Posts by HAL9000

1) Message boards : Number crunching : Multicore smartphones - how to use their full potential (Message 1907237)
Posted 1 day ago by Profile HAL9000
Post:
By enabling Developer options/mode they then make other options, such as screen staying on while on charger, available.
Anything similar for Android phones?

Thanks for the idea!
The phone is now lying face-down on my night stand, continuously running two Seti tasks. I also know now why the CPU would clock down as the temperatures in this state are high. For just two cores running at full blast (and a third being used by the OS), temps have gone up from 25C to 45C and they're still rising. Glad it's cold in the bedroom.

The option is Preferences->Developer options->Stay awake (Screen will never sleep while charging)

I ran No Screen Off on that phone before but it would do so for only 10 minutes (600 seconds). I didn't dare try the other one when I read one or more people bricked their device with it. So this is the easier thing to do.
Of course enabling the Developer options is a pre (Open Settings> About> Software Information> More. Then tap “Build number” seven times to enable Developer options in the main preferences menu.)

Where I wouldn't mind leaving the phone alone and walk out the house, I'll unplug it before doing so later on. Especially with the higher heat build-up of the CPU and charger, I'd rather be home when it's doing stuff.

Reducing the screen brightness can help lower the heat build up on some devices.
2) Message boards : Number crunching : BOINC Manager replacement (Message 1907183)
Posted 1 day ago by Profile HAL9000
Post:
Personally I find the Processes tab in the Win 10 task manager as useful as the Notices tab in BOINC manager.
3) Message boards : Number crunching : Bug in Top Computers List (Message 1907096)
Posted 1 day ago by Profile HAL9000
Post:
It looks like your other machine has appeared. With your two hosts holding #30 and #40.
4) Message boards : Number crunching : Bug in Top Computers List (Message 1906914)
Posted 2 days ago by Profile HAL9000
Post:
This could also be related
Replica seconds behind master 66,571
5) Message boards : Number crunching : Bug in Top Computers List (Message 1906912)
Posted 2 days ago by Profile HAL9000
Post:
I don't recall what the update interval for the top host pages and other stats are. I was thinking it was around 30min or so, but maybe it is much less frequent.

One of my E5-2670 hosts at #351 displays a RAC of 23,356.36 and a Total of 11,331,790 in the host list. Currently it has a RAC of 24,235.82and a Total of 11,345,668.
That host is granted ~30k a day. So a difference of ~14k tells me the host list data is updating, but a few hours old.
I wonder if the data is being updated only when the daily stats are generated now?

Looking at the top list I see your other host
ID: 8011375, #32, RAC 64,249.27, Total 38,640,886
That host, at the time I'm making this post, has a RAC of 66,949.86 and a Total of 38,682,470.
The stat sites show that host normally is granted 40-80k credit a day and there is currently a difference of ~42K.

I still feel like your host 8188478 , with a RAC of 61K, might be stuck between pages.
6) Message boards : Number crunching : Multicore smartphones - how to use their full potential (Message 1906844)
Posted 2 days ago by Profile HAL9000
Post:

I was thinking of how in works, at least in Windows, when you launch BOINC with CPU affinity. It launches all child processes with the same affinity.

Ah, I see. Is it any tool in Android to see process/thread affinity like in Windows?

I don't know of any apps that show that info, but if there are apps they might require root access. :/
7) Message boards : Number crunching : Multicore smartphones - how to use their full potential (Message 1906786)
Posted 2 days ago by Profile HAL9000
Post:

Anyway when the phone is idle (second picture) i see only one core seems active, while when running BOINC (first picture) it seems all are active.
Cheers

That's how should be in case each task crunched on own core andphone uses all his computation nodes for crunching.
in my case 2 tasks launched by BOINC but only 1 CPU of 2 remains active.
So, each task takes ~2 times more elapsed time than CPU time to process and phone itself operates as single core devices.

Maybe the manufacture has limited each process that starts to only use one processor with some kind of processor affinity command.
Based on the behavior you have described that seems like something that may be occurring.

But cause BOINC launches 2 tasks there are 2 independent processes actually. Still they both use CPU 0 and CPU1 get switched off soon I stop touching the screen.

