Posts by Dirk Sadowski


log in
1) Message boards : Number crunching : Is it possible to swap a guppi assigned to GPU with a Arecibo assigned to CPU? (Message 1799221)
Posted 28 Jun 2016 by Profile Dirk Sadowski
I don't want to throw oil on the fire.

It was discussed in the forum many times, rescheduling and the resulting screw up of the Credit granting.

Each app have his own 'average processing rate'. E.g. the server send a WU to the GPU, will be calculated on the GPU, maybe 10 minutes. An other WU which was send to your GPU will now be calculated on the CPU (because of the usage of a rescheduling tool), the server (CreditNew calculation) think the WU was calculated on the GPU and is confused because it lasts maybe 5 hours.
You could find the related threads after a forum search.

I don't want to give much tips...
Fred's rescheduler is still available in his forum for download (he made this tool before CreditNew was installed here at SETI@home). He have also a warning near the download URL that it 'may result in less credits, for you or your wing man'.
And an instruction is available in this forum to upgrade the tool for SETIv8.

I was in E-Mail contact inter alia with Eric (SETI@home Director) - long time ago as CreditNew was installed here,
I asked why they don't write 'please don't use rescheduler' in the forum, Eric replied (from my remembering) something like 'that would do/change nothing'.

Maybe if you don't trust my statements, maybe you don't have the E-Mail address of him, here is she.
2) Message boards : Number crunching : Is it possible to swap a guppi assigned to GPU with a Arecibo assigned to CPU? (Message 1799187)
Posted 28 Jun 2016 by Profile Dirk Sadowski
You don't need to create such a tool.

If you make a forum search with 'rescheduler' you will find such tool.

But, (after release of CreditNew) the admins aren't pleased about the usage of such tools, because it will screw up (the correct calculation of) the Credit granting for you and your wingmen (-> less Credits).
3) Message boards : Cafe SETI : Das Deutsche Cafe. The German Cafe. (Message 1798965)
Posted 27 Jun 2016 by Profile Dirk Sadowski
Hier wurde 'ne lange Zeit nichts geschrieben... ;-)
4) Message boards : Number crunching : Question Of Meaning = SETI Is Useful Currently : Yes Or No? (Message 1787020)
Posted 12 May 2016 by Profile Dirk Sadowski
I saw a TV show with inter alia Dr. Michio Kaku.

On his website you can read:
(...) So far, we see no hard evidence of signals from extra-terrestrial civilizations from any earth-like planet. The SETI project (the search for extra-terrestrial intelligence) has yet to produce any reproducible evidence of intelligent life in the universe from such earth-like planets, but the matter still deserves serious scientific analysis. The key is to reanalyze the objection to faster-than-light travel. (...)

(...) The current SETI project only scans a few frequencies of radio and TV emissions sent by a Type 0 civilization, but perhaps not an advanced civilization. Because of the enormous static found in deep space, broadcasting on a single frequency presents a serious source of error. Instead of putting all your eggs in one basket, a more efficient system is to break up the message and smear it out over all frequencies (e.g. via Fourier like transform) and then reassemble the signal only at the other end. In this way, even if certain frequencies are disrupted by static, enough of the message will survive to accurately reassemble the message via error correction routines. However, any Type 0 civilization listening in on the message on one frequency band would only hear nonsense. In other words, our galaxy could be teeming with messages from various Type II and III civilizations, but our Type 0 radio telescopes would only hear gibberish. (...)

(...) we are a Type 0 civilization, which extracts its energy from dead plants (oil and coal). Growing at the average rate of about 3% per year, however, one may calculate that our own civilization may attain Type I status in about 100-200 years, Type II status in a few thousand years, and Type III status in about 100,000 to a million years. These time scales are insignificant when compared with the universe itself. (...)

SETI project = SETI@home?


Which frequencies are searched through here at SETI@home and AstroPulse?
How SETI@home works.
It's still just a bit around 1420 MHz?


I don't understand very well what Dr. Michio Kaku mean. And Google Translator don't help much.
If I understood him 'correct', currently we can't find extra-terrestrial intelligence.
Maybe in a few thousand years with new/better equipment it would be possible?
My understanding is right?


