New AstroPulse for GPU ( ATi & NV) released (r1316)

Message boards : Number crunching : New AstroPulse for GPU ( ATi & NV) released (r1316)
Message board moderation

To post messages, you must log in.

Previous · 1 . . . 5 · 6 · 7 · 8 · 9 · 10 · 11 · Next

AuthorMessage
Claggy
Volunteer tester

Send message
Joined: 5 Jul 99
Posts: 4654
Credit: 47,537,079
RAC: 4
United Kingdom
Message 1262159 - Posted: 19 Jul 2012, 9:08:18 UTC - in response to Message 1262156.  

Thanks Claggy I've corrected this but I'm still getting 19/07/2012 8:54:02 p.m. SETI@home [error] State file error: missing application file AP6_win_x86_SSE2_OpenCL_NV_r1316 in message log

There are two places in the app_info where AP6_win_x86_SSE2_OpenCL_NV_r1316.exe is mentioned, make sure both are correct, then shut down Boinc, restore the files from the download, and restart Boinc,

Claggy
ID: 1262159 · Report as offensive
Richard Haselgrove Project Donor
Volunteer tester

Send message
Joined: 4 Jul 99
Posts: 14649
Credit: 200,643,578
RAC: 874
United Kingdom
Message 1262160 - Posted: 19 Jul 2012, 9:08:33 UTC - in response to Message 1262153.  

Thanks Richard. File is no longer in transfer tab :) How ever in my message log I'm getting
SETI@home[error] State file error: missing application file AP6_win_x86_SSE2_OpenCL_NV_r1316 Have I missed something or is this line ok?

Provided you have corrected every reference to that file, and the text string (every occurrence) in app_info matches the true file name, you should be good to go. You might get that error line once at startup, as BOINC cleans itself up after the previous mistake.

The fact that you told Claggy you're 'still' seeing the error message suggests that one or more typos still exists in the app_info file.
ID: 1262160 · Report as offensive
Speedy
Volunteer tester
Avatar

Send message
Joined: 26 Jun 04
Posts: 1639
Credit: 12,921,799
RAC: 89
New Zealand
Message 1262327 - Posted: 19 Jul 2012, 21:51:10 UTC

Thanks Richard & Claggy. I fixed it. I was completely missing 1 <file_info>
<name>AP6_win_x86_SSE2_OpenCL_NV_r1316.exe</name>
<executable/>
</file_info> I've learnt a lesson read forum posts properly & don't try & hurry when editing app info files
ID: 1262327 · Report as offensive
rob smith Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer moderator
Volunteer tester

Send message
Joined: 7 Mar 03
Posts: 22160
Credit: 416,307,556
RAC: 380
United Kingdom
Message 1262408 - Posted: 20 Jul 2012, 5:40:35 UTC

Not so much an error as a "behavioural" comment.
While running a "mixed load" (1MB, 1AP) on my GPU the time to go, and progress appear to increment smoothly, however when the GPU is running 2AP the time to go and progress increment in a strange manner - time_to_go slowly increases for a few minute, then suddenly takes a dive, at the same time progress is frozen, suddenly taking a leap up, the two being synchronised and very confusing....
Bob Smith
Member of Seti PIPPS (Pluto is a Planet Protest Society)
Somewhere in the (un)known Universe?
ID: 1262408 · Report as offensive
Profile BilBg
Volunteer tester
Avatar

Send message
Joined: 27 May 07
Posts: 3720
Credit: 9,385,827
RAC: 0
Bulgaria
Message 1262521 - Posted: 20 Jul 2012, 13:19:53 UTC - in response to Message 1262408.  

... time_to_go slowly increases for a few minute, then suddenly takes a dive, at the same time progress is frozen, suddenly taking a leap up, the two being synchronised and very confusing....

Not confusing but logical and normal.

