Message boards :
Number crunching :
Panic Mode On (103) Server Problems?
Message board moderation
Previous · 1 . . . 11 · 12 · 13 · 14 · 15 · 16 · 17 . . . 34 · Next
Author | Message |
---|---|
arkayn Send message Joined: 14 May 99 Posts: 4438 Credit: 55,006,323 RAC: 0 |
My 1070 does a guppie in about 10 minutes working on 2 at a time. |
betreger Send message Joined: 29 Jun 99 Posts: 11361 Credit: 29,581,041 RAC: 66 |
Thanx, that fixed it. I wonder why it wouldn't refresh on it's own. |
Al Send message Joined: 3 Apr 99 Posts: 1682 Credit: 477,343,364 RAC: 482 |
It will be interesting to see how the rig with 56 cores shapes up, once I get the time to complete it. Bwhahahaha! |
Stubbles Send message Joined: 29 Nov 99 Posts: 358 Credit: 5,909,255 RAC: 0 |
Bwhahahaha! Thanks, I needed that since I just changed my signature to: August 2016 saga update: I just found out that (ab)user was a S@h moderator!!! :-O I don't even feel like: "Keep calm and I just want to get off this stupid planet!!! |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
. . So nonVLAR work on your CPU runs faster than VLAR work on your CPU? . . Or does VLAR work on your GPU run faster than nonVLAR work on your GPU? . . To be clear I will rephrase my words. . . CPUs actually like Guppis (well mine do anyway). They run quicker than normal AR {on CPUs} work so yes your RAC would go up. But normARs {on GPUs} definitely run better than VLAR work on GPUs. . |
Zalster Send message Joined: 27 May 99 Posts: 5517 Credit: 528,817,460 RAC: 242 |
Both run faster on my GPUs than my CPU so much so that I don't bother with the CPU anymore. 3 nonvlars in 12 minutes, 3 vlars in 18-20 minutes Only Petri runs faster |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
. . So how much longer do nonVLARs take to run on your 1070? . |
Stubbles Send message Joined: 29 Nov 99 Posts: 358 Credit: 5,909,255 RAC: 0 |
Both run faster on my GPUs than my CPU so much so that I don't bother with the CPU anymore. Can I shake your money tree and pick up the loose change left on the ground? lol :-p |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
On my systems, Arecibo nonVLARs on the CPU runs usually around 2 hours +/- 5 minutes or so. Arecibo VLARs on the CPU run usually around 1:45 hours +/- 5 minutes. Guppi VLARs on the CPU usually run around 1:45 hours +/- 15 minutes. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Guppi nonVLARS on my 1070 take 5-10 minutes to finish. Two tasks per card. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
Stubbles Send message Joined: 29 Nov 99 Posts: 358 Credit: 5,909,255 RAC: 0 |
. . CPUs actually like Guppis (well mine do anyway). They run quicker than normal AR {on CPUs} work so yes your RAC would go up. But normARs {on GPUs} definitely run better than VLAR work on GPUs. For those who use both CPU & GPU, I agree ...except for "so yes your RAC would go up" as I haven't scrolled up to find out the context. |
Zalster Send message Joined: 27 May 99 Posts: 5517 Credit: 528,817,460 RAC: 242 |
Both run faster on my GPUs than my CPU so much so that I don't bother with the CPU anymore. lol...I have over 8K validation pending...and climbing... |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
Both run faster on my GPUs than my CPU so much so that I don't bother with the CPU anymore. . . OK I'll say it one more time. I was NOT comparing CPU to GPU times sheeeeeesh! . . But your card is a 1070 is it? Or is it a 1080? . . Have you ever ran an Arecibo VLAR task on your GPU? No sorry I just realised you are running CUDA like Petri. You would need to be running an openCL app like SoG. I was impressed that it is only slightly slower than a Guppi. Your comment of no longer using CPUs for crunching made me think of it. . |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
. . I would like to discuss that more with you Kevin but in another thread I think. . |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Sure, start the new thread and point me at it. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
That's mind-boggling Zalster. I only have about 900 validation pending. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
Zalster Send message Joined: 27 May 99 Posts: 5517 Credit: 528,817,460 RAC: 242 |
Uh, no.. I don't run CUDA.. I'm a Raistmer SoG fanboy... So all work, non dependent of where it comes from is run on the GPUs. I have run both BLC VLARS, Arecibo VLAR, BLC VHAR, Arecibo VHAR and everything in between. I didn't say much about this for a long time and allowed everyone to bash Raistmer, but now the pudding in the showing. All my crunchers are SoG and they run better than standard Cuda. Only Petri special app is faster. And as for my cards, they are listed in my computers Titan Xs, 1080, 980Tis So when people make broad statements to others that they should move all BLC to CPU because it's faster, it's not true! Please stop saying this. Maybe for your system is it, but that doesn't represent everyone else. Happy Crunching... Zalster Edit.. I apologize if any of this sounds angry or offends anyone, not my intentions Z |
woohoo Send message Joined: 30 Oct 13 Posts: 972 Credit: 165,671,404 RAC: 5 |
i don't use cpus, so nowhere to reschedule to either |
Stubbles Send message Joined: 29 Nov 99 Posts: 358 Credit: 5,909,255 RAC: 0 |
So when people make broad statements to others that they should move all BLC to CPU because it's faster, it's not true! With all due and intended respect: Most average rigs (1 CPU + 1or2 GPUs) will produce more with some CPU tasks than none. Therefore moving BLCs (aka guppi) to CPU queue is optimal since Arecibo tasks take longer on CPU cores. Us non-gurus only help other non-gurus who have average rigs. Your rigs are the exception as you've spent many thousands on each power rig. I don't think it is unreasonable to: make broad statements to others that they should move all BLC to CPU because it's fasterbecause it is true for 99% of rigs that also do some crunching on CPU cores. As I started, with all due and intended respect Zalster, RobG :-) |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Will make for an interesting experiment I think .... after the contest close. Don't want to upset the apple cart now with how well things are currently running. I figure, if I have CPU cores sitting idle and doing nothing, I am not running efficiently. I may try to run 3 up per card after the contest which will knock my available CPU cores down to 1. I like having at least 1 core available to do general desktop maintenance so as to avoid system lags. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
©2024 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.