What you think about this?


Thanks.
5) Message boards : Number crunching : GBT ('guppi') .vlar tasks will be send to GPUs, what you think about this? (Message 1784929)
Posted 5 May 2016 by Profile Dirk Sadowski
Here in the SETI-Beta thread I wrote what I think about this.

I thought a larger discussion (here) would be helpful.


I made my decision/statement...
Either...

  • an option in the project prefs for to un-/check 'GBT ('guppi') .vlar tasks to GPU' (so each member can decide to reduce or preserve the performance of the PC),
  • or I use a tool for to send GBT ('guppi') .vlar tasks from GPU to CPU (and screw up CreditNew),
  • or I search for a new primary project,
  • or I switch off my PCs.



Which opinion you have about the title/topic of this thread?

Thanks.

6) Message boards : Number crunching : 1.)MSI Afterburner doesn't start at Windows start up - why? 2.)FuryX downclock bug. (Message 1781590)
Posted 23 Apr 2016 by Profile Dirk Sadowski
MSI Afterburner (v4.2.0) doesn't start at Windows (8.1 Pro x64) start up...

I searched the web, but I'm not smarter...

(I need to start Afterburner with admin rights manually for correct function.
Until now I use this tool just for a 'better' fan curve.)

I check 'start with Windows' in the tool settings, but...
- or -
I check 'apply o/c at system startup' in the tool, but...
- or -
I copy a tool shortcut in the (*/normal_account/ (no admin rights)) 'Autostart' folder, but...
- or -
I copy a tool shortcut in the (C:/Autostart (admin rights?)) folder, but...
- or -
Over the task scheduler 'start at log on', but...

- it don't start automatically.

Why?

What I need to do that Afterburner start automatically?



Crimson 15.12 have a downclock bug (at least with my FuryX's).
Start of Windows and after a few minutes or a few days, one or two VGA cards downclock from 1050 to 300 MHz, up to 1050 again and down to 300 MHz again, and over again...
A reboot is needed to fix it... - to the time it happens again.

Crimson 16.3.2 have a 'power efficiency' point in the software (recommendation of the AMD support), I tested it 3 1/2 days and in this time the downclock doesn't happen.
I don't know if it fix the downclock bug, because sometimes it happen after 7 or more days...
But this software I couldn't use, because it make invalid AstroPulse results.


I need to use 15.12, but...
I checked in Afterburner:
disable ULPS
enabled force constant voltage

- and the downclock bug happens nevertheless.

Is there a way to make a work around (disable of power efficiency) that the FuryX's don't downclock?

Maybe in the registry (because I read here in the forum, that it's possible to disable ULPS there, but don't know how) or somewhere other?


Thanks.
7) Message boards : News : Breakthrough Listen data now flowing. (Message 1780421)
Posted 19 Apr 2016 by Profile Dirk Sadowski
Eric Korpela wrote:
The VLARs go out to ATI GPUs, but are held back from NVIDIA. If I could find a way to send VLAR to only NVIDIA OpenCL and not NVIDIA CUDA, I would...

I myself wrote:
The *guppi*.vlar's or also the normal .vlar's go to AMD/ATI GPUs?

The normal .vlar tasks lasts 4 times more, the *guppi*.vlar tasks lasts 3 times more - than a mid-AR task (on one of my four FuryX VGA cards) - (I'm a SETI-Beta tester).

If the AMD/ATI GPU PCs have good luck and get just this *guppi*.vlar tasks, their RAC will decrease /3, if also the normal .vlar tasks then the RAC will decrease /4. Not funny.

One of my FuryX calculate a (*guppi*).vlar task, in this time the card could calculate (3) 4 mid-AR tasks.

The nVIDIA GPUs don't get (*guppi*).vlar tasks...

It's not about Credits (only).
I (the most members here also) use the RAC for to compare (members/PCs/teams).

This would be like the AMD/ATI VGA card user do the 'dirty work' and the nVIDIA VGA cards are protected for them, that's like cherry-picking.
Fairness, equality?

