Posts by Zalster

1) Message boards : Number crunching : Anything relating to AstroPulse (2) tasks (Message 1970180)
Posted 23 hours ago by Profile Zalster Special Project $250 donor
Post:
5 for today
2) Message boards : Number crunching : Incorrect timing in the "Not sending work - last request too recent:" logic. (Message 1970095)
Posted 1 day ago by Profile Zalster Special Project $250 donor
Post:
+1

You are requesting work too soon so that is why it's refusing you new work. I complete work in 57 seconds but I allow BOINC to wait until the default timer calls for new work.
3) Message boards : Number crunching : Don't know where it should go? Stick it here! (Message 1969386)
Posted 5 days ago by Profile Zalster Special Project $250 donor
Post:
If I remember correctly that downloading more than 1 work unit per GPU was an error issue with BOINC. Can't remember where I saw it, Juan is correct that if BOINC is working correctly, then it only downloads 1 work unit per GPU. That said....I have had the issue that Keith mentions but haven't had it in a while. So, was it an issue with BOINC before 7.4.44??
4) Message boards : Number crunching : User achievements thread......... (Message 1969384)
Posted 5 days ago by Profile Zalster Special Project $250 donor
Post:
Congrats Mark.. I see you have the prize in your gunsights...1 BILLION...keep going Kittyman!!
5) Message boards : Number crunching : GTX is dead long live RTX !! (Message 1968820)
Posted 9 days ago by Profile Zalster Special Project $250 donor
Post:
Just do the math.

With about 40 secs to crunch a WU. A single 2080Ti could crunch more than 2100 WU per day
At around 60 credit per WU (thanks to Credit Screw) it produces a little more than 120 K credits per day.

That's is a little more than 2X a 1070 using less than 30% more power. Amazing!


Except lately Credit screw is giving about 1 credit for 1 second of work (or less, actually starting to see that) so cut that 120K by 20%
6) Message boards : Number crunching : Anything relating to AstroPulse (2) tasks (Message 1968770)
Posted 9 days ago by Profile Zalster Special Project $250 donor
Post:
Got 5, but the first 3 are showing overflows. Waiting on the last 2 to crunch.
7) Message boards : Number crunching : 03dc18od (Message 1968746)
Posted 9 days ago by Profile Zalster Special Project $250 donor
Post:
Yeah, i realized that soon after I posted this, haha... Been so long that I forgot about Arecibo work units.
8) Message boards : Number crunching : 03dc18od (Message 1968736)
Posted 9 days ago by Profile Zalster Special Project $250 donor
Post:
So, I'm curious...

What are the run times people are seeing using the special app on this tape??
9) Message boards : Number crunching : Panic Mode On (114) Server Problems? (Message 1968667)
Posted 10 days ago by Profile Zalster Special Project $250 donor
Post:
back already??
10) Message boards : Number crunching : NVidia GPU tasks 'postponed' (Message 1967911)
Posted 14 days ago by Profile Zalster Special Project $250 donor
Post:
You downloaded the nvidia driver from the nvidia website and not Windows correct???

If not, then you need to download directly from Nvidia website, do a clean install and restart your system.


Edit..

Option 2 is to download a prior driver that is known to work and install that one
11) Message boards : Number crunching : Developing a Multi-Threaded Benchmarking App for Linux (Message 1967852)
Posted 14 days ago by Profile Zalster Special Project $250 donor
Post:
Was afraid of that.

Josef Winsor Segur
DECEASED | Keeseville, NY
12) Message boards : Number crunching : Developing a Multi-Threaded Benchmarking App for Linux (Message 1967846)
Posted 14 days ago by Profile Zalster Special Project $250 donor
Post:
Way off topic but does anyone know if Joe was from NY?
13) Message boards : Number crunching : Should I leave cores or threads free for GPU? (Message 1965885)
Posted 27 days ago by Profile Zalster Special Project $250 donor
Post:
I have a new theory. A number of the people in this community have gotten cranky (Yes, I am one of them :( ). I think that as a group we are all suffering from Seasonal Affective Disorder and taking it out on each other :)

Here is is coming up on Thanksgiving and the Sun is staying up shorter and shorter times.

