mersenneforum.org  

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

Reply
 
Thread Tools
Old 2011-07-03, 00:19   #1
LiquidNitrogen
 
LiquidNitrogen's Avatar
 
Jun 2011
Henlopen Acres, Delaware

7·19 Posts
Default What are your per-iteration times?

I am just curious about what some of your per-iteration times might be.

M 46,878,773 = 0.024 for me.
LiquidNitrogen is offline   Reply With Quote
Old 2011-07-03, 00:41   #2
science_man_88
 
science_man_88's Avatar
 
"Forget I exist"
Jul 2009
Dumbassville

26×131 Posts
Default

Quote:
Originally Posted by LiquidNitrogen View Post
I am just curious about what some of your per-iteration times might be.

M 46,878,773 = 0.024 for me.
I'm doing 2 double checks of ll I think and my minimum I can see so far is .078 I'm not sure if they are double checks or not.

Last fiddled with by science_man_88 on 2011-07-03 at 00:42
science_man_88 is offline   Reply With Quote
Old 2011-07-03, 02:33   #3
Christenson
 
Christenson's Avatar
 
Dec 2010
Monticello

5×359 Posts
Default

30-40msec on M24,262,141....Liquid Nitrogen has a relatively "hot" machine.....
Christenson is offline   Reply With Quote
Old 2011-07-03, 06:07   #4
imwithid
 
imwithid's Avatar
 
Apr 2009
Venice, Chased by Jaws

3·29 Posts
Default

My machines are a bit old, but out of curiosity for what others are able to output, I'll post what I can. I hope this is not simply a low brow "mine is bigger than yours" thread. In today's age of computers, your unit will be blown away eventually by what I replace it with when the time comes.

I had four machines (now three, since two weeks ago - one TF and now P-1 for GIMPS, the rest SoB).

Three are Intel Core 2 class. Depending on the system's resource allocation and relative "cleanliness", I get:

Core2 6300 @ 1.86: LL ~0.059 19913348, 19913348 (moved now to GIMPS P-1 & LL - 47907107 - timings, soon to come)
Core2 4300 @ 1.80: LL ~0.080 19880194.

Not currently running (too hot, even with a laptop fan cooler - used as a heater during winter -- thanks HP!):

AMD Mobile K10 X2 RM-72: LL ~.110 19913348.
imwithid is offline   Reply With Quote
Old 2011-07-03, 08:21   #5
lycorn
 
lycorn's Avatar
 
Sep 2002
Oeiras, Portugal

23·181 Posts
Default

M28865407 (1536K FFT) -> 0.010 - 0.011 msec/iter (using two cores of a slightly OCed i5-750 - timing fluctuations are due to variations in the type of work done by the other two cores: e.g., if I use both of them to P-1 testing, I get 0.011 msec/iter; if I switch one of them to TF I normally get 0.010.
lycorn is offline   Reply With Quote
Old 2011-07-03, 15:08   #6
LiquidNitrogen
 
LiquidNitrogen's Avatar
 
Jun 2011
Henlopen Acres, Delaware

2058 Posts
Default

Quote:
Originally Posted by Christenson View Post
30-40msec on M24,262,141....Liquid Nitrogen has a relatively "hot" machine.....
Well it runs mostly at about 58 C, so maybe not too hot.

:)

It's an overclocked i7-870 @ 3.9 GHz. This is my "spare system," it has single core speed that is slightly faster than a stock Gulftown (i7-980X @ 3.33 GHZ)
LiquidNitrogen is offline   Reply With Quote
Old 2011-07-03, 15:13   #7
LiquidNitrogen
 
LiquidNitrogen's Avatar
 
Jun 2011
Henlopen Acres, Delaware

100001012 Posts
Default

Quote:
Originally Posted by imwithid View Post
I hope this is not simply a low brow "mine is bigger than yours" thread.
No, I was just curious. I noticed for smaller numbers the time is much faster, so I am just trying to get a sense of how fast/slow other people are iterating for numbers of various sizes.

Quote:
Originally Posted by imwithid View Post
In today's age of computers, your unit will be blown away eventually by what I replace it with when the time comes.
Ummm.... I don't think so. I own a 5.27 GHz i7-980X that is cooled to -40 using a Single Stage Vapor Phase Change unit. Message me here privately and I will send a link to its YouTube video.

It will be faster than whatever you can buy until the year 2018 or maybe longer.

:)
LiquidNitrogen is offline   Reply With Quote
Old 2011-07-03, 16:36   #8
ATH
Einyen
 
ATH's Avatar
 
Dec 2003
Denmark

57278 Posts
Default

Use "PercentPrecision=6" in prime.txt then you get maximum precision and decimals on the milliseconds.
ATH is offline   Reply With Quote
Old 2011-07-09, 19:36   #9
LiquidNitrogen
 
LiquidNitrogen's Avatar
 
Jun 2011
Henlopen Acres, Delaware

7×19 Posts
Default

Quote:
Originally Posted by ATH View Post
Use "PercentPrecision=6" in prime.txt then you get maximum precision and decimals on the milliseconds.
I did do this, and the percent precision is now 6 decimal places, but not the per iteration time.
LiquidNitrogen is offline   Reply With Quote
Old 2011-07-09, 20:58   #10
Batalov
 
Batalov's Avatar
 
"Serge"
Mar 2008
Phi(4,2^7658614+1)/2

2×4,663 Posts
Default

TimingOutput=4 in prime.txt
Batalov is offline   Reply With Quote
Old 2011-07-10, 12:45   #11
ATH
Einyen
 
ATH's Avatar
 
Dec 2003
Denmark

BD716 Posts
Default

Yeah sorry I forgot that there are 2 settings for precision, one for progress and one for timings. I have had those on since I started GIMPS. I should have checked undoc.txt before posting:

Code:
You can adjust how many decimal digits of precision are displayed
in lines output to the screen.  In prime.txt enter a value between 0 and 6:
	PercentPrecision=n

You can alter the way the program outputs timings.  In prime.txt set:
	TimingOutput=n
Where n=1 for seconds with 3 digits of precision, n=2 for milliseconds
with 1 digit of precision, n=3 for milliseconds with 2 digits of precision,
n=4 for milliseconds with 3 digit of precision.

Last fiddled with by ATH on 2011-07-10 at 12:52
ATH is offline   Reply With Quote
Reply

Thread Tools


Similar Threads
Thread Thread Starter Forum Replies Last Post
Iteration times in i5 and i7 Jud McCranie Information & Answers 53 2013-08-17 19:09
CPU frequency and iteration times. rx7350 Hardware 12 2006-05-08 21:54
LLR.exe FFT crossovers and iteration times SlashDude 15k Search 0 2004-01-28 05:47
slow iteration times PLeopard Hardware 9 2003-10-29 05:48
Slow iteration times with 23.7 smoffat Software 13 2003-10-22 22:50

All times are UTC. The time now is 19:22.

Fri Feb 26 19:22:20 UTC 2021 up 85 days, 15:33, 0 users, load averages: 2.11, 1.87, 2.08

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.