Message boards :
Number crunching :
Panic Mode On (102) Server Problems?
Message board moderation
Previous · 1 . . . 14 · 15 · 16 · 17 · 18 · 19 · 20 . . . 25 · Next
Author | Message |
---|---|
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14656 Credit: 200,643,578 RAC: 874 |
I think last week was for the introduction of GBT data which could not wait until Tuesday. After we'd been waiting since New Year's Eve... But I suppose 100 million bucks buys you some influence over the launch date(s), and Gagarin Day was as good a day as any. |
Al Send message Joined: 3 Apr 99 Posts: 1682 Credit: 477,343,364 RAC: 482 |
...But I suppose 100 million bucks buys you some influence over the launch date(s), and Gagarin Day was as good a day as any. What was said $100 mil for, and from who, why was it given, and are there any perceived downsides to us SETI crunchers? Thanks! |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14656 Credit: 200,643,578 RAC: 874 |
...But I suppose 100 million bucks buys you some influence over the launch date(s), and Gagarin Day was as good a day as any. Big boost for SETI@home from Yuri Milner's Breakthrough Listen Initiative |
betreger Send message Joined: 29 Jun 99 Posts: 11366 Credit: 29,581,041 RAC: 66 |
I'm confused when do we get to have our weekly outrage? |
kittyman Send message Joined: 9 Jul 00 Posts: 51469 Credit: 1,018,363,574 RAC: 1,004 |
I'm confused when do we get to have our weekly outrage? When the page goes blank. "Freedom is just Chaos, with better lighting." Alan Dean Foster |
Zalster Send message Joined: 27 May 99 Posts: 5517 Credit: 528,817,460 RAC: 242 |
So someone has noticed that there has been a decrease in the amount of MB for GPU coming out. I've notice that I have not received no new GPU work units since the outage. Could this be related to the GBT being split? |
Jimbocous Send message Joined: 1 Apr 13 Posts: 1855 Credit: 268,616,081 RAC: 1,349 |
So someone has noticed that there has been a decrease in the amount of MB for GPU coming out. Could be wrong, but I think during the outage they increased the number of GBT Splitters, and reduced the number of PFB Splitters. I suppose that could cause a reduction in units available for GPU. My caches are not full, as they would normally be ... |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
So someone has noticed that there has been a decrease in the amount of MB for GPU coming out. Well we do know that the majority of the GBT data is going to generate VLAR tasks. However the 750ti I'm playing around with seems to be getting work just fine. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
rob smith Send message Joined: 7 Mar 03 Posts: 22286 Credit: 416,307,556 RAC: 380 |
...don't forget, we've been suffering a VLAR plague from the current Arecibo tapes, thus there have been fewer tasks being sent to (Nvidia) GPUs... (Although I did see somewhere that Eric was going to be trialing the release of VLARs to GPUs....) Bob Smith Member of Seti PIPPS (Pluto is a Planet Protest Society) Somewhere in the (un)known Universe? |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
...don't forget, we've been suffering a VLAR plague from the current Arecibo tapes, thus there have been fewer tasks being sent to (Nvidia) GPUs... Has there been a shortage of non-VLAR tasks? I've been playing with a 750ti for about a week and I've not had any issues keeping 100 tasks. I have noticed that my phone has pretty much been getting VLAR tasks. Which doesn't help getting a good Average processing rate so it will stop switching between the 12 damn Android apps. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
petri33 Send message Joined: 6 Jun 02 Posts: 1668 Credit: 623,086,772 RAC: 156 |
Hi, My GPU WU queue is empty, I'm running MB v8 NV CUDA. There are 500000+ work units ready to send. The CPU app downloads those guppi vlars just fine. Do the ATI/AMD OpenCL platforms get guppi VLARS for processing? If yes then: What shoud I set to plan_class to get GPU work? (To fake I'm running AMD opencl) In the absence of non vlar work I could do vlars albeit slowly. They take about 14 minutes one at a time. Petri EDIT: I just received 20 tasks for my GPU. They are not guppi. My plan_class is <plan_class>opencl_nvidia_sah</plan_class> To overcome Heisenbergs: "You can't always get what you want / but if you try sometimes you just might find / you get what you need." -- Rolling Stones |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
I haven't received any GPU tasks at all today since the outage. Nothing but GBT vlars being downloaded. Setting the log options for scheduling shows an acknowledgement of GPU deficit but BOINC refuses to download any GPU work. Something has changed in the scheduler I think. Maybe Eric put something in place that changes the rules for Nvidia. These entries in the log are suspicious and something I've never seen before. Keith-Windows7 36177 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] reserving 0.330000 of coproc NVIDIA 36178 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] add to run list: 13au10aa.23534.4598.16.43.43_0 (NVIDIA GPU, FIFO) (prio -0.983826) 36179 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] reserving 0.330000 of coproc NVIDIA 36180 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] add to run list: 13au10aa.23534.4598.16.43.95_0 (NVIDIA GPU, FIFO) (prio -0.992389) 36181 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] reserving 0.330000 of coproc NVIDIA 36182 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] add to