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

2017-09-27, 20:04   #441
wombatman
I moo ablest echo power!

May 2013

32·193 Posts

Quote:
 Originally Posted by xilman 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.
I can do little to nothing on the programming side of things, but I'm always happy to try and help out with testing. Please feel free to PM me when or if you want help there.

2017-09-28, 03:03   #442
VBCurtis

"Curtis"
Feb 2005
Riverside, CA

107B16 Posts

Quote:
 Originally Posted by wombatman 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.
Timing is within 1% of linear from 60M to 1200M (the smallest and largest bounds I've used for GPU-ECM). So, we can benchmark by testing a single B1 bound across cards.

To make the bench short-ish, how about the t50 standard B1 = 43M? I'll report 750ti numbers tomorrow.

 2017-09-28, 04:54 #443 wombatman I moo ablest echo power!     May 2013 32×193 Posts I checked B1=3M and 11M, and they were also within 1% of each other (0.6%, to be precise), so we could probably use one of those to decrease the time. If reproducibility is a concern, B1=3M could be run, say, 3 times and averaged. Last fiddled with by wombatman on 2017-09-28 at 04:54
 2017-09-28, 12:53 #444 wombatman I moo ablest echo power!     May 2013 32·193 Posts Times for the C197 bsquared put up on a GTX980Ti: B1=3M: 776.75s B1=11M: 2830.76s B1=43M: 11235.902s As noted by Curtis, these all scale linearly with B1 within ~1%.
2017-09-28, 13:16   #445
bsquared

"Ben"
Feb 2007

5·653 Posts

Quote:
 Originally Posted by wombatman Times for the C197 bsquared put up on a GTX980Ti: B1=3M: 776.75s B1=11M: 2830.76s B1=43M: 11235.902s As noted by Curtis, these all scale linearly with B1 within ~1%.
Thank you, much appreciated. How many curves does that card run in parallel? I'm trying to gauge the throughput of these things...

2017-09-28, 13:28   #446
wombatman
I moo ablest echo power!

May 2013

32×193 Posts

Quote:
 Originally Posted by bsquared Thank you, much appreciated. How many curves does that card run in parallel? I'm trying to gauge the throughput of these things...
1408 at once. Also, please note that those timings are just for Stage 1.

2017-09-28, 13:37   #447
bsquared

"Ben"
Feb 2007

5×653 Posts

Quote:
 Originally Posted by wombatman 1408 at once. Also, please note that those timings are just for Stage 1.
Yep, understood. Thanks - this is very helpful!

2017-09-28, 14:38   #448
wombatman
I moo ablest echo power!

May 2013

32·193 Posts

Quote:
 Originally Posted by bsquared Yep, understood. Thanks - this is very helpful!
Does this mean YAFU may be incorporating GPU-based ECM?

 2017-09-28, 16:55 #449 chris2be8     Sep 2009 2×52×37 Posts Output from the last job I ran with B1=43M: Code:  Wed 27 Sep 2017 03:16:08 BST ecm to 50 digits stage 1 step 1 of 2 ended GMP-ECM 7.0-dev [configured with GMP 5.1.3, --enable-asm-redc, --enable-gpu, --enable-assert] [ECM] Input number is 3129333620258940486330629139630925933631807344645219843266754670086579137577512492047980091055198974792305750155580720314468906941756462912147587701714558353912867079793467240454311904331638921 (193 digits) Using B1=43000000, B2=1, sigma=3:2949756002-3:2949756417 (416 curves) Computing 416 Step 1 took 251097ms of CPU time / 5018458ms of GPU time Wed 27 Sep 2017 04:42:07 BST ecm to 50 digits stage 1 step 2 of 2 ended The GPU does 416 curves at a time. The script waits for the stage 2 tasks to finish before starting the next stage 1 run. But the last save file says the residues were saved at Wed Sep 27 04:39:49 2017 so the run was from Wed 27 Sep 2017 03:16:08 to Wed Sep 27 04:39:49. The GPU is a GeForce GTX 970 according to nvidia-smi: Code: Thu Sep 28 16:56:39 2017 +------------------------------------------------------+ | NVIDIA-SMI 352.39 Driver Version: 352.39 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | |===============================+======================+======================| | 0 GeForce GTX 970 Off | 0000:01:00.0 Off | N/A | | 0% 54C P0 34W / 201W | 15MiB / 4095MiB | 0% Default | +-------------------------------+----------------------+----------------------+ +-----------------------------------------------------------------------------+ | Processes: GPU Memory | | GPU PID Type Process name Usage | |=============================================================================| | No running processes found | +-----------------------------------------------------------------------------+ Chris
2017-09-28, 18:48   #450
bsquared

"Ben"
Feb 2007

5×653 Posts

Quote:
 Originally Posted by wombatman Does this mean YAFU may be incorporating GPU-based ECM?
No... but possibly a competing technology
No promises...

2017-09-28, 20:41   #451
wombatman
I moo ablest echo power!

May 2013

6C916 Posts

Quote:
 Originally Posted by bsquared No... but possibly a competing technology No promises...
https://imgur.com/uu9pmDP

Edit: And when or if you want some testing done, feel free to PM

Last fiddled with by wombatman on 2017-09-28 at 20:42

 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 19:01.

Wed Jul 15 19:01:46 UTC 2020 up 112 days, 16:34, 2 users, load averages: 2.43, 1.85, 1.76