AP on GPU update the 'Progress' once per a few minutes (maybe to not slow the processing), everytime about +0.9 % is added to 'Progress'
While the 'Progress' do not move BOINC 'thinks' the app is stuck so "time_to_go slowly increases for a few minute"
Then at once a 'huge' +0.9 % is added to 'Progress' and "time_to_go suddenly takes a dive"


 


- ALF - "Find out what you don't do well ..... then don't do it!" :)
 
ID: 1262521 · Report as offensive
Topher

Send message
Joined: 23 May 99
Posts: 36
Credit: 12,655,451
RAC: 0
Australia
Message 1262814 - Posted: 21 Jul 2012, 3:21:21 UTC

A quick question from a first time manually editing app_info n00b.

Do I replace the existing AP details with the details for the CUDA AP or add them as additional settings? I added the NVidia samples provided by others here to my app_info file and the event log doesn't report any errors but new AP WU's are still being crunched by CPU so I'm guessing I should have replaced the existing AP CPU settings instead.
ID: 1262814 · Report as offensive
Horacio

Send message
Joined: 14 Jan 00
Posts: 536
Credit: 75,967,266
RAC: 0
Argentina
Message 1262859 - Posted: 21 Jul 2012, 7:09:03 UTC - in response to Message 1262814.  

A quick question from a first time manually editing app_info n00b.

Do I replace the existing AP details with the details for the CUDA AP or add them as additional settings? I added the NVidia samples provided by others here to my app_info file and the event log doesn't report any errors but new AP WU's are still being crunched by CPU so I'm guessing I should have replaced the existing AP CPU settings instead.


Nope. Unless you want to stop crunching them on CPU.
The WUs that you already had that were assigned to the CPU will be crunched on CPU. If your GPU version of the app is ok in the ap_info, eventually, you will get new WUs that will be assigned to the GPU, but only when BOINC thinks that needs work for the GPU (and only if there are available AP WUs, obviously).

If you delete the CPU version the already assigned WUs will be deleted from your host... (And it seems that for some reason they might not be resent to the GPU. I did it on one of my hosts hoping to re-get them assigned on the GPU but instead they were all cancelled and marked as "out of time").

It's also possible that there is something wrong in the ap_info, not serious enough to throw an error, if you want to be sure, post here the ap_info section you added so we can see if it's ok.

ID: 1262859 · Report as offensive
Profile [AF>EDLS] Polynesia
Volunteer tester
Avatar

Send message
Joined: 1 Apr 09
Posts: 54
Credit: 5,361,172
RAC: 0
France
Message 1262908 - Posted: 21 Jul 2012, 11:57:21 UTC

Hello,

I find it hard to have units .. one that is downloadable at this time is not near start with a download speed of not even 2 kbps ...


Alliance Francophone
ID: 1262908 · Report as offensive
Profile Fred J. Verster
Volunteer tester
Avatar

Send message
Joined: 21 Apr 04
Posts: 3252
Credit: 31,903,643
RAC: 0
Netherlands
Message 1262945 - Posted: 21 Jul 2012, 14:52:07 UTC - in response to Message 1262908.  
Last modified: 21 Jul 2012, 15:10:00 UTC

Hello,

I find it hard to have units .. one that is downloadable at this time is not near start with a download speed of not even 2 kbps ...

[As of 21 Jul 2012 | 14:30:09 UTC] there are AstroPulse Units again,
total channels to do:	MB=264	AP=55.

You have 1 AstroPulse Unit on your computer, I hope, 2 errored while downloading and 1 (also D'Load Error) Exit status -186 (0xffffffffffffff46) ERR_RESULT_DOWNLOAD?!

Don't know why you aborted almost all MB work? (Error=768)
This isn't helpfull in getting new work, wheter it maybe MB and/or AstroPulse.
You can try to leave out MB work in your account preferences, always better
then aborting them!

Third option in preferences:
Run only the selected applications	SETI@home Enhanced
Astropulse v505 Y/N
SETI@home v7    Y/N
AstroPulse v6   Y/N
If no work for selected applications is available, accept work from other applications?	Y/N 

ID: 1262945 · Report as offensive
Profile [AF>EDLS] Polynesia
Volunteer tester
Avatar

Send message
Joined: 1 Apr 09
Posts: 54
Credit: 5,361,172
RAC: 0
France
Message 1262988 - Posted: 21 Jul 2012, 16:58:43 UTC

I had an abortion because the download is very long ...

