Posts by petri33


log in
1) Message boards : Number crunching : Panic Mode On (98) Server Problems? (Message 1703811)
Posted 13 days ago by Profile petri33Project donor
My version has still some accuracy problems.


Still didn't find the complete story there, though have the full team winding up to put each bit in and see what breaks (watch that Github soon). The Chirp explains a little, but not all of the issue. It'll be interesting what falls out the next few weeks in the background.


My answer is off topic. Not a server problem. I'll pm.
2) Message boards : Number crunching : Panic Mode On (98) Server Problems? (Message 1703799)
Posted 13 days ago by Profile petri33Project donor
Now I'd be happy to get VLARs to my NVIDIA cards.
Is there a way to say in app_info.xml that my cards could take a try? (2000 seconds one at a time)
(Fake they are ATI/AMD ...)


you could pretend they are CPU instead.
And revive my old @teammod@ to process both CPU and GPU apps via CPU-only BOINc scheduling. Good old days before BOINC even know what GPU is :DDD


I thought of that. I remember seeing a bit of code that determined what GPU to use by looking which one had most free memory or something similar.

I coded once a solution that had a variable in shared (CPU) memory and an increment counter modulo N (N=number of GPUs) to put the next task to that GPU..

But none of that is not necessary since the normal MB work is flowing in again.

I used the down-time to upgrade my Linux (Ubuntu) version to a newer one.
3) Message boards : Number crunching : Panic Mode On (98) Server Problems? (Message 1703486)
Posted 14 days ago by Profile petri33Project donor
Now I'd be happy to get VLARs to my NVIDIA cards.
Is there a way to say in app_info.xml that my cards could take a try? (2000 seconds one at a time)
(Fake they are ATI/AMD ...)

No idea. But maybe you can use the Rescheduler to move them from CPU to GPU?


I could reschedule one task by hand. How? Editing some file?
I will not try to find a rescheduler for my linux machine.

Just edit the client state file by changing the <results> entry to the version number and plan class of your CUDA App in your app_info. Works for ATIs.
Just watch the estimated time, it may be too short after the change.
Best way is to suspend the VLAR, stop BOINC, then edit the entry containing the suspended line. In my case I would change;
<version_num>700</version_num>
to
<version_num>708</version_num>
<plan_class>opencl_ati5_sah</plan_class>

Don't make a mistake...or you Lose All your cache...



Thanks TBar, that is what I did. I had to do it to both clien_state and client_state_prev .xml files.

Now I'm going to check how it did (WU). It may require a third run by someone else. My version has still some accuracy problems.

Hmmm, not much difference. Except mine didn't overflow;
Yours, Run time: 28 min 46 sec
Mine, Run time: 28 min 37 sec
I think the Grump found the nVidia OpenCL App was a little faster on MBs, but it ate a whole CPU core.
Or, maybe it was someone else...


Here is one that did not overflow. Runtime a bit high. (WU)
4) Message boards : Number crunching : Panic Mode On (98) Server Problems? (Message 1703442)
Posted 14 days ago by Profile petri33Project donor
Now I'd be happy to get VLARs to my NVIDIA cards.
Is there a way to say in app_info.xml that my cards could take a try? (2000 seconds one at a time)
(Fake they are ATI/AMD ...)

No idea. But maybe you can use the Rescheduler to move them from CPU to GPU?


I could reschedule one task by hand. How? Editing some file?
I will not try to find a rescheduler for my linux machine.

Just edit the client state file by changing the <results> entry to the version number and plan class of your CUDA App in your app_info. Works for ATIs.
Just watch the estimated time, it may be too short after the change.
Best way is to suspend the VLAR, stop BOINC, then edit the entry containing the suspended line. In my case I would change;
<version_num>700</version_num>
to
<version_num>708</version_num>
<plan_class>opencl_ati5_sah</plan_class>

Don't make a mistake...or you Lose All your cache...



Thanks TBar, that is what I did. I had to do it to both clien_state and client_state_prev .xml files.

Now I'm going to check how it did (WU). It may require a third run by someone else. My version has still some accuracy problems.
5) Message boards : Number crunching : Panic Mode On (98) Server Problems? (Message 1703428)
Posted 14 days ago by Profile petri33Project donor
I managed to do the edit manually...

