mfaktc: a CUDA program for Mersenne prefactoring - Page 174

TheJudger · 2012-09-11, 16:15

Hi,

Quote:

Originally Posted by frmky

My poor S1070.

no, the situation is not that bad. The current development (0.20) does not run very well (slow performance) on CC 1.x GPUs iff sieving is done on GPU.
There will be new kernels in mfaktc 0.20 and depending on the factor size (above 2⁷⁶) you'll notice a performance improvement even on CC 1.x GPUs.
So the questions/suggestions are more about how much effort should be spent on CC 1.x GPUs? Currently I don't plan to drop support on CC 1.x GPUs but I don't spent much time on optimizations for CC 1.x, got the idea?
I was thinking about disabling GPU sieving on CC 1.x GPUs (just because it runs slow), this will save some time during testing.

Oliver
P.S. thank you George and rcv for GPU sieving, thank you George for the new kernels

ET_ · 2012-09-12, 07:56

Quote:

Originally Posted by TheJudger

P.S. thank you George and rcv for GPU sieving, thank you George for the new kernels

Thank you Oliver for not dropping cc 1.3

Luigi

aketilander · 2012-09-14, 17:27

I have a question, which maybe not is a big issue, but anyway:
A HDD was smoked on one of my systems, but happily I was able to rescue the intermediary results from mfaktc 0.19 from the old hard drive. I was happy because I am doing some work for Operation Billion Digits high up between ^85 and ^86.
Now I have installed a new disk and Windows fresh from the beginning on that disk.
When I tried to resume from last checkpoint-file mfaktc 0.19 refuses me to resume and insists that I should begin trial factoring from the beginning. This would mean that I would loose a couple of weeks of work, so I wonder if there is a way to resume?

Sorry, I just looked at the content of the checkpoint files and there are only blank spaces, no real content. So the old Hard disk was in a worse state then I thought! Nothing to do then, sorry for taking your time.

c10ck3r · 2012-10-06, 19:58

My Pentium D 940 CPU can't feed my GTX 460 fully. I can get 24 Ghz-Days/day running 24/7 instead of however many it should get (~120).

TheJudger · 2012-10-06, 21:50

c10ck3r: I guess the poor performance is related to the relative small L1 cache size. You'll like mfaktc 0.20 once it is finished.

Oliver

Btw: CPU Launch date Q1'06 vs. Q3'10 GTX 460, this is four and a half year difference...

c10ck3r · 2012-10-07, 02:13

It is technically my mothers desktop, with my GPU and PSU... This summer I hope to add a desktop of my own...

bcp19 · 2012-10-10, 01:56

I had a similar problem with a Core2Quad and a 480, could not max out the GPU even with all 4 cores running mfaktc. A single core of my 2500 outproduced the entire quad on the 480.

ixfd64 · 2012-11-04, 00:40

Could we please have Prime95-style timestamps accompany the results? That would be quite useful!

Edit: Never mind, I found out that I can configure it in mfaktc.ini.

flashjh · 2012-11-04, 01:17

I would also like to see the option to do sieve on the GPU only like mmff. How hard is that?

James Heinrich · 2012-11-04, 02:26

Quote:

Originally Posted by flashjh

I would also like to see the option to do sieve on the GPU only like mmff. How hard is that?

Oliver's post from 2 months ago seems to indicate it's planned for inclusion in mfaktc v0.20, and presumably working (at least in alpha form) at that time.

flashjh · 2012-11-04, 02:31

Quote:

Originally Posted by James Heinrich

Oliver's post from 2 months ago seems to indicate it's planned for inclusion in mfaktc v0.20, and presumably working (at least in alpha form) at that time.

That's right, I forgot. I know it won't be as fast, but it will be nice to use the CPU for something else.

2012-09-14, 17:27	#1906
aketilander "Åke Tilander" Apr 2011 Sandviken, Sweden 2·283 Posts	Resume from chekpoint file with mfaktc 0.19 I have a question, which maybe not is a big issue, but anyway: A HDD was smoked on one of my systems, but happily I was able to rescue the intermediary results from mfaktc 0.19 from the old hard drive. I was happy because I am doing some work for Operation Billion Digits high up between ^85 and ^86. Now I have installed a new disk and Windows fresh from the beginning on that disk. When I tried to resume from last checkpoint-file mfaktc 0.19 refuses me to resume and insists that I should begin trial factoring from the beginning. This would mean that I would loose a couple of weeks of work, so I wonder if there is a way to resume? Sorry, I just looked at the content of the checkpoint files and there are only blank spaces, no real content. So the old Hard disk was in a worse state then I thought! Nothing to do then, sorry for taking your time. Last fiddled with by aketilander on 2012-09-14 at 18:02

2012-11-04, 00:40	#1911
ixfd64 Bemusing Prompter "Danny" Dec 2002 California 2·11·109 Posts	Could we please have Prime95-style timestamps accompany the results? That would be quite useful! Edit: Never mind, I found out that I can configure it in mfaktc.ini. Last fiddled with by ixfd64 on 2012-11-04 at 01:36

Similar Threads
Thread	Thread Starter	Forum	Replies	Last Post
mfakto: an OpenCL program for Mersenne prefactoring	Bdot	GPU Computing	1676	2021-06-30 21:23
The P-1 factoring CUDA program	firejuggler	GPU Computing	753	2020-12-12 18:07
gr-mfaktc: a CUDA program for generalized repunits prefactoring	MrRepunit	GPU Computing	32	2020-11-11 19:56
mfaktc 0.21 - CUDA runtime wrong	keisentraut	Software	2	2020-08-18 07:03
World's second-dumbest CUDA program	fivemack	Programming	112	2015-02-12 22:51

2012-10-06, 19:58	#1907
c10ck3r Aug 2010 Kansas 223₁₆ Posts	My Pentium D 940 CPU can't feed my GTX 460 fully. I can get 24 Ghz-Days/day running 24/7 instead of however many it should get (~120).

2012-10-06, 21:50	#1908
TheJudger "Oliver" Mar 2005 Germany 457₁₆ Posts	c10ck3r: I guess the poor performance is related to the relative small L1 cache size. You'll like mfaktc 0.20 once it is finished. Oliver Btw: CPU Launch date Q1'06 vs. Q3'10 GTX 460, this is four and a half year difference...

2012-10-07, 02:13	#1909
c10ck3r Aug 2010 Kansas 547 Posts	It is technically my mothers desktop, with my GPU and PSU... This summer I hope to add a desktop of my own...

2012-10-10, 01:56	#1910
bcp19 Oct 2011 1010100111₂ Posts	I had a similar problem with a Core2Quad and a 480, could not max out the GPU even with all 4 cores running mfaktc. A single core of my 2500 outproduced the entire quad on the 480.

2012-11-04, 01:17	#1912
flashjh "Jerry" Nov 2011 Vancouver, WA 1,123 Posts	I would also like to see the option to do sieve on the GPU only like mmff. How hard is that?