Message boards :
Number crunching :
Anything relating to AstroPulse (3) tasks
Message board moderation
Previous · 1 · 2 · 3 · 4 · 5 · 6 . . . 104 · Next
Author | Message |
---|---|
Wiggo Send message Joined: 24 Jan 00 Posts: 34748 Credit: 261,360,520 RAC: 489 |
10 turned up here for the 21st UTC. Cheers. |
betreger Send message Joined: 29 Jun 99 Posts: 11361 Credit: 29,581,041 RAC: 66 |
1 so far on the 22nd but the day is young. |
johnnymc Send message Joined: 5 May 99 Posts: 35 Credit: 9,138,623 RAC: 0 |
The most AP's I've ever had at one time occurred today when I noticed 13 (lucky me?!) in my queue. Boinc processed two of them then coyly moved along to pester the guppis... Life's short; make fun of it. |
Zalster Send message Joined: 27 May 99 Posts: 5517 Credit: 528,817,460 RAC: 242 |
24 for the 22nd.... |
Mike Send message Joined: 17 Feb 01 Posts: 34258 Credit: 79,922,639 RAC: 80 |
14 here. With each crime and every kindness we birth our future. |
Bill G Send message Joined: 1 Jun 01 Posts: 1282 Credit: 187,688,550 RAC: 182 |
51 for the 22nd. Yippie SETI@home classic workunits 4,019 SETI@home classic CPU time 34,348 hours |
Wiggo Send message Joined: 24 Jan 00 Posts: 34748 Credit: 261,360,520 RAC: 489 |
30 arrived here for the 22nd UTC. Cheers. |
Kissagogo27 Send message Joined: 6 Nov 99 Posts: 716 Credit: 8,032,827 RAC: 62 |
7 here for the 22th ^^ |
Tom M Send message Joined: 28 Nov 02 Posts: 5124 Credit: 276,046,078 RAC: 462 |
Documentation seems to think that 2 AP tasks at a time on a higher end gpu produces the most production? What is your experience/opinion? Thank you. Tom A proud member of the OFA (Old Farts Association). |
tazzduke Send message Joined: 15 Sep 07 Posts: 190 Credit: 28,269,068 RAC: 5 |
I got 5 in one hit for 23rd Cheers |
Zalster Send message Joined: 27 May 99 Posts: 5517 Credit: 528,817,460 RAC: 242 |
Documentation seems to think that 2 AP tasks at a time on a higher end gpu produces the most production? This response is for Windows only...No testing on Linus ( or Linux for that matter hahaha) Yes, it will. Best production is 5 per GPU but...... APs are so rare that it's hard to get that many anymore. So the default is 1 per card. You can change your app_config to run more than 1 but you run into a problem if you an AP and MB both run on the GPU. The MB will slow down while the AP speeds up. Once the AP finishes, the MB will return to normal run. Those were the old cudas 42,50 Again, all this was for windows based systems. No idea how Linux special sauce will react with OpenCl on the same card. Z |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
I got busy and forgot to look. Received 152 AP tasks for the 22nd UTC. Plenty more are coming for the 23rd. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
Tom M Send message Joined: 28 Nov 02 Posts: 5124 Credit: 276,046,078 RAC: 462 |
Documentation seems to think that 2 AP tasks at a time on a higher end gpu produces the most production? Thank you. I have my AP setup to run 2 tasks under linus/errr/linux. But my MB is setup to run 1 / gpu so I don't have a problem with running a MB at the same time I am running AP tasks. The docs did seem to think that you should run 2 cpus / gpu task. So I am doing that too. I was just wondering what the best combo would be for a mixed gtx 1070Ti/gtx 1060 3GB system? For some reason I don't think any of my gtx 1070ti's are getting hit with AP tasks. What is your "favorite" AP command line for your gpu? Thank you. Tom A proud member of the OFA (Old Farts Association). |
Zalster Send message Joined: 27 May 99 Posts: 5517 Credit: 528,817,460 RAC: 242 |
Add this to your app_config.xml. The unroll is probably need to be changed as it's for a 1080Ti. Change that to 68 for a 2080Ti. <app_version> <app_name>astropulse_v7</app_name> <plan_class>opencl_nvidia_100</plan_class> <avg_ncpus>1</avg_ncpus> <ngpus>0.5</ngpus> <cmdline>-unroll 28 -oclFFT_plan 256 16 256 -ffa_block 12288 -ffa_block_fetch 6144 -tune 1 64 4 1 -tune 2 64 4 1</cmdline> </app_version> |
Tom M Send message Joined: 28 Nov 02 Posts: 5124 Credit: 276,046,078 RAC: 462 |
Add this to your app_config.xml. The unroll is probably need to be changed as it's for a 1080Ti. Change that to 68 for a 2080Ti. Thank you. Tom A proud member of the OFA (Old Farts Association). |
Speedy Send message Joined: 26 Jun 04 Posts: 1643 Credit: 12,921,799 RAC: 89 |
Zalster I was reading your post to Tom about the command line. I have a 1070 TI and do you have any suggestions for the other (blc) units to make them run a little more efficiently? Currently they are running at around 7 minute mark TIA |
Zalster Send message Joined: 27 May 99 Posts: 5517 Credit: 528,817,460 RAC: 242 |
Hey Speedy, I think you can use the same commandline as I originally posted except use 19 instead of 28. I'm guessing. Never had a 1070Ti. Mike would know for sure but you can try it and see how it does. |
Speedy Send message Joined: 26 Jun 04 Posts: 1643 Credit: 12,921,799 RAC: 89 |
Hey Speedy, Thanks Zalster. I will wait until I hear from Mike or somebody else in them know as I do not want to damage my card or lock my system up |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Yes the unroll for a 1070 Ti should be 19. Unroll = the number of SM's in the chip. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
Speedy Send message Joined: 26 Jun 04 Posts: 1643 Credit: 12,921,799 RAC: 89 |
Yes the unroll for a 1070 Ti should be 19. Unroll = the number of SM's in the chip. Thanks Keith does it majorly effect Power usage? |
©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.