If it ever would work, that the SETI server send the (*guppi*).vlar tasks to nVIDIA's OpenCL app and not to the CUDA app, the APR (average processing rate) of the OpenCL app will go so down, that the server 'use' just the CUDA app for the PC... with the result that no (*guppi*).vlar tasks will be send to the PC - or?


It's not possible to send the (*guppi*).vlar tasks just to CPUs?


I'm disappointed, I have set SETI in BOINC to 'no new tasks'.
I don't know when, or if I will set it again to 'allow new tasks'.
I'll follow the process and decide then...

I'm very sad (a hardcore SETIzen). :-(

I looked to other AMD/ATI VGA card PCs - if I looked correct they don't get the *guppi*.vlar tasks for their GPUs.

I set 'allow new tasks' again.

I don't know if it's really true what I saw... - if I'm wrong I set again 'no new tasks'. :-(
8) Message boards : News : Breakthrough Listen data now flowing. (Message 1779961)
Posted 17 Apr 2016 by Profile Dirk Sadowski
Eric Korpela wrote:
The VLARs go out to ATI GPUs, but are held back from NVIDIA. If I could find a way to send VLAR to only NVIDIA OpenCL and not NVIDIA CUDA, I would...


The *guppi*.vlar's or also the normal .vlar's go to AMD/ATI GPUs?

The normal .vlar tasks lasts 4 times more, the *guppi*.vlar tasks lasts 3 times more - than a mid-AR task (on one of my four FuryX VGA cards) - (I'm a SETI-Beta tester).

If the AMD/ATI GPU PCs have good luck and get just this *guppi*.vlar tasks, their RAC will decrease /3, if also the normal .vlar tasks then the RAC will decrease /4. Not funny.

One of my FuryX calculate a (*guppi*).vlar task, in this time the card could calculate (3) 4 mid-AR tasks.

The nVIDIA GPUs don't get (*guppi*).vlar tasks...

It's not about Credits (only).
I (the most members here also) use the RAC for to compare (members/PCs/teams).

This would be like the AMD/ATI VGA card user do the 'dirty work' and the nVIDIA VGA cards are protected for them, that's like cherry-picking.
Fairness, equality?

If it ever would work, that the SETI server send the (*guppi*).vlar tasks to nVIDIA's OpenCL app and not to the CUDA app, the APR (average processing rate) of the OpenCL app will go so down, that the server 'use' just the CUDA app for the PC... with the result that no (*guppi*).vlar tasks will be send to the PC - or?


It's not possible to send the (*guppi*).vlar tasks just to CPUs?


I'm disappointed, I have set SETI in BOINC to 'no new tasks'.
I don't know when, or if I will set it again to 'allow new tasks'.
I'll follow the process and decide then...

I'm very sad (a hardcore SETIzen). :-(
9) Message boards : Number crunching : CPU affinity tools? (Message 1776739)
Posted 6 Apr 2016 by Profile Dirk Sadowski
I have inter alia a board with two Xeon CPUs.
HT off.
So there are 6 Cores and 6 Cores.

It's possible to adjust with a CPU affinity tool following:
Core#0 and Core#5: MB8_win_x86_SSE2_OpenCL_ATi_HD5_r3330.exe and AP7_win_x86_SSE2_OpenCL_ATI_r2742.exe
Core#6 and Core#11: MB8_win_x86_SSE2_OpenCL_ATi_HD5_r3330.exe and AP7_win_x86_SSE2_OpenCL_ATI_r2742.exe
Core#1, #2, #3, #4: MB8_win_x64_AVX_VS2010_r3330.exe and AP7_win_x64_SSE3_CPU_r2692.exe
Core#7, #8, #9, #10: MB8_win_x64_AVX_VS2010_r3330.exe and AP7_win_x64_SSE3_CPU_r2692.exe
[just these apps possible on Core#x]

Or...

Adjust with a CPU affinity tool that following apps will be fixed at own Core each?
MB8_win_x86_SSE2_OpenCL_ATi_HD5_r3330.exe
AP7_win_x86_SSE2_OpenCL_ATI_r2742.exe
MB8_win_x64_AVX_VS2010_r3330.exe
AP7_win_x64_SSE3_CPU_r2692.exe


In both cases, 4 GPU and 8 CPU apps are running simultaneously in BOINC.


