Welcome to MilkyWay@home

Posts by Starfire

21) Message boards : News : windows intelx86 and x86_64 binaries added for the nbody simulations (Message 41579)
Posted 19 Aug 2010 by Starfire
Post:
How do I get this file?


This should do it: Link
22) Message boards : Number crunching : CAT 10.2 ..not working.. (Message 36693)
Posted 21 Feb 2010 by Starfire
Post:
So far I haven't run in any problems with Catalyst 10.2 on Windows 7 Ultimate x64.
23) Message boards : Number crunching : Disable CPU-tasks (Message 35801)
Posted 18 Jan 2010 by Starfire
Post:
There are ways to adjust the behavior of the ATI application (developed by Cluster Physik) used here. They're however not trivial.
They're several command line parameters you can adjust to configure the GPU utilization. Basically you need to use something called anonymous platform. This however means that you've to set up everything manual, e.g. if the project releases a new application you've to download it manually and edit the configuration file to enable it. That means you need to monitor the project to find out when changes are necessary. If you just want to set and forget I would strongly advise against it.

If you still want to continue:
1) Download Cluster Physiks application package
here
2) Unzip it to a temporary location
3) read the included readme.txt
4) Quit BOINC
5) Copy everything from the Win64_Ati-subfolder to your milkyway directory (probably C:\ProgramData\BOINC\projects\milkyway.cs.rpi.edu_milkyway)
6) edit the app_info.xml file to set your options. As a starting point the content of mine:

<app_info>
 <app>
  <name>milkyway</name>
  <user_friendly_name>Milkyway@Home</user_friendly_name>
 </app>
 <file_info>
  <name>astronomy_0.20b_ATI_x64_ati.exe</name>
  <executable/>
 </file_info>
 <file_info>
  <name>brook64.dll</name>
  <executable/>
 </file_info>
 <app_version>
  <app_name>milkyway</app_name>
  <version_num>21</version_num>
    <flops>1.0e11</flops>
    <avg_ncpus>0.05</avg_ncpus>
    <max_ncpus>1</max_ncpus>
    <coproc>
      <type>ATI</type>
      <count>1</count>
    </coproc>
    <plan_class>ati13ati</plan_class>
    <cmdline>w1.3</cmdline>
  <file_ref>
   <file_name>astronomy_0.20b_ATI_x64_ati.exe</file_name>
   <main_program/>
  </file_ref>
  <file_ref>
   <file_name>brook64.dll</file_name>
  </file_ref>
 </app_version>
</app_info>


This is the part you need no change to keep the system more responsive. Your system should become more responsive when you raise the value (standard is: w1.0):
<cmdline>w1.3</cmdline>
Everytime you want to change the value you have to stop BOINC, change it and start BOINC again.

7) Start BOINC
24) Message boards : News : Need a sample app_info.xml (Message 35785)
Posted 18 Jan 2010 by Starfire
Post:
Yay, it's working - thank you very much.

That was one of the only differences between my Milkyway and Collatz setup (the only one I didn't change because I never suspected it). I've disabled the fractional GPU jobs on Milkyway (coproc_count=1) for the time being. Now everything is working like it used to be.
I guess we'll have to wait until it's fixed by the BOINC devs in the next server version.
25) Message boards : News : Need a sample app_info.xml (Message 35778)
Posted 18 Jan 2010 by Starfire
Post:
I've tried several modifications on my own since the problem started - none of them helped.

I started out with:
<app_info>
 <app>
 <name>milkyway</name>
 <user_friendly_name>Milkyway@Home</user_friendly_name>
 </app>
 <file_info>
  <name>astronomy_0.20b_ATI_x64_ati.exe</name>
  <executable/>
 </file_info>
 <file_info>
  <name>brook64.dll</name>
  <executable/>
 </file_info>

 <app_version>
  <app_name>milkyway</app_name>
  <version_num>20</version_num>
    <flops>1.0e11</flops>
    <avg_ncpus>0.05</avg_ncpus>
    <max_ncpus>1</max_ncpus>
    <coproc>
      <type>ATI</type>
      <count>0.32</count>
    </coproc>
    <cmdline>w1.3</cmdline>
  <file_ref>
   <file_name>astronomy_0.20b_ATI_x64_ati.exe</file_name>
   <main_program/>
  </file_ref>
  <file_ref>
   <file_name>brook64.dll</file_name>
  </file_ref>
 </app_version>