run list: 14se10ad.23501.4975.12.39.107_1 (NVIDIA GPU, FIFO) (prio -1.000953) 36183 Milkyway@Home 4/19/2016 11:04:24 PM [cpu_sched_debug] reserving 0.500000 of coproc NVIDIA 36184 Milkyway@Home 4/19/2016 11:04:24 PM [cpu_sched_debug] add to run list: de_modfit_fast_15_2s_136_ModfitConstraints1_2_1453826702_38380416_0 (NVIDIA GPU, FIFO) (prio -1.007310) 36185 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] reserving 0.330000 of coproc NVIDIA 36186 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] add to run list: 13au10aa.23534.4598.16.43.167_1 (NVIDIA GPU, FIFO) (prio -1.009516) 36187 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 13au10aa.21706.6234.15.42.25_1 36188 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 13au10aa.21706.6234.15.42.77_1 36189 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 13au10aa.23534.4598.16.43.97_0 36190 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 13au10aa.21706.6234.15.42.27_1 36191 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 13au10aa.23534.4598.16.43.41_1 36192 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 14se10ad.23501.4975.12.39.95_0 36193 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 13au10aa.23534.4598.16.43.115_1 36194 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 13au10aa.23534.4598.16.43.169_1 36195 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 13au10aa.23534.4598.16.43.113_1 36196 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 13au10aa.21706.6234.15.42.95_0 36197 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 14se10ad.23501.8247.12.39.88_0 36198 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 13au10aa.21706.11142.15.42.10_0 36199 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 13au10aa.21706.11142.15.42.163_1 36200 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 13au10aa.21706.11142.15.42.7_1 36201 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 13au10aa.21706.15641.15.42.175_0 36202 SETI@home 4/19/2016 11:04:24 PM [cpu_sched_debug] insufficient NVIDIA for 14se10ad.23501.15609.12.39.174_1 I'm sitting at about 100 GPU tasks on each machine and I should be at 200 tasks per machine since they both have two GTX970's. I'm fully loaded at 100 CPU tasks per machine. I don't think that the MB splitters are only pushing out VLAR GPU tasks right now which is the only other reason that Nvidia cards aren't getting GPU work. Anybody else confirm the scheduler requests? [Edit] So maybe the spigot has re-opened. I'm getting GPU work again on Pipsqueek, up to about 170 right now. Hope I see the same event happen on the main cruncher. But also seeing the 'insufficient Nvidia' on Pipsqueek also. Very weird recovery from the project outage today. Still think something's changed in the scheduler. 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 |
I'm getting the message "this computer has reached a limit on tasks in progress" |
Brent Norman Send message Joined: 1 Dec 99 Posts: 2786 Credit: 685,657,289 RAC: 835 |
I have 2 computers, each with a 750Ti, my cache drops to about 70 then crawls back up to 100. I can certainly see why people with 2 or more - 900 series cards are running out of work. Eric said that he couldn't find a way to send vlar tasks to NVidia cards so they work well. How about we try to send ONLY vlar to AMD cards, and leave nvidea to work on the rest? |
Zalster Send message Joined: 27 May 99 Posts: 5517 Credit: 528,817,460 RAC: 242 |
I don't think that would go over well with the ATI guys. I've already seen a post by someone complaining just about that. And I could see why. Their Credits would take a nosedive if they were forced to crunch those VLARs all the time. Unless they raise the credit for them to make it worthwhile. It really wouldn't be fair to punish the AMD people. |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
Hi, The value of <plan_class> in your app_info.xml doesn't have any specific meaning. You could enter <plan_class>banana</plan_class> & you would still be sent work for your Nvidia GPUs. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
Brent Norman Send message Joined: 1 Dec 99 Posts: 2786 Credit: 685,657,289 RAC: 835 |
Zal, I agree everyone is complaining about declining RAC at this time. But, there are (I would guess 100's) of Nvidia cards out there that are running on just a trickle of work. i.e. low RAC If you look at it from Berkley's side, they want data out and returned as fast as possible as a reliable result. If they are not utilizing the distributed computing power fully it hurts them. So why not try to split the computing power between cards? |
William Send message Joined: 14 Feb 13 Posts: 2037 Credit: 17,689,662 RAC: 0 |
Hi, it's not only the plan_class but also the device type (intel amd NV) that boinc determines and passes on. and the vlar filter hinges on the device type. A person who won't read has no advantage over one who can't read. (Mark Twain) |
William Send message Joined: 14 Feb 13 Posts: 2037 Credit: 17,689,662 RAC: 0 |
and according to this post from Eric at beta he is well aware of the problem and will be testing how the current NV app fares with guppis. do people ever look at their acronyms? I keep thinking of them as A person who won't read has no advantage over one who can't read. (Mark Twain) |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13770 Credit: 208,696,464 RAC: 304 |
do people ever look at their acronyms? I keep thinking of them as Nice to know I'm not the only one. Grant Darwin NT |
©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.