline   Reply With Quote
Reply

Thread Tools


Similar Threads
Thread Thread Starter Forum Replies Last Post
Modifying the Lucas Lehmer Primality Test into a fast test of nothing Trilo Miscellaneous Math 25 2018-03-11 23:20
there is another way to test the primality of a no shawn Miscellaneous Math 5 2007-07-17 17:55
N-1 primality test Citrix Math 3 2005-09-19 15:06
AKS Primality Test Guilherme Math 2 2004-11-26 05:29
A primality test for Fermat numbers faster than Pépin's test ? T.Rex Math 0 2004-10-26 21:37

All times are UTC. The time now is 16:15.


Sun Aug 1 16:15:41 UTC 2021 up 9 days, 10:44, 0 users, load averages: 1.73, 1.88, 1.73

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.