This case, or this, or one other, which CPU affinity tools are available (for free preferable ;-) ?

Thanks.
10) Message boards : Number crunching : Radeon Software Crimson (Message 1775933)
Posted 3 Apr 2016 by Profile Dirk Sadowski
Additional to all...

Because of VGA card driver uninstall and install... : Message 1733115.

The newest DDU you could get here (at the developer website): http://www.wagnardmobile.com/forums
11) Message boards : Number crunching : Radeon Software Crimson (Message 1775932)
Posted 3 Apr 2016 by Profile Dirk Sadowski
I myself wrote:
My four FuryX's (from PowerColor) PC is currently top host #5.
And this with just 1 WU/GPU.
More isn't possible with the currently driver.
Two Xeon's each with 6 CPU-Cores/12 threads, but HT off for faster GPU app calculation, so 12 CPU-Cores.
1 Core/GPU app, so 8 Cores crunch tasks.


BTW.
Crimson 15.12 is available. (at least for Win8.1 x64)
For some minutes installed, but it's the same v1912.5 driver like in Crimson v15.11 and v15.11.1 Beta.
So I guess still not 2+WUs/GPU possible, right?

RueiKe wrote:
I have been having trouble getting decent RAC with my latest build, FX-8370 with 2 Fury Nanos (powercolor). Both cards have an average loading of about 55%, where my single Fury X system is at about 85%. The RAC of the dual Nano system is significantly lower than the single Fury X. I have tried Crimson 15.12 and the latest 16.3.2, with no difference. I have tried many CPU/GPU per app configurations. I get errors with more than 1 per GPU, so I have settled with 1 task to 1 CPU and 1 GPU. Just curious if you faced this issue and how you overcame it for your 4 Fury X system.


It was a long way to find the best way... ;-)

- - - - - - - - - -
BTW.
I tested Crimson 16.3.2 for around 3 1/2 days, the result:
SETI results are OK.
AstroPulse results go invalid.

I'm back to Crimson 15.12.
- - - - - - - - - -

Like Mike mentioned already, SETI r3330 ATI app don't work well with default cpu_lock (at least at my system). All 4 GPU apps were fixed at Core#0.
(This could be the reason that your Fury Nano's have ~ 55 % GPU Load each.)
I need to use -no_cpu_lock in cmdline.txt file (more slightly further down).

You use the stock SETI@home apps.
You should/could go with opti apps, at least higher RAC for the CPUs (and just the correct/best/fastest GPU apps installed/used).
Example here (in the middle of the site). If you decided to go with opti apps, we will help you.


If you would like to go still with stock apps... :

(I tell you what I would do (if I would go with stock apps))

You should make an app_config.xml (on the bottom of the site) file with:
<app_config> <app> <name>setiathome_v7</name> <gpu_versions> <gpu_usage>1</gpu_usage> <cpu_usage>1</cpu_usage> </gpu_versions> </app> <app> <name>setiathome_v8</name> <gpu_versions> <gpu_usage>1</gpu_usage> <cpu_usage>1</cpu_usage> </gpu_versions> </app> <app> <name>astropulse_v7</name> <gpu_versions> <gpu_usage>1</gpu_usage> <cpu_usage>1</cpu_usage> </gpu_versions> </app> </app_config>

(I don't think there are SETIv7 tasks still around, but it's still possible to check it in the project prefs, so I included it.)

This make: 1 CPU-thread reserved for 1 GPU app (on this CPU-thread no CPU app/task (theoretically)).

