mersenneforum.org ECM for CUDA GPUs in latest GMP-ECM ?
 Register FAQ Search Today's Posts Mark Forums Read

 2017-02-25, 16:44 #430 VBCurtis     "Curtis" Feb 2005 Riverside, CA 3×23×61 Posts The GPU's advantage is running many curves in parallel; pm1 does a single curve, so a GPU would be a total waste for pm1.
2017-02-25, 16:47   #431
ET_
Banned

"Luigi"
Aug 2002
Team Italia

3×5×317 Posts

Quote:
 Originally Posted by VBCurtis The GPU's advantage is running many curves in parallel; pm1 does a single curve, so a GPU would be a total waste for pm1.
...unless you use CUDA-Pm1 that parallelizes the FFT calculations...
But that's a totally different subject.

Last fiddled with by ET_ on 2017-02-25 at 16:47

2017-02-25, 16:56   #432
pepi37

Dec 2011
After milion nines:)

3×7×61 Posts

Quote:
 Originally Posted by VBCurtis The GPU's advantage is running many curves in parallel; pm1 does a single curve, so a GPU would be a total waste for pm1.
Many curves in parallel until limit.

2017-02-25, 16:57   #433
pepi37

Dec 2011
After milion nines:)

24018 Posts

Quote:
 Originally Posted by ET_ ...unless you use CUDA-Pm1 that parallelizes the FFT calculations... But that's a totally different subject.

That program is only for base2, I am doing outside that :)

2017-02-25, 18:11   #434
xilman
Bamboozled!

May 2003
Down not across

10,069 Posts

Quote:
 Originally Posted by pepi37 So GPU has limit, when you use ECM, and what is about -pm1? In that case is same limit ?
The limit is on the arithmetic, not the algorithms built on top of it.

2017-02-25, 18:19   #435
pepi37

Dec 2011
After milion nines:)

3·7·61 Posts

Quote:
 Originally Posted by xilman The limit is on the arithmetic, not the algorithms built on top of it.
So for now GPU as option in GMP-EMC is no choice for me :(
Continuing to explore GMP-EMC.....

 2017-09-27, 16:50 #436 bsquared     "Ben" Feb 2007 26×3×17 Posts Maybe I missed it, but I haven't seen any benchmark numbers for GPU-ECM since several years ago in this thread. Could I ask someone to do that for current-generation GPUs? e.g., how long does it take to run N parallel curves for each of the 512-bit and 1018-bit versions (which I understand to be the only reliable ones)?
2017-09-27, 18:33   #437
wombatman
I moo ablest echo power!

May 2013

6C916 Posts

Quote:
 Originally Posted by bsquared Maybe I missed it, but I haven't seen any benchmark numbers for GPU-ECM since several years ago in this thread. Could I ask someone to do that for current-generation GPUs? e.g., how long does it take to run N parallel curves for each of the 512-bit and 1018-bit versions (which I understand to be the only reliable ones)?
Got a particular number (or size of number) in mind?

2017-09-27, 18:59   #438
bsquared

"Ben"
Feb 2007

26×3×17 Posts

Quote:
 Originally Posted by wombatman Got a particular number (or size of number) in mind?
The way I understand things, it doesn't matter; any number will run in the same amount of time (although different for the different versions 512 vs. 1018-bit). Someone let me know if that's not the case.

I'm currently working on the 197 digit cofactor of 149^70+70^149:
Code:
18990123508557902868419834986612849212629329047848408031918356871905091180915018818857084783656883790655928770567349115604303665109625610225945717466120031386943078873289069222693826896799892056101
which you can use for the larger ECM version. Pick anything you like for the smaller one.

2017-09-27, 19:02   #439
wombatman
I moo ablest echo power!

May 2013

32×193 Posts

Quote:
 Originally Posted by bsquared The way I understand things, it doesn't matter; any number will run in the same amount of time (although different for the different versions 512 vs. 1018-bit). Someone let me know if that's not the case. I'm currently working on the 197 digit cofactor of 149^70+70^149: Code: 18990123508557902868419834986612849212629329047848408031918356871905091180915018818857084783656883790655928770567349115604303665109625610225945717466120031386943078873289069222693826896799892056101 which you can use for the larger ECM version. Pick anything you like for the smaller one.
I'll run the lower levels tonight as I get a chance to. That will provide an approximate trend, as I've noticed that the time involved for higher B1s is roughly linear with B1.

2017-09-27, 19:26   #440
xilman
Bamboozled!

May 2003
Down not across

10,069 Posts

Quote:
 Originally Posted by bsquared Maybe I missed it, but I haven't seen any benchmark numbers for GPU-ECM since several years ago in this thread. Could I ask someone to do that for current-generation GPUs? e.g., how long does it take to run N parallel curves for each of the 512-bit and 1018-bit versions (which I understand to be the only reliable ones)?
I'll see what I can do. For better or worse I seem to have ended up with the job of maintaining GPU-ECM. Any assistance with that task will be much appreciated. In particular, evidence of inadequacies of the software will be useful. Even more useful will be contributions to its enhancement.

BTW, and AFAIK, the 512-bit version is really 506-bit limited. One of the things on my to-do list is to allow for more versions. Ideally the end-user shouldn't have to predetermine the size of the arithmetic. Another WIBNI is to implement stage 2 on the GPU. That might be the easier of the two. I would also like to extend the ECMNET client to use a GPU where available.

 Similar Threads Thread Thread Starter Forum Replies Last Post Rodrigo GPU Computing 3 2016-05-17 05:43 ATH GMP-ECM 10 2012-07-29 17:15 ATH GMP-ECM 7 2012-01-07 18:34 davieddy Lounge 0 2011-01-21 19:29 [CZ]Pegas Software 3 2002-08-23 17:05

All times are UTC. The time now is 00:14.

Sat Jul 4 00:14:11 UTC 2020 up 100 days, 21:47, 1 user, load averages: 1.19, 1.33, 1.31