In my preferences I put yes to everything in CPU / GPU


Alliance Francophone
ID: 1262988 · Report as offensive
Profile Mike Special Project $75 donor
Volunteer tester
Avatar

Send message
Joined: 17 Feb 01
Posts: 34253
Credit: 79,922,639
RAC: 80
Germany
Message 1263030 - Posted: 21 Jul 2012, 18:14:15 UTC

You have 762 errors.
Lots of them marked as aborted by user.

Try to retry early in the morning.
Thats the best you can do.



With each crime and every kindness we birth our future.
ID: 1263030 · Report as offensive
Topher

Send message
Joined: 23 May 99
Posts: 36
Credit: 12,655,451
RAC: 0
Australia
Message 1263179 - Posted: 22 Jul 2012, 1:24:52 UTC - in response to Message 1262859.  

A quick question from a first time manually editing app_info n00b.

Do I replace the existing AP details with the details for the CUDA AP or add them as additional settings? I added the NVidia samples provided by others here to my app_info file and the event log doesn't report any errors but new AP WU's are still being crunched by CPU so I'm guessing I should have replaced the existing AP CPU settings instead.


Nope. Unless you want to stop crunching them on CPU.
The WUs that you already had that were assigned to the CPU will be crunched on CPU. If your GPU version of the app is ok in the ap_info, eventually, you will get new WUs that will be assigned to the GPU, but only when BOINC thinks that needs work for the GPU (and only if there are available AP WUs, obviously).

If you delete the CPU version the already assigned WUs will be deleted from your host... (And it seems that for some reason they might not be resent to the GPU. I did it on one of my hosts hoping to re-get them assigned on the GPU but instead they were all cancelled and marked as "out of time").

It's also possible that there is something wrong in the ap_info, not serious enough to throw an error, if you want to be sure, post here the ap_info section you added so we can see if it's ok.

Thanks Horacio, I woke up this morning and had 4 CUDA AP's downloaded so I was just being impatient it seems.
ID: 1263179 · Report as offensive
Profile BilBg
Volunteer tester
Avatar

Send message
Joined: 27 May 07
Posts: 3720
Credit: 9,385,827
RAC: 0
Bulgaria
Message 1263187 - Posted: 22 Jul 2012, 2:01:07 UTC - in response to Message 1262988.  
Last modified: 22 Jul 2012, 2:03:44 UTC

I had an abortion because the download is very long ...


http://setiathome.berkeley.edu/forum_thread.php?id=68679&postid=1260962#1260962

P.S.
Did you remove -instances_per_device 1 ?


 


- ALF - "Find out what you don't do well ..... then don't do it!" :)
 
ID: 1263187 · Report as offensive
Profile [AF>EDLS] Polynesia
Volunteer tester
Avatar

Send message
Joined: 1 Apr 09
Posts: 54
Credit: 5,361,172
RAC: 0
France
Message 1263267 - Posted: 22 Jul 2012, 8:13:40 UTC - in response to Message 1263187.  

NO


Alliance Francophone
ID: 1263267 · Report as offensive
Claggy
Volunteer tester

Send message
Joined: 5 Jul 99
Posts: 4654
Credit: 47,537,079
RAC: 4
United Kingdom
Message 1263315 - Posted: 22 Jul 2012, 11:48:10 UTC - in response to Message 1263267.  

NO


Then remove it, that parameter isn't required any more,

Claggy
ID: 1263315 · Report as offensive
Profile [AF>EDLS] Polynesia
Volunteer tester
Avatar

Send message
Joined: 1 Apr 09
Posts: 54
Credit: 5,361,172
RAC: 0
France
Message 1263422 - Posted: 22 Jul 2012, 17:51:50 UTC
Last modified: 22 Jul 2012, 18:01:36 UTC

ok thanks

edit :

hoping that the calculation error will not go in for this unit here since that long to be downloaded ...

Seti's servers are really lagging behind ...