My ap_cmdline_win_x86_SSE2_OpenCL_ATI.txt file in my setiathome.berkeley.edu project folder have inside:
-cpu_lock -instances_per_device 1 -unroll 18 -ffa_block 2830 -ffa_block_fetch 2830 -tune 1 64 4 1 -tune 2 64 4 1 -oclFFT_plan 256 16 256 -hp

My mb_cmdline_win_x86_SSE2_OpenCL_ATi_HD5.txt file in my setiathome.berkeley.edu project folder have inside:
-instances_per_device 1 -no_cpu_lock -sbs 512 -period_iterations_num 20 -spike_fft_thresh 4096 -tune 1 64 1 4 -oclfft_tune_gr 256 -oclfft_tune_lr 16 -oclfft_tune_wg 256 -oclfft_tune_ls 512 -oclfft_tune_bn 64 -oclfft_tune_cw 64 -hp

(With stock apps, the .TXT files could have the same name.
But you could have more (a few) .TXT files for SETI (MB) apps.)

This cmdline settings should go with your FuryX, could be tested on your Fury Nano's.
12) Message boards : Number crunching : Radeon Software Crimson (Message 1774933)
Posted 29 Mar 2016 by Profile Dirk Sadowski
FYI

Crimson 16.3.2 - (NO Hotfix/Beta) is available...

http://support.amd.com/en-us/kb-articles/Pages/AMD-Radeon-Software-Crimson-Edition-16-3-2.aspx

;-)
13) Message boards : Number crunching : Radeon Software Crimson (Message 1772697)
Posted 19 Mar 2016 by Profile Dirk Sadowski
FYI

Crimson 16.3.1 Hotfix (Beta) is available...

http://support.amd.com/en-us/kb-articles/Pages/AMD_Radeon_Software_Crimson_Edition_16.3.1.aspx

;-)
14) Message boards : Number crunching : Radeon Software Crimson (Message 1770798)
Posted 10 Mar 2016 by Profile Dirk Sadowski
Chris Adamek wrote:
You should give one or both of the new apps just put out for testing (see the OpenCL NV Multibeam v8 edition for Windoes thread) as Raistmer has put out a couple of new ATI variants that should better utilize all the compute units in the cards during pulsefind. Might help you get a little more production out of your Fury's even running 1 wu at a time... Plus I'm curious to see how high end ATI cards like the new apps lol. If the early beta results are any indication the SoG version might be slower than the APU versions and the non-SoG ATI5 version but very few people have run it so time will tell which is fastest...

Chris

Until now I didn't read this thread you mentioned, because of the 'NV' in the title.

I didn't know that in this thread are also AMD/ATI apps...

Please could you give me the URL of the message in this thread which mention the (latest/newest) AMD/ATI apps (URL for download)? ...because it's very long thread.

Thanks.

(Before I test the apps, I'll test the 2 WUs/GPU with Crimson 16.3 - in it is a new driver v2004.6.
I tested the AMD/ATI SoG app at SETI-Beta in past, but it needed 1 1/3 CPUs. The CPU time was higher than the whole calculation time.)
15) Message boards : Number crunching : Radeon Software Crimson (Message 1770659)
Posted 10 Mar 2016 by Profile Dirk Sadowski
Crimson 16.3 Hotfix (Beta) is available...

http://support.amd.com/en-us/kb-articles/Pages/AMD_Radeon_Software_Crimson_Edition_16.3.aspx

I'll test it tomorrow (if simultaneously tasks possible)...

Maybe someone other is curious and will test it before me? ;-)
16) Message boards : Number crunching : After Windows Update No Log-In Possible. (Message 1769695)
Posted 5 Mar 2016 by Profile Dirk Sadowski
Thanks.

After a long web search and long telephone call for trouble shooting we created two new accounts.

http://www.pcwelt.de/ratgeber/Defekte_Windows-Benutzerkonten_im_Griff-PC-Notfaelle-7834137.html
(...)
Zunächst starten Sie Windows 8 über das Symbol rechts unten auf dem Anmeldebildschirm mit „Neu starten“ bei gedrückter Umschalt-Taste neu. Im angezeigten Vorab-Bootmenü wählen Sie „Problembehandlung ➞ Erweiterte Optionen ➞ Starteinstellungen ➞ Neu starten“ aus. Danach startet das System neu, und Sie kommen mit der F6-Taste zum abgesicherten Modus mit Eingabeaufforderung.
(...)