I was thinking of how in works, at least in Windows, when you launch BOINC with CPU affinity. It launches all child processes with the same affinity.
It sounds like some kind of aggressive power saving function.
I'm not sure if the default Android developer options, once enabled, would be of any help.
8) Message boards : Number crunching : Multicore smartphones - how to use their full potential (Message 1906604)
Posted 4 days ago by Profile HAL9000
Post:

Anyway when the phone is idle (second picture) i see only one core seems active, while when running BOINC (first picture) it seems all are active.
Cheers

That's how should be in case each task crunched on own core andphone uses all his computation nodes for crunching.
in my case 2 tasks launched by BOINC but only 1 CPU of 2 remains active.
So, each task takes ~2 times more elapsed time than CPU time to process and phone itself operates as single core devices.

Maybe the manufacture has limited each process that starts to only use one processor with some kind of processor affinity command.
Based on the behavior you have described that seems like something that may be occurring.
9) Message boards : Number crunching : Multicore smartphones - how to use their full potential (Message 1906602)
Posted 4 days ago by Profile HAL9000
Post:
Another point of comparison:

Host 8398355, currently running S@H and pogs.
[EDIT: Android 5.1.1, LG LTE model K330, in case the host info eventually gets deleted.]

Per CPU-z all 4 cores are running 97-100% at 998 MHz on wall socket, 95-99% at 1094 MHz on battery; listed range being 200MHz to 1.09 GHz

From an example WU: Wall Clock=85,532.95, CPU time=83,848.01 [seconds]

And I vaguely remember that it doesn't do Hyperthreading, but I'm forgetting how I found out.

There is a really quick way to find out if your ARM Snapdragon 210 (8909) processor does SMT.
1. Remember it is an ARM processor and ARM has not implemented SMT.

I would guess that they haven't implemented SMT due to licensing or they don't see a use for it. Given most ARM processors are used in embedded systems where SMT mat not be advantageous.
10) Message boards : Number crunching : Bug in Top Computers List (Message 1906215)
Posted 5 days ago by Profile HAL9000
Post:
That is a fairly well know issue with how the BOINC server code shows stats.

The issue is something along the lines of:
When someone requests a page for the stats a check is done to see if it has been updated in X amount of time.
If it hasn't it updates then. Otherwise it shows data from the last time it updated.

So if the interval is 20 minutes and someone looks at page 5 then 15 minutes later you look at page 4 and 5.
Page 4 may be up to date but page 5 is 15 minutes old.
11) Message boards : Number crunching : Task Deadline Discussion (Message 1905096)
Posted 10 days ago by Profile HAL9000
Post:
Other sources of useful data available on our end may be on BONCstats
A complete list of Host stats and not just the first 10,000
The Host CPU breakdown to see what kinds of hardware the ~100,000 active hosts are running.

Another consideration to keep in mind regarding the tasks that timed out and were added the ready to send tasks are ghosts that were timing out.
12) Message boards : Number crunching : Panic Mode On (108) Server Problems? (Message 1904919)
Posted 11 days ago by Profile HAL9000
Post:
No luck on the Xeon. Maybe I should install the resceduler and see if that helps. Or do I have to have at least one CPU already?

I don't know if rescheduling would help or not. I haven't run into that specific issue myself.
For others swapping settings and poking BOINC with a stick would resolve their issue.

I suppose if rescheduling some tasks does get things flowing a project reset in BOINC might work, but I never like doing a project reset myself.
13) Message boards : Number crunching : Panic Mode On (108) Server Problems? (Message 1904848)
Posted 11 days ago by Profile HAL9000
Post:
I have only got GPU tasks. Anybody got anything for CPU?

Some users have had an issues where their system would not receive CPU tasks when their GPU cache was full.
A workaround is to uncheck the GPU in your project prefs, update to get new settings, and then CPU tasks should be assigned on the next update.
Once you have CPU tasks recheck the GPU in your project prefs.
14) Message boards : Number crunching : Panic Mode On (108) Server Problems? (Message 1904829)
Posted 11 days ago by Profile HAL9000
Post:
Anybody any thoughts on how quick the RAC should recover after the outage? Mine was quick to drop but has not shown much sign of recovery despite crunching 100% since Saturday morning.

