mersenneforum.org  

Go Back   mersenneforum.org > Great Internet Mersenne Prime Search > Hardware > GPU Computing

Reply
 
Thread Tools
Old 2013-10-04, 22:54   #1
nucleon
 
nucleon's Avatar
 
Mar 2003
Melbourne

5×103 Posts
Default Latest Nvidia drivers 331.40 & Titans

Anyone trying out the latest 331.40 driver on a Titan?

I'm seeing some major slowdowns.

I'm predominately doing P-1, and I've gone down from 80GHz-days/day (ish) to about 50 (ish).

-- Craig
nucleon is offline   Reply With Quote
Old 2013-10-04, 23:11   #2
nucleon
 
nucleon's Avatar
 
Mar 2003
Melbourne

5·103 Posts
Default

I'll neither confirm nor deny the double-precision config item checked in the driver was cleared.

It must have cleared on installing latest driver.

Tip for a new Titan player - when doing LL/P-1 on your Titan, make sure the Double-Precision config item is checked. :)

-- Craig
nucleon is offline   Reply With Quote
Old 2013-10-05, 02:03   #3
kladner
 
kladner's Avatar
 
"Kieren"
Jul 2011
In My Own Galaxy!

2×3×1,693 Posts
Default

So performance turned out about the same, then? Is that a WHCL or a beta driver?
kladner is offline   Reply With Quote
Old 2013-10-05, 04:33   #4
nucleon
 
nucleon's Avatar
 
Mar 2003
Melbourne

5·103 Posts
Default

I wish I had more accurate stats. But there's no noticeable performance difference.

-- Craig
nucleon is offline   Reply With Quote
Old 2013-10-05, 15:51   #5
kladner
 
kladner's Avatar
 
"Kieren"
Jul 2011
In My Own Galaxy!

2×3×1,693 Posts
Default

Quote:
Originally Posted by nucleon View Post
I wish I had more accurate stats. But there's no noticeable performance difference.

-- Craig
A general impression is usually as far as I go, anyway. Thanks!
kladner is offline   Reply With Quote
Old 2013-10-19, 07:15   #6
Manpowre
 
"Svein Johansen"
May 2013
Norway

20110 Posts
Default

I installed latest beta driver 331.40, as I had 320.59 which I believe came with Cuda 5.5. In the 320.59 driver I had to drop memory hz to 2500 (-500), as one of the first issues with titan was memory heating up on the back side of the card where there is no fan. I was waiting for that to get fixed, and it seems like new drivers has fixed some of this. Did Nvidia only activate memory inside the card unless more memory is needed ? Mabye something changed with gtx 780 release.

To get these results, I am now at 3004 mhz on mem clock. 940mhz on gpu clock. EVGA precision power set to 106%. This has now run stable overnight.

- Driver version: 331.40
- Mem clock: 3004 mhz
- GPU clock: 914-940 mhz
- Compute 35 cuda 64bit cudalucas on windows 64bit
- EVGA power set to 106%
- test exponent: 38000009

Titan with DP switch on:
Code:
Iteration 10000 M( 38000009 )C, 0xfd9116e3760e4571, n = 2097152, CUDALucas v2.03  err = 0.2090 (0:16 real, 1.5878 ms/iter, ETA 16:45:21)
Iteration 20000 M( 38000009 )C, 0xd91fe21f272e5099, n = 2097152, CUDALucas v2.03  err = 0.2090 (0:15 real, 1.5032 ms/iter, ETA 15:51:29)
Iteration 30000 M( 38000009 )C, 0x7ec1302ed5173c26, n = 2097152, CUDALucas v2.03  err = 0.2090 (0:15 real, 1.5025 ms/iter, ETA 15:50:51)
Titan with DP switch off:
Code:
Iteration 10000 M( 38000009 )C, 0xfd9116e3760e4571, n = 2097152, CUDALucas v2.03  err = 0.2090 (0:22 real, 2.2743 ms/iter, ETA 24:00:02)
Iteration 20000 M( 38000009 )C, 0xd91fe21f272e5099, n = 2097152, CUDALucas v2.03  err = 0.2090 (0:22 real, 2.1882 ms/iter, ETA 23:05:08)
Iteration 30000 M( 38000009 )C, 0x7ec1302ed5173c26, n = 2097152, CUDALucas v2.03  err = 0.2090 (0:22 real, 2.1871 ms/iter, ETA 23:04:04)
I ran with these settings overnight, and they seem to run stable. (I did not have these settings run stable on driver 320.59)

