What are your per-iteration times?

[LiquidNitrogen]

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

M 46,878,773 = 0.024 for me.

[science_man_88]

Originally Posted by LiquidNitrogen

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.

[Christenson]

30-40msec on M24,262,141....Liquid Nitrogen has a relatively "hot" machine.....

[imwithid]

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.

[lycorn]

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.

[LiquidNitrogen]

Originally Posted by Christenson

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]

Originally Posted by imwithid

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.

Originally Posted by imwithid

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.

:)

[ATH]

Use "PercentPrecision=6" in prime.txt then you get maximum precision and decimals on the milliseconds.

[LiquidNitrogen]

Originally Posted by ATH

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.

[Batalov]

TimingOutput=4 in prime.txt

[ATH]

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:

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.