Slowly.
If there are no other unexpected or extended outages I expect mine to be back where it was in a few weeks.
15) Message boards : Number crunching : Welcome to the 18 Year Club! (Message 1904818)
Posted 11 days ago by Profile HAL9000
Post:
I'm off by 3 days, but Happy Birthday Me, WooHoo, Cheers!

Yes things have changed, About 8 months ago I fired up an old 133MHz cpu, and what pops up ... Seti3, LOL, if I could have got a network card to work I would have tried reporting the 1 task that was remaining :D

I have a HDD from an old system that still has stuff from when I was testing BOINC Alpha and the SET@home classic app. However it doesn't seem to have SETI Spy on it for some reason.
16) Message boards : Number crunching : Panic Mode On (108) Server Problems? (Message 1904815)
Posted 11 days ago by Profile HAL9000
Post:
I have ordered with Amazon a treadmill to exercise my legs. I received a big package containing the treadmill and a manual. The manual referred to an electric motor which I could not find in the package. Since it was on Sunday i coud not phone the firm to ask why. So I went to the website, found a blog and discovered that the model I had bought had no electric motor, only a rotating wheel. They had sent me the wrong manual. This happened often when, buying a computer or a printer you got also a manual. Now all you get is a leaflet which gives you some instructions in 20 languages. If you need a manual you have to search for it on the Web.
Tullio

Normally by the time a product hits the shelves the drivers and manuals have been updated at least once. Possibly a few times depending on test/dev cycles.
The printer company I previously worked for released their Linux drivers for CUPS and SANE so backward and future compatibility issues were not often an issue.
Some of the printer and multi-function devices had decent enough processors that could have run SETI@home, but I never got around ti giving it a go.
17) Message boards : Number crunching : Panic Mode On (108) Server Problems? (Message 1904277)
Posted 14 days ago by Profile HAL9000
Post:
Which, again, is in fact not the science database that runs informix .


Is this along with each's systems OS and primary DB documented anywhere?

You can check the Server Status for most of that information.
https://setiathome.berkeley.edu/show_server_status.php
18) Message boards : Number crunching : Panic Mode On (108) Server Problems? (Message 1904273)
Posted 14 days ago by Profile HAL9000
Post:
Since the issue is with the SETI@home science database and not the master or replica databases I'm not sure how how the deadlines would even be relevant.
Given the data is stored in the science database after it has been validated.

The reason for the serverside limits was due to the load on master database and it falling over or just plain getting bogged down.

That is correct. Either the MySQL database software or the hardware the BOINC master db system is using couldn't handle scanning a table of 11,000,000+ tasks several hundred, or thousand?, times a second.

Which, again, is in fact not the science database that runs informix .
19) Message boards : Number crunching : Panic Mode On (108) Server Problems? (Message 1904260)
Posted 14 days ago by Profile HAL9000
Post:
I too have wondered why SETI has stuck with the extremely long deadlines I assess were implemented for the original hardware used on the project. That kind of hardware is 18 years in the past and does not need to continue to be supported. I agree with you Jeff, I would expect the sizes of databases and the strain they put on the project would be greatly lessened if the deadlines were reduced by a month, lets say from the current 2 month deadline.

As I understand it, the reason there has been no adjustment is because Eric does not wish to disenfranchise anybody from participating in this project.

And that would include folks with very meager hardware resources. Not everybody can afford what some of us are able to.

That is why.

Since the issue is with the SETI@home science database and not the master or replica databases I'm not sure how how the deadlines would even be relevant.
Given the data is stored in the science database after it has been validated.
20) Message boards : Number crunching : Modest GPU upgrade suggestions? (Message 1904150)
Posted 14 days ago by Profile HAL9000
Post:
If you are looking at current models.
As mentioned the GeForce GTX 1050 or 1050 Ti are probably the best low cost performance options.
If even lower cost is desired the Radeon RX 550 or RX 560 would also work.

Older generation GPUs could possibly be found new or more likely used.


Next 20


 
©2017 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.