It started to crunch ...

root@Linux1:~/Downloads/BOINC# cat slots/6/stderr.txt setiathome_CUDA: Found 4 CUDA device(s): Device 1: GeForce GTX 780, 3071 MiB, regsPerBlock 65536 computeCap 3.5, multiProcs 12 pciBusID = 2, pciSlotID = 0 Device 2: GeForce GTX 780, 3071 MiB, regsPerBlock 65536 computeCap 3.5, multiProcs 12 pciBusID = 1, pciSlotID = 0 Device 3: GeForce GTX 780, 3071 MiB, regsPerBlock 65536 computeCap 3.5, multiProcs 12 pciBusID = 3, pciSlotID = 0 Device 4: GeForce GTX 780, 3071 MiB, regsPerBlock 65536 computeCap 3.5, multiProcs 12 pciBusID = 4, pciSlotID = 0 In cudaAcc_initializeDevice(): Boinc passed DevPref 3 setiathome_CUDA: CUDA Device 3 specified, checking... Device 3: GeForce GTX 780 is okay SETI@home using CUDA accelerated device GeForce GTX 780 Using pfb = 4 from command line args Using pfp = 192 from command line args setiathome enhanced x41zc, Cuda 6.50 special Detected setiathome_enhanced_v7 task. Autocorrelations enabled, size 128k elements. Work Unit Info: ............... WU true angle range is : 0.012579 Sigma 127 Thread call stack limit is: 1k


now I'm waiting it to finish. Estimate (bad) was 7 minutes.


EDIT:
minutes done
4:00 10%
5:00 12.57%
7:00 17.67%
8:00 20.32%
9:00 23.16%
10:00 26.16%
14:00 40.39%
15:00 43.61%
16:00 46.59%
17:00 49.81%
18:00 52.98%
19:00 55.00%
20:00 59.07%
21:00 62.30%
22:00 65.00%
23:00 68.10%
24:00 71.18%
25:00 73.90%
26:00 76.75%
27:00 79.60%
28:00 82.25%
28:46 100.00% (sudden jump, maybe 30/30)

End of test.
6) Message boards : Number crunching : Panic Mode On (98) Server Problems? (Message 1703398)
Posted 14 days ago by Profile petri33Project donor
Now I'd be happy to get VLARs to my NVIDIA cards.
Is there a way to say in app_info.xml that my cards could take a try? (2000 seconds one at a time)
(Fake they are ATI/AMD ...)

No idea. But maybe you can use the Rescheduler to move them from CPU to GPU?


I could reschedule one task by hand. How? Editing some file?
I will not try to find a rescheduler for my linux machine.
7) Message boards : Number crunching : Panic Mode On (98) Server Problems? (Message 1703392)
Posted 14 days ago by Profile petri33Project donor
I have a CUDA MB app built from the source (modified to use CUDA streams to achieve 95% GPU occupancy when running just one MB at a time). This is not the beta OpenCL app.

I'd need the right information for the app_info.xml to make the server think this is an OpenCL app even though it is not.

A user selectable option "compute VLAR" y/n in the preferences would be good too.
8) Message boards : Number crunching : Panic Mode On (98) Server Problems? (Message 1703383)
Posted 14 days ago by Profile petri33Project donor
Now I'd be happy to get VLARs to my NVIDIA cards.
Is there a way to say in app_info.xml that my cards could take a try? (2000 seconds one at a time)
(Fake they are ATI/AMD ...)
9) Message boards : Number crunching : Anything relating to AstroPulse tasks (Message 1699954)
Posted 25 days ago by Profile petri33Project donor
Somehow nv driver 353.30 messes up my intel-gpu tasks.
Once installed and settled, every new task started seems to run fine.
However, every intel-gpu tasks, that was started progresses very slowly with very little gpu utilization.
Unless there is a way to "reset" a single task, i guess, i just have to sit it out.


I'd try suspend and resume for Seti at home in Boinc manager projects tab. Or suspend and resume for the task.
10) Message boards : Number crunching : TIME FOR A NEW FUND DRIVE. (Message 1699257)
Posted 28 days ago by Profile petri33Project donor
Even though the donations statistics does not show it I'm donating $25 every month. Started when I joined Raccoon Lovers team.
11) Message boards : Number crunching : Panic Mode On (98) Server Problems? (Message 1699145)
Posted 28 days ago by Profile petri33Project donor
http://setiathome.berkeley.edu/gpu_list.php

