mersenneforum.org

mersenneforum.org (https://www.mersenneforum.org/index.php)
-   GPU Computing (https://www.mersenneforum.org/forumdisplay.php?f=92)
-   -   mfakto: an OpenCL program for Mersenne prefactoring (https://www.mersenneforum.org/showthread.php?t=15646)

NormanRKN 2013-08-01 21:37

yes with the 13.8 beta i cant do nothing.
at selftest you will see a drivercrash.
( i hate ati/amd drivers all ) grrrrrrrrrr

kracker 2013-08-01 22:28

[QUOTE=NormanRKN;347991]yes with the 13.8 beta i cant do nothing.
at selftest you will see a drivercrash.
( i hate ati/amd drivers all ) grrrrrrrrrr[/QUOTE]
Well, they *are* beta. Might want to roll back as I :smile:

NormanRKN 2013-08-01 22:52

yes, beta is relativ ;)
i switched back to the olders.

Jayder 2013-08-06 01:25

I'm a little confused by this error message:

[CODE]got assignment: exp=4027913 bit_min=63 bit_max=64 (0.46 GHz-days)
WARNING: SievePrimes is too big for the current assignment, lowering to 284998
It is not allowed to sieve primes which are equal or bigger than the
exponent itself![/CODE]

How was the new limit of 284998 calculated? Note the exponent = 4027913. I had attempted to do a SP of 1000000.

axn 2013-08-06 03:04

[QUOTE=Jayder;348381]I'm a little confused by this error message:

[CODE]got assignment: exp=4027913 bit_min=63 bit_max=64 (0.46 GHz-days)
WARNING: SievePrimes is too big for the current assignment, lowering to 284998
It is not allowed to sieve primes which are equal or bigger than the
exponent itself![/CODE]

How was the new limit of 284998 calculated? Note the exponent = 4027913. I had attempted to do a SP of 1000000.[/QUOTE]

#primes < 4027913 = 284999. I guess, it is excluding 2 as well, hence 284998.

Jayder 2013-08-06 03:13

Oh, duh. I was just interpreting the error message in the stupidest way possible.

Thanks for the quick response.

TeknoHog 2013-08-22 14:19

I hacked up something for the automatic assignment handling, as I could not find anything else that worked. It's not perfect, but works for me:

[URL]https://github.com/teknohog/primetools[/URL]

Oh, and thanks for all the great work on mfakto :)

kracker 2013-08-22 14:26

[QUOTE=TeknoHog;350510]I hacked up something for the automatic assignment handling, as I could not find anything else that worked. It's not perfect, but works for me:

[URL]https://github.com/teknohog/primetools[/URL]

Oh, and thanks for all the great work on mfakto :)[/QUOTE]
Interesting. So is this a python script for submitting results?

P.S.: You might want to check out misfit.

TeknoHog 2013-08-22 14:40

[QUOTE=kracker;350511]So is this a python script for submitting results?

P.S.: You might want to check out misfit.[/QUOTE]

Wow, I didn't know about misfit, but it wouldn't really help me anyway as I use Linux. Mine is just a command-line Python script.

TeknoHog 2013-08-25 10:22

[QUOTE=kracker;347982]Just a note that, on catalyst 13.8 beta mfakto does not run at all,at selftest the driver crashes and I have to hard reset. :no:[/QUOTE]

Just noticed the same on 13.8_beta2 that came with the latest Gentoo updates. It crashed upon restarting mfakto, when the old drivers were still running :huh:

EDIT: downgraded to 13.6_beta while running 13.8_beta2, and mfakto runs just fine again...

Bdot 2013-08-27 13:35

[QUOTE=TeknoHog;350510]I hacked up something for the automatic assignment handling, as I could not find anything else that worked. It's not perfect, but works for me:

[URL]https://github.com/teknohog/primetools[/URL]

Oh, and thanks for all the great work on mfakto :)[/QUOTE]

Hi,

I just had a quick look over your script, and I'm quite interested in using it as I'm running a number of Linux machines too.

I'd like to refer you to [URL="http://www.mersenneforum.org/showpost.php?p=319728&postcount=53"]this[/URL] post where I briefly explained the file locking that mfakto uses for worktodo and results files. (details in [URL="https://github.com/Bdot42/mfakto/blob/master/src/filelocking.c"]filelocking.c[/URL] :smile:) This should help for directly accessing the files while mfakto is running.

Regarding the latest driver issue, I think I need to report this to AMD ... :rolleyes:.


All times are UTC. The time now is 23:10.

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