In addition I also try to have enchanded CPUs and still nothing that GPU 6.10




<app_info>
<app>
<name>astropulse_v6</name>
</app>
<file_info>
<name>AP6_win_x86_SSE2_OpenCL_NV_r1316.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>astropulse_v6</app_name>
<version_num>604</version_num>
<avg_ncpus>0.04</avg_ncpus>
<max_ncpus>0.2</max_ncpus>
<platform>windows_intelx86</platform>
<plan_class>cuda</plan_class>
<cmdline>-unroll 10 -ffa_block 6144 -ffa_block_fetch 1536 -sbs 256</cmdline>
<coproc>
<type>CUDA</type>
<count>0.5</count>
</coproc>
<file_ref>
<file_name>AP6_win_x86_SSE2_OpenCL_NV_r1316.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app_version>
<app_name>astropulse_v6</app_name>
<version_num>604</version_num>
<avg_ncpus>0.04</avg_ncpus>
<max_ncpus>0.2</max_ncpus>
<platform>windows_x86_64</platform>
<plan_class>cuda</plan_class>
<cmdline>-instances_per_device 1 -unroll 10 -ffa_block 6144 -ffa_block_fetch 1536 -sbs 256</cmdline>
<coproc>
<type>CUDA</type>
<count>0.5</count>
</coproc>
<file_ref>
<file_name>AP6_win_x86_SSE2_OpenCL_NV_r1316.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app>
<name>setiathome_enhanced</name>
</app>
<file_info>
<name>AK_v8b2_win_x64_SSE41.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>603</version_num>
<platform>windows_intelx86</platform>
<file_ref>
<file_name>AK_v8b2_win_x64_SSE41.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>603</version_num>
<platform>windows_x86_64</platform>
<file_ref>
<file_name>AK_v8b2_win_x64_SSE41.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app>
<name>astropulse_v6</name>
</app>
<file_info>
<name>ap_6.01r557_SSE2_331_AVX.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>astropulse_v6</app_name>
<version_num>601</version_num>
<platform>windows_intelx86</platform>
<file_ref>
<file_name>ap_6.01r557_SSE2_331_AVX.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app_version>
<app_name>astropulse_v6</app_name>
<version_num>601</version_num>
<platform>windows_x86_64</platform>
<file_ref>
<file_name>ap_6.01r557_SSE2_331_AVX.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app>
<name>astropulse_v505</name>
</app>
<app_version>
<app_name>astropulse_v505</app_name>
<version_num>505</version_num>
<platform>windows_intelx86</platform>
<cmdline>-v505</cmdline>
<file_ref>
<file_name>ap_6.01r557_SSE2_331_AVX.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app_version>
<app_name>astropulse_v505</app_name>
<version_num>505</version_num>
<platform>windows_x86_64</platform>
<cmdline>-v505</cmdline>
<file_ref>
<file_name>ap_6.01r557_SSE2_331_AVX.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app>
<name>setiathome_enhanced</name>
</app>
<file_info>
<name>Lunatics_x40_Win32_Cuda40.exe</name>
<executable/>
</file_info>
<file_info>
<name>cudart32_40_17.dll</name>
<executable/>
</file_info>
<file_info>
<name>cufft32_40_17.dll</name>
<executable/>
</file_info>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>610</version_num>
<platform>windows_intelx86</platform>
<plan_class>cuda_fermi</plan_class>
<avg_ncpus>0.040000</avg_ncpus>
<max_ncpus>0.040000</max_ncpus>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
<file_ref>
<file_name>Lunatics_x40_Win32_Cuda40.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart32_40_17.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft32_40_17.dll</file_name>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>609</version_num>
<platform>windows_intelx86</platform>
<plan_class>cuda23</plan_class>
<avg_ncpus>0.040000</avg_ncpus>
<max_ncpus>0.040000</max_ncpus>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
<file_ref>
<file_name>Lunatics_x40_Win32_Cuda40.exe.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart32_40_17.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft32_40_17.dll</file_name>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>608</version_num>
<platform>windows_intelx86</platform>
<plan_class>cuda</plan_class>
<avg_ncpus>0.040000</avg_ncpus>
<max_ncpus>0.040000</max_ncpus>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
<file_ref>
<file_name>Lunatics_x40_Win32_Cuda40.exe.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart32_40_17.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft32_40_17.dll</file_name>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>610</version_num>
<platform>windows_x86_64</platform>
<plan_class>cuda_fermi</plan_class>
<avg_ncpus>0.040000</avg_ncpus>
<max_ncpus>0.040000</max_ncpus>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
<file_ref>
<file_name>Lunatics_x40_Win32_Cuda40.exe.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart32_40_17.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft32_40_17.dll</file_name>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>609</version_num>
<platform>windows_x86_64</platform>
<plan_class>cuda23</plan_class>
<avg_ncpus>0.040000</avg_ncpus>
<max_ncpus>0.040000</max_ncpus>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
<file_ref>
<file_name>Lunatics_x40_Win32_Cuda40.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart32_40_17.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft32_40_17.dll</file_name>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>608</version_num>
<platform>windows_x86_64</platform>
<plan_class>cuda</plan_class>
<avg_ncpus>0.040000</avg_ncpus>
<max_ncpus>0.040000</max_ncpus>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
<file_ref>
<file_name>Lunatics_x40_Win32_Cuda40.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart32_40_17.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft32_40_17.dll</file_name>
</file_ref>
</app_version>
</app_info>