this is what I got

The following lists show the most productive GPU models on different platforms. Relative speeds, measured by average elapsed time of tasks, are shown in parentheses. Notice: Trying to get property of non-object in /disks/carolyn/b/home/boincadm/projects/sah/html/user/gpu_list.php on line 208 NVIDIA Notice: Trying to get property of non-object in /disks/carolyn/b/home/boincadm/projects/sah/html/user/gpu_list.php on line 175 No GPU tasks reported Notice: Trying to get property of non-object in /disks/carolyn/b/home/boincadm/projects/sah/html/user/gpu_list.php on line 209 ATI/AMD Notice: Trying to get property of non-object in /disks/carolyn/b/home/boincadm/projects/sah/html/user/gpu_list.php on line 175 No GPU tasks reported Notice: Trying to get property of non-object in /disks/carolyn/b/home/boincadm/projects/sah/html/user/gpu_list.php on line 210 Intel Notice: Trying to get property of non-object in /disks/carolyn/b/home/boincadm/projects/sah/html/user/gpu_list.php on line 175 No GPU tasks reported Notice: Trying to get property of non-object in /disks/carolyn/b/home/boincadm/projects/sah/html/user/gpu_list.php on line 211 Generated ---
12) Message boards : Number crunching : Ooops, Sorry guys (Message 1699144)
Posted 28 days ago by Profile petri33Project donor
My i100 has run now for 2-3 years with no problems. Yours i80 should be OK. (The noise should be enough to warrant it).

I'm probably the best person to tell you that since I did not warrant my GTX780's when their fans started to make noise. I bored holes into them and tried to rescue them with some oil....

If You are getting work back I guess it may have been a temporary hiccup. But ...
13) Message boards : Number crunching : It is official! 15th Seti Anni Shirts are a go. (Message 1698578)
Posted 5 Jul 2015 by Profile petri33Project donor
Starting from Sat 11th July I'll be wearing my Seti T-shirt in Valencia, Spain, for a week.

If there are restaurants with a dress code - then especially so.
14) Message boards : Number crunching : Bad News on BOINC funding (Message 1698574)
Posted 5 Jul 2015 by Profile petri33Project donor
Before you ask "what about crowd-funding", it was one of the first things I asked David when I got the news. He answered me:

That would be a last resort.
The main beneficiary of volunteer computing is government-funded science research.
We save these funding agencies (like NSF) many millions of dollars, so logically they should fund us.

Also, Rom and I are expensive, and it's not likely that crowd-funding would
produce enough to support us.


No they are not expensive.


I think it would be very expensive to develop some water to not to fill the void their fingers would leave once dipped into a cup and raised back up.
15) Message boards : Number crunching : Invalid Host Messaging (Message 1696709)
Posted 29 Jun 2015 by Profile petri33Project donor
I'll fix the heat problem when I get home next Sunday.

The other issue is with seventh or eigth decimal. Summing sequentially, summing sequentially on groups or summing recursively pairwise produce slightly different results due to using float data type.
16) Message boards : Number crunching : 17" GPU fan died yesterday (Message 1695298)
Posted 24 Jun 2015 by Profile petri33Project donor
looks like he has asus GTX780-DC2OC-3GD5


That is the card. I have removed the metal shield and the malfunctioning fans.
It is easier to replace a tabletop fan once every half years. That's what they seem to last even when lubricated with Mobil 1 rally formula 5W-50. Maybe I should re-apply the oil weekly every tuesday :)
17) Message boards : Number crunching : 17" GPU fan died yesterday (Message 1695279)
Posted 24 Jun 2015 by Profile petri33Project donor
Here is the sidepanel (not in use) and the old fan.

http://setiathome.berkeley.edu/forum_thread.php?id=73909&postid=1635858
18) Message boards : Number crunching : 17" GPU fan died yesterday (Message 1695220)
Posted 24 Jun 2015 by Profile petri33Project donor
My solution is a bank of four 150mm fans in the side of the case.....

(room may be noisy, but I'm never i there to find out...)


I have got a customised side panel with four 21 cm fans but they are not as powerful as the tabletop fan.

And yes, no harm to other components.
19) Message boards : Number crunching : 17" GPU fan died yesterday (Message 1695205)
Posted 24 Jun 2015 by Profile petri33Project donor
Got home today and wondered why it was so cool and quiet here.

My machine had stopped working because of CPU overheat protection. But not soon enough. There will be a lot of calculation errors on CPU tasks. The GPU fans have died a long time ago and are cooled with a 17" tabletop fan blowing air directly to them.

The old broken tabletop fan is now replaced with a new one.

The machine is reporting old tasks (some failed) and loading new ones.
20) Message boards : Number crunching : Possible memory deal? (Message 1694884)
Posted 23 Jun 2015 by Profile petri33Project donor
Hi Petri,

I was away for a long weekend but the memory was there when I arrived home yesterday. I will fit it later today.

OCZ is a well known upmarket memory make, but am intrigued at the heat spreaders with "Nvidia SLI ready" on them". Not seen that before.

Thank you very much :-)


You're welcome.

The SLI-ready must be some marketing trick to get more money from enthusiasts.


Next 20

Copyright © 2015 University of California