mfaktc: a CUDA program for Mersenne prefactoring

[BigBrother]

Originally Posted by firejuggler

so around 35 a day, 150 GHz day/day. one more precision if possible : which cpu?

One core of a i5-2500k @ 4.2 GHz, no other processes running. Only single channel memory though, don't know if that matters much in this case.

[firejuggler]

I was just wondering if your 680 was 'underfed'

[bcp19]

Originally Posted by firejuggler

so around 35 a day, 150 GHz day/day. one more precision if possible : which cpu?

You forgot the 74% load, which would take it to a hair over 200, or a bit less than what a GTX 470 can do.

Edit: With that performance, if I were BB, I think I'd take the card and sell it on EBAY, since the scarcity seems to be driving up prices.

[BigBrother]

Originally Posted by bcp19

You forgot the 74% load, which would take it to a hair over 200, or a bit less than what a GTX 470 can do.

Edit: With that performance, if I were BB, I think I'd take the card and sell it on EBAY, since the scarcity seems to be driving up prices.

I primarily bought it for gaming, so I'm not really disappointed :)

[James Heinrich]

Originally Posted by bcp19

You forgot the 74% load, which would take it to a hair over 200, or a bit less than what a GTX 470 can do.

Edit: With that performance, if I were BB, I think I'd take the card and sell it on EBAY, since the scarcity seems to be driving up prices.

I've updated http://mersenne-aries.sili.net/mfaktc.php for GTX 680 and compute 3.0

GTX 680 performance is horrible for mfaktc and CUDALucas. Updating my previous post, relative performance of various compute versions using 2.1 (e.g. GTX 560) as a baseline:

CUDALucas:
compute 1.3 = 82%
compute 2.0 = 137%
compute 2.1 = 100%
compute 3.0 = 56%

mfaktc:
compute 1.3 = 54%
compute 2.0 = 150%
compute 2.1 = 100%
compute 3.0 = 33%

[James Heinrich]

Originally Posted by BigBrother

I primarily bought it for gaming, so I'm not really disappointed :)

It also presents a good opportunity for those who want to get (more) into mfaktc / CUDALucas: a number of gamers will be trying to sell off their GTX 570(s) and/or GTX 580(s) at quite reasonable prices so they can upgrade to a GTX 680. A used GTX 570 could provide excellent price/performance for GIMPS if you get it at a good price.

[Prime95]

Originally Posted by James Heinrich

GTX 680 performance is horrible for mfaktc and CUDALucas.

This is somewhat surprising to me. I guessed CUDALucas would be bad because it does FP64 in 8 special computation units rather than the more numerous CUDA cores (an effective 1/24 FP64 speed). However, I thought mfaktc would use the more numerous CUDA cores to do the 32-bit muls and adds that predominate in TF. Where did I go wrong?

[bcp19]

Originally Posted by James Heinrich

It also presents a good opportunity for those who want to get (more) into mfaktc / CUDALucas: a number of gamers will be trying to sell off their GTX 570(s) and/or GTX 580(s) at quite reasonable prices so they can upgrade to a GTX 680. A used GTX 570 could provide excellent price/performance for GIMPS if you get it at a good price.

I just picked up a GTX 480 for $125 :D

[Dubslow]

Originally Posted by bcp19

I just picked up a GTX 480 for $125 :D

Newegg has new 580s for <$400

http://www.newegg.com/Product/Produc...82E16814162092
http://www.newegg.com/Product/Produc...82E16814162073

[Batalov]

I'd stay away from Galaxy or Zotac...

[Dubslow]

The reviews seemed good. You've had bad experiences?