</app_info>


In the first attempt I changed the version to 21. When that didn't help I manually added the planclass without success.
This is what I'm using now:

<app_info>
 <app>
 <name>milkyway</name>
 <user_friendly_name>Milkyway@Home</user_friendly_name>
 </app>
 <file_info>
  <name>astronomy_0.20b_ATI_x64_ati.exe</name>
  <executable/>
 </file_info>
 <file_info>
  <name>brook64.dll</name>
  <executable/>
 </file_info>

 <app_version>
  <app_name>milkyway</app_name>
  <version_num>21</version_num>
  <plan_class>ati13ati</plan_class>
    <flops>1.0e11</flops>
    <avg_ncpus>0.05</avg_ncpus>
    <max_ncpus>1</max_ncpus>
    <coproc>
      <type>ATI</type>
      <count>0.32</count>
    </coproc>
    <cmdline>w1.3</cmdline>
  <file_ref>
   <file_name>astronomy_0.20b_ATI_x64_ati.exe</file_name>
   <main_program/>
  </file_ref>
  <file_ref>
   <file_name>brook64.dll</file_name>
  </file_ref>
 </app_version>

</app_info>


Apart from some minor differences (filenames, cpu-proc-count, version number) there are identically to the ones I use for Collatz, where they strangely work.
26) Message boards : Number crunching : Server down twice today?? (Message 35670)
Posted 15 Jan 2010 by Starfire
Post:
What makes it work for you are propably these two options

<zero_debts>1</zero_debts>
<report_results_immediately>1</report_results_immediately>

Boinc keeps track of how much CPU time projects have used in comparison with their resource share by maintaining debt values for each project. By these values it determines which CPU projects will run next and which project will download CPU workunits next.
Since the server change Milkyway only gives out work to users using app_info.xml when the client requests CPU work. Direct requests for GPU(ATI) work are always answered with "No work sent". Before the change ATI work requests where answered with new WUs if the cache was not full.
If you are using multiple projects you run into the problem that the BOINC client may only request CPU WUs for Milkyway in small doses or none at all if its CPU debts are too high even though your ATI card is idle.
<zero_debts> will clear these debts across all projects every time the client is restarted. So after every restart each projects has the same priority in getting CPU work which makes it more likely for BOINC to ask for CPU WUs from Milkyway.

This seems to be a configuration problem on the server since Collatz is using the same server version (611) and doesn't suffer from this. Lets hope it will get fixed soon.
27) Message boards : Number crunching : Server down twice today?? (Message 35510)
Posted 11 Jan 2010 by Starfire
Post:
I use the command line setting to keep the system more responsive and to be able to view videos without the need to stop Milkyway. So I don't want to use the automatic download either. However I don't really want to go back to all that hassle before 6.10 was released. I'm still hoping Travis will be able to change the current behavior.
Right now I've to go through these 85 Collatz tasks I downloaded to test their scheduler response to the ATI work request. So I'll wait and see what happens.
28) Message boards : Number crunching : Server down twice today?? (Message 35507)
Posted 11 Jan 2010 by Starfire
Post:
If you are using the ATI app_info.xml version the upgraded server now treats the anonymous platform as a CPU. You need to tick "Use CPU" in MilkyWay preferences. Otherwise BOINC will continue to ask for GPU tasks only and not receive any.


Thanks for pointing this out.
However with several other CPU projects running BOIC now will only ask for more Milkyway-CPU-work after it has run dry - and probably only as long as I continuously raise it's resource share because of increasing STD and LTD.

Limiting anonymous platform to CPU doesn't make sense to me. Is that also done that way at Collatz? I'm using anonymous platform there too and never had to play with my resource share to get work.