Alliance Francophone
ID: 1263422 · Report as offensive
Speedy
Volunteer tester
Avatar

Send message
Joined: 26 Jun 04
Posts: 1639
Credit: 12,921,799
RAC: 89
New Zealand
Message 1263505 - Posted: 22 Jul 2012, 21:59:06 UTC - in response to Message 1263422.  


<app_info>
<app>
<name>astropulse_v6</name>
</app>
<file_info>
<name>AP6_win_x86_SSE2_OpenCL_NV_r1316.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>astropulse_v6</app_name>
<version_num>604</version_num>
<avg_ncpus>0.04</avg_ncpus>
<max_ncpus>0.2</max_ncpus>
<platform>windows_intelx86</platform>
<plan_class>cuda</plan_class>
<cmdline>-unroll 10 -ffa_block 6144 -ffa_block_fetch 1536 -sbs 256</cmdline>
<coproc>
<type>CUDA</type>
<count>0.5</count>
</coproc>
<file_ref>
<file_name>AP6_win_x86_SSE2_OpenCL_NV_r1316.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app_version>
<app_name>astropulse_v6</app_name>
<version_num>604</version_num>
<avg_ncpus>0.04</avg_ncpus>
<max_ncpus>0.2</max_ncpus>
<platform>windows_x86_64</platform>
<plan_class>cuda</plan_class>
<cmdline>-instances_per_device 1 -unroll 10 -ffa_block 6144 -ffa_block_fetch 1536 -sbs 256</cmdline>
<coproc>
<type>CUDA</type>
<count>0.5</count>
</coproc>
<file_ref>
<file_name>AP6_win_x86_SSE2_OpenCL_NV_r1316.exe</file_name>
<main_program/>
</file_ref>
</app_version>

<app>
<name>setiathome_enhanced</name>
</app>
<file_info>
<name>AK_v8b2_win_x64_SSE41.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>603</version_num>
<platform>windows_intelx86</platform>
<file_ref>
<file_name>AK_v8b2_win_x64_SSE41.exe</file_name>
<main_program/>
</file_ref>
</app_version>

I think the reason why you aren't able to process any AP work on your GPU is because you have the AP NV app section in 3 times try deleting the section in your app info i put in Red

ID: 1263505 · Report as offensive
Profile [AF>EDLS] Polynesia
Volunteer tester
Avatar

Send message
Joined: 1 Apr 09
Posts: 54
Credit: 5,361,172
RAC: 0
France
Message 1263511 - Posted: 22 Jul 2012, 22:52:30 UTC

A heck I had not noticed I had 2 times this part ...


Alliance Francophone
ID: 1263511 · Report as offensive
Claggy
Volunteer tester

Send message
Joined: 5 Jul 99
Posts: 4654
Credit: 47,537,079
RAC: 4
United Kingdom
Message 1263519 - Posted: 22 Jul 2012, 23:33:18 UTC - in response to Message 1263505.  
Last modified: 22 Jul 2012, 23:34:58 UTC

I think the reason why you aren't