Tom


Hench my comment last week about sending all Seti Users on a vacation for a week to the Caribbean.....lol
14) Message boards : Number crunching : Anyone else get the latest News and donor request? (Message 1965854)
Posted 27 days ago by Profile Zalster Special Project $250 donor
Post:
If and when there is something to test on Beta I'll move my machines, but there hasn't been anything to test in well over a year so no need to Beta test a app that already on Main.
15) Message boards : Number crunching : Anyone else get the latest News and donor request? (Message 1965761)
Posted 27 days ago by Profile Zalster Special Project $250 donor
Post:
Thanks Keith,

Interesting reading. More than we can process he says?? Don't know how much of that is true or not, lol...but either way, it makes a good sales pitch....
16) Message boards : Number crunching : Anyone else get the latest News and donor request? (Message 1965742)
Posted 27 days ago by Profile Zalster Special Project $250 donor
Post:
Just checked my email..Nothing...
17) Message boards : Number crunching : Anything relating to AstroPulse (2) tasks (Message 1965724)
Posted 27 days ago by Profile Zalster Special Project $250 donor
Post:
I thought Raistmer had written the OpenCl apps for the GPUs. He might be able to point you in the right direction.
18) Message boards : Number crunching : Anything relating to AstroPulse (2) tasks (Message 1965397)
Posted 29 days ago by Profile Zalster Special Project $250 donor
Post:

Nom ap_23oc18ac_B2_P0_00049_20181024_10557.wu_1
Unité de travail (WU) 3184556651
Créé 24 Oct 2018, 14:49:15 UTC
Envoyé 24 Oct 2018, 14:49:16 UTC
Date limite de rapport 18 Nov 2018, 14:49:16 UTC
Reçu 15 Nov 2018, 15:19:49 UTC
État du serveur Sur
Résultats Succès
État du client Fait
État à la sortie 0 (0x00000000)
ID de l'ordinateur 8538185
Temps de fonctionnement 21 jours 21 heures 3 min 53 sec
Temps de CPU 16 jours 12 heures 12 min
Valider l'état Valide
Crédit 461.76
FLOPS maximum de l'appareil 0.68 GFLOPS
Version de l'application AstroPulse v7 v7.00
windows_intelx86
Peak working set size 24.91 MB
Peak swap size 20.30 MB
Peak disk usage 2.52 MB
Stderr output


this is the longuest AP wu crunching time i ever seen before ^^


well it's running on a 1.6GHz intel atom processor, so....


+1
19) Message boards : Number crunching : Should I leave cores or threads free for GPU? (Message 1965394)
Posted 29 days ago by Profile Zalster Special Project $250 donor
Post:
And you are welcome to your "opinion" but I don't run 1 core 1 gpu. I run 12, 16, 20 thread with 3 and 4 GPUs across 3 projects. So my "solution" does work.

First "project max concurrent" only applies that project where it is used. So of course it will not affect "other" projects. It's not meant to. It's only affecting the project to which it is assigned.

Doing multiple projects requires you to remember what the limits you are placing on each project. That means both website preference and local ie.. max concurrent or project max concurrent in each different project. It's a balancing act that you will need to spend time figuring out just how to set each project. I've spent months on different projects learning how to tune my systems for each. I used that information to balance out my computers so that run at their fastest configuration. There is no "one key fits all". Your system may run "faster" with the % of cpu but it's probably not at its' most efficient design.

Z
20) Message boards : Number crunching : Should I leave cores or threads free for GPU? (Message 1965162)
Posted 14 Nov 2018 by Profile Zalster Special Project $250 donor
Post:
And here we start again with the % of CPU cores to be used.

It doesn't do what you think it does.

If you don't want to use all your CPU thread then insert a <project_max_current>N</project_max_concurrent> into your app_config.xml and set 100% of all CPU threads.

GPU will be given preference and when there is no GPU work, the CPU will pick up the extra thread. Example, an 16 thread CPU with 2 GPUs(if only 1 work unit per GPU)and 10 CPU work units would a value of 12 .. If 2 work units per GPU then it would be 4 GPU and 8 CPU work unit with the continue value of 12 in project max current. When the GPU run of of work, 4 more CPU work units would start and then there would be 12 max work units running. When fresh GPU work is available, 4 CPU would be suspended and the GPUs would start up again. Those 4 suspended would finish up whenever a CPU thread frees up.

The concept that reducing CPU usage to 90% frees up a core is wrong. The only thing you have done is reduced the number of threads that are processing the same amount of work. That "free" thread isn't going to be used by the GPUs. Because you specifically told BOINC that it isn't allowed to use the 10%. So the GPUs are going to be stealing cycles from the other threads. If you want the GPU to have a unused thread, it has to be able to use any non used thread.


Next 20


 
©2018 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.