Edit: I just tried Collatz again. Using anonymous platform BOINC requested 259200 secs of ATI work and got 85 tasks. Milkyway is still only giving out work when being asked for CPU - which only happens once in a while. Both projects appear to use server version 611 according to the scheduler reply.
29) Message boards : Number crunching : Sudden mass of WU's finishing with Computation Error (Message 34120)
Posted 2 Dec 2009 by Starfire
Post:
Can someone please suspend network activity for one WU and look into the result file of the finished WU to see what this "fitness" thing is good for? If fitness on a valid WU is set to -1 too then it means nothing, I think.


The following results were calculated using Gipsels ATI app - fitness is displaying a real number here:

de_s222_3s_best_1p_01r_44
parameters [20]: 0.726530534475273 1.000000000000000 -11.309963264750689 164.068245039415330 29.351026000962452 3.773916232705108 1.607818178975123 1.291489947920174 -17.570005048174835 158.561785668195650 18.510896578133526 5.738129192817610 3.323711933363694 11.394196875578736 2.936906508509978 162.759205639023720 0.700000000000000 1.444900940888767 0.408269541430983 14.596364746148591
metadata: i: 77
fitness: -3.200465856044408
Gipsel_GPU_CAL_0.20_x64: 0.20


de_s222_3s_best_1p_01r_44
parameters [20]: 0.968326917012557 1.000000000000000 -10.203487737339231 164.345084867324940 25.920729630235499 5.304565981764101 2.004622029391751 7.127507855253272 -16.032826229817438 154.840719713304740 11.483539537133694 3.739142191627291 3.987127183052219 10.319835656129992 1.401691284083597 162.058382692022750 12.793184654502657 0.833880293137536 0.817510569264601 16.330915579064580
metadata: i: 97
fitness: -3.231483990977578
Gipsel_GPU_CAL_0.20_x64: 0.20


de_s222_3s_best_1p_01r_44
parameters [20]: 1.000000000000000 1.055320290988556 -10.887774134384429 180.667161994741240 32.615322424742459 5.778394578605021 1.360893960164031 4.648841479380868 -15.579053670534684 159.303785370296170 19.866325091491856 3.582786323103195 3.739731946757967 12.959971223927784 -0.576617745668031 156.690938802085500 0.700000000000000 1.326891535596566 1.348254152737073 14.256789232543523
metadata: i: 98
fitness: -3.197918134189094
Gipsel_GPU_CAL_0.20_x64: 0.20
30) Message boards : Number crunching : astronomy_020.ATI_x64 problems (Message 31466)
Posted 24 Sep 2009 by Starfire
Post:
Hi,
Your app_info.xml is OK - these errors sometimes occur because of a bug in the 6.10.* Boinc clients.
The new version 6.10.7 - available here - should fix this.
31) Message boards : Number crunching : astronomy_020.ATI_x64 problems (Message 31460)
Posted 24 Sep 2009 by Starfire
Post:
Hi,

glad I could help.
This limit is set by the project - you can only have 6 WUs per CPU core downloaded at any time. New tasks will be downloaded when you complete and upload some of them.
32) Message boards : Number crunching : astronomy_020.ATI_x64 problems (Message 31446)
Posted 24 Sep 2009 by Starfire
Post:
Ausnahmecode 0xc0000135


Hi,

this indicates that the application could not be initialized.

Did you copy and(!) rename the CAL-DLLs (this is necessary for Catalyst 9.2 and newer) in the Windows-System directories - simply renaming them is not enough.
If not do the following:
1. Open command prompt as Administrator
2. execute "cd %systemroot%\system32"
3. execute "copy atical*.dll amdcal*.dll"
4. execute "cd %systemroot%\SysWOW64"
5. execute "copy atical*.dll amdcal*.dll"

Now you should have the following files:
System32: amdcalrt64.dll,amdcalcl64.dll,amdcaldd64.dll,aticalrt64.dll,
aticalcl64.dll,aticaldd64.dll
SysWOW64: amdcalrt.dll,amdcalcl.dll,amdcaldd.dll,aticalrt.dll,
aticalcl.dll,aticaldd.dll

You've to repeat this procedure anytime you update the Catalyst drivers.

If you already did this, please check if you have the Visual Studio C++ runtimes (2005 and maybe 2008) installed.

Starfire


Previous 20

©2024 Astroinformatics Group