Last fiddled with by Manpowre on 2013-10-19 at 07:17
Manpowre is offline   Reply With Quote
Old 2013-10-19, 13:46   #7
MikeBerlin
 
Mar 2012
Germany

328 Posts
Default

Quote:
Originally Posted by Manpowre View Post
Titan with DP switch on:
Code:
Iteration 10000 M( 38000009 )C, 0xfd9116e3760e4571, n = 2097152, CUDALucas v2.03  err = 0.2090 (0:16 real, 1.5878 ms/iter, ETA 16:45:21) ....
Titan with DP switch off:
Code:
Iteration 10000 M( 38000009 )C, 0xfd9116e3760e4571, n = 2097152, CUDALucas v2.03  err = 0.2090 (0:22 real, 2.2743 ms/iter, ETA 24:00:02) ....
Thx for lists, i´m looking a long time for this comparison. But only 33% shorter ETA? DP is nearly 10times faster than the other GFORCES.

Last fiddled with by MikeBerlin on 2013-10-19 at 13:48
MikeBerlin is offline   Reply With Quote
Old 2013-10-19, 13:50   #8
Manpowre
 
"Svein Johansen"
May 2013
Norway

3·67 Posts
Default

Quote:
Originally Posted by MikeBerlin View Post
Thx for lists, i´m looking a long time for this comparison. But only 33% shorter ETA? DP is nearly 10times faster than the other GFORCES.
Dunno. I think I saw similar timings earlier with dp switch off.
I dont think it is 10 times though. We are talking 7.5b transistors even with dp switch off.
Manpowre is offline   Reply With Quote
Old 2013-10-19, 17:56   #9
Manpowre
 
"Svein Johansen"
May 2013
Norway

3·67 Posts
Default

Quote:
Originally Posted by MikeBerlin View Post
Thx for lists, i´m looking a long time for this comparison. But only 33% shorter ETA? DP is nearly 10times faster than the other GFORCES.
well if you take original post: 50*100/80 = percentage of with DP = 80ghz days.. then its 62ish.. since original poster reinstalled driver, and DP setting was off, he got 50ish instead of 80ish,, which seems like ishish same result as I get something like 33 percent difference..

I guess there is complexity in FFT that makes this 33% instead of 1/3 stepper with DP compared to 1/24 for 680/690/780/790 series of geforce.

then again, the difference is on Titan only with and without DP setting. For 6xx platform and 7xx platform there is really no dp on/off setting, and these platforms also got less transistor counts inside GPU, so there is huge difference with cudalucas compared to Titan with its 7.5 bill transistors and 2600 ish computecores.

Last fiddled with by Manpowre on 2013-10-19 at 17:58
Manpowre is offline   Reply With Quote
Old 2013-10-21, 18:05   #10
Karl M Johnson
 
Karl M Johnson's Avatar
 
Mar 2010

3·137 Posts
Default

A WHQL 331.58 Forceware is out, anything regarding it?
Karl M Johnson is offline   Reply With Quote
Old 2013-10-21, 21:18   #11
Manpowre
 
"Svein Johansen"
May 2013
Norway

3·67 Posts
Default

Quote:
Originally Posted by Karl M Johnson View Post
A WHQL 331.58 Forceware is out, anything regarding it?
I tested 331.58. I did 2 tests on a Titan:
* FFT length tests 3.5m-4.5m 1024 step, DP on. marginal differences. Some fft lengths marginal quicker, some fft lengths marginal worser...
* Exponent test. exactly same time, and timings as with the 331.40 beta driver.

so I dont see the big differences.. I just hope it is stable...
Manpowre is offline   Reply With Quote
Reply

Thread Tools


Similar Threads
Thread Thread Starter Forum Replies Last Post
Nvidia unlocking Titan X (P) through drivers Karl M Johnson GPU Computing 3 2017-08-11 08:40
Getting the blasted nV drivers working again fivemack GPU Computing 4 2017-03-08 13:54
Nvidia 364.xx drivers returning incorrect results UBR47K GPU Computing 2 2016-06-11 22:38
Extensions to drivers/guides henryzz Aliquot Sequences 1 2013-09-16 21:29
Need help with drivers (Vista 64) schickel Lounge 3 2009-11-19 05:09

All times are UTC. The time now is 12:45.


Mon Dec 6 12:45:24 UTC 2021 up 136 days, 7:14, 0 users, load averages: 1.67, 1.65, 1.63

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

This forum has received and complied with 0 (zero) government requests for information.

Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation.
A copy of the license is included in the FAQ.