Google Translator say:
First start Windows 8 over the icon at the bottom right on the login screen with "Restart" Hold down the Shift key again. In pre-boot menu that appears, select "Troubleshooting ➞ Advanced Options ➞ Start settings ➞ Restart" from. After the system reboots, and join the F6 key to safe mode with command prompt.


But he pressed (F)4 for 'normal' safe mode.

Created two new accounts and after reboot into 'normal' Windows it worked like before.
(He need to set up his Desktop like it was in past.)

(Some strange was there, during the 1st Windows installation, my friend made an online account with outlook E-Mail.
I had to delete the HDD and install Windows a 2nd time (because the PC was unusable in past) and I created two (admin and user) local accounts.
For a few days the PC wanted the 1st online account PIN for to log-in (maybe because of the E-Mail Software which is in Windows?).

No matter, now the PC is again usable.
17) Message boards : Number crunching : After Windows Update No Log-In Possible. (Message 1769678)
Posted 5 Mar 2016 by Profile Dirk Sadowski
A friend installed today Windows (8.1 x64) Updates.

He made a reboot - he see now the log-in screen, but there is nothing except on the bottom right corner the power icon, with switch off, stand-by and reboot option.

He had two accounts, admin and user.

Where are the accounts now?

Currently he can't use the PC (if he can't log-in).

Is there a trick to come into Windows and create again a new account?

Thanks.
18) Message boards : Number crunching : Radeon Software Crimson (Message 1769276)
Posted 3 Mar 2016 by Profile Dirk Sadowski
Crimson 16.2.1 Hotfix (Beta, .EXE from Feb/27) is available...

And, no, still not possible to let run 2 WUs/GPU - errors (at least on my FuryX's).

It's sad, annoying... IIRC, the FuryX is available since 2015/06, I let run them since ~ 5 months - and the driver is still buggy... - the RAC (performance) could be much higher...
19) Message boards : Number crunching : Radeon Software Crimson (Message 1769012)
Posted 2 Mar 2016 by Profile Dirk Sadowski
I tested 2 WUs/GPU with 'default' settings - with Crimson 16.2.

After ~ 4 hours the 1st error.
The computation times vary a lot.
Same AR, some results after ~ 10 mins or ~ 1 hour.

Still not possible to let run 2+ WUs/GPU (at least on my FuryX's. :-(

With 1 WU/GPU the GPU Load go up and down, ~45% - ~99%.

The RAC could be much higher...


Maybe I will let the Vulkan Software a try...
20) Message boards : Number crunching : VLARs now also sent to CUDA app? (Message 1769011)
Posted 2 Mar 2016 by Profile Dirk Sadowski
Ulrich Metzner wrote:
Have a look at the AR:
"WU true angle range is : 0.080614"

This WU ran nearly "forever" compared to other WUs and i had a lot of lags while this was running. Is this a new adjustment to the server routine?


Richard Haselgrove wrote:

Yes, that matches the discussion and conclusion we reached a week ago. A small arithmetic error in preparing the splitters to handle Green Bank (and other) telescope data shifted the threshhold for definition as a VLAR down by 50% - from 0.12 down to 0.06 (see Panic Mode On (102) Server Problems?)

Eric did reply "I'll fix it during this week's outage", but evidently something intervened and it dropped off the ToDo list. I'll remind him tomorrow, closer to the likely timeframe for action. (Today is a Federal Holiday - Presidents' Day - in the USA, so no point in writing today.)


FYI

My PC still get/got a few ARs <0.12 for the AMD/ATI GPU app (examples):

0.08x
29ja10aa.19856.74043.4.31.195_0
Created 2 Mar 2016, 3:20:51 UTC
Sent 2 Mar 2016, 7:19:26 UTC

0.09x
29ja10aa.19856.75270.4.31.229_1
Created 2 Mar 2016, 3:26:04 UTC
Sent 2 Mar 2016, 7:24:48 UTC

29ja10aa.19856.75270.4.31.233_1
Created 2 Mar 2016, 3:26:04 UTC
Sent 2 Mar 2016, 7:24:48 UTC


Next 20

Copyright © 2016 University of California