Cuda Cores

storm5510 · 2016-10-20, 16:16

My current video adapter is an nVidia GT-610. It has 48 Cuda cores. I just ordered a GTX-750 Ti. It has 640 Cuda cores. I will go out on a limb and say that this will make some difference in calculation speed. I've been running mfaktc. With the one I have now, a 72 to 73 factorization takes about 5.5 hours Comments anyone.

tServo · 2016-10-20, 16:49

Quote:

Originally Posted by storm5510

My current video adapter is an nVidia GT-610. It has 48 Cuda cores. I just ordered a GTX-750 Ti. It has 640 Cuda cores. I will go out on a limb and say that this will make some difference in calculation speed. I've been running mfaktc. With the one I have now, a 72 to 73 factorization takes about 5.5 hours Comments anyone.

Probably, as long as mfaktc doesn't use FP64 math extensively.
The 750Ti is a Maxwell, and Nvidia cut back drastically on FP64 capabilities
of those boards.

kladner · 2016-10-20, 17:51

Quote:

Originally Posted by tServo

Probably, as long as mfaktc doesn't use FP64 math extensively.
The 750Ti is a Maxwell, and Nvidia cut back drastically on FP64 capabilities
of those boards.

As far as I understand, mfaktc makes little or no use of FP64. There is a different story with CUDALucas.

Prime95 · 2016-10-20, 21:03

Quote:

Originally Posted by kladner

As far as I understand, mfaktc makes little or no use of FP64. There is a different story with CUDALucas.

mfaktc uses a lot of 32x32 multiplies. IIRC, some (all?) nVidia use the FP64 unit to do these multiplies.

axn · 2016-10-21, 02:45

From http://www.mersenne.ca/mfaktc.php

GT-610 produces 29 GHz day/day consuming 29 W for an efficiency score of 1 GHzd/d/w

750 Ti - 139.7 GHd/d, 60W, 2.3GHzd/d/w

So, about 5x performance, and 2x power consumption

EDIT:- FWIW, the low end GPU sweetspot for mfaktc/o is probably Radeon RX 460

storm5510 · 2016-10-21, 03:47

My desktop is not new by any means so there is probably a limit as to what I can put in it. Replacing it has not been an option, as of yet. Perhaps soon. Thank you all for your replies.

kladner · 2016-10-21, 04:02

Quote:

Originally Posted by Prime95

mfaktc uses a lot of 32x32 multiplies. IIRC, some (all?) nVidia use the FP64 unit to do these multiplies.

Thanks for the correction, George. I guess my comment was just an inference from TF work being less affected by the reduced FP capabilities of nVidia consumer cards above the 500 series.

storm5510 · 2016-10-21, 16:58

Quote:

There is a different story with CUDALucas.

Speaking of CUDALucas, This is something I would like to try at some point. I've only seen references to a Mac build. Nothing for Windows yet.

tServo · 2016-10-21, 17:15

Quote:

Originally Posted by Prime95

mfaktc uses a lot of 32x32 multiplies. IIRC, some (all?) nVidia use the FP64 unit to do these multiplies.

You mean 32 bit INTs, correct?

ATH · 2016-10-21, 18:05

Quote:

Originally Posted by storm5510

Speaking of CUDALucas, This is something I would like to try at some point. I've only seen references to a Mac build. Nothing for Windows yet.

Here are the binaries for many different versions of CUDA:
http://mersenneforum.org/mfaktc/mfak...win.cuda80.zip

and here are the extra Wagstaff factoring binary and the Less Classes versions:
http://mersenneforum.org/mfaktc/mfak...a-versions.zip

You need to download the CUDA library files for the version you selected in the "CUDA Libs" directory here:
https://sourceforge.net/projects/cudalucas/files/

Prime95 · 2016-10-21, 19:26

Quote:

Originally Posted by tServo

You mean 32 bit INTs, correct?

Yes, 32-bit integer multiplies yielding either the high or low 32 bits of the result.

2016-10-20, 16:16	#1
storm5510 Random Account Aug 2009 2·1,051 Posts	Cuda Cores My current video adapter is an nVidia GT-610. It has 48 Cuda cores. I just ordered a GTX-750 Ti. It has 640 Cuda cores. I will go out on a limb and say that this will make some difference in calculation speed. I've been running mfaktc. With the one I have now, a 72 to 73 factorization takes about 5.5 hours Comments anyone.

2016-10-21, 02:45	#5
axn Jun 2003 1010011101111₂ Posts	From http://www.mersenne.ca/mfaktc.php GT-610 produces 29 GHz day/day consuming 29 W for an efficiency score of 1 GHzd/d/w 750 Ti - 139.7 GHd/d, 60W, 2.3GHzd/d/w So, about 5x performance, and 2x power consumption EDIT:- FWIW, the low end GPU sweetspot for mfaktc/o is probably Radeon RX 460 Last fiddled with by axn on 2016-10-21 at 02:47

Similar Threads
Thread	Thread Starter	Forum	Replies	Last Post
4 Cores, only 1 worker?	sonjohan	Software	13	2016-08-26 05:34
32 cores limitation	gabrieltt	Software	12	2010-07-15 10:26
CPU cores	Unregistered	Information & Answers	7	2009-11-02 08:27
6 Intel Cores	petrw1	Hardware	3	2008-09-16 16:33
A program that uses all the CPU-cores	Primix	Hardware	7	2008-09-06 21:09

2016-10-21, 03:47	#6
storm5510 Random Account Aug 2009 836₁₆ Posts	My desktop is not new by any means so there is probably a limit as to what I can put in it. Replacing it has not been an option, as of yet. Perhaps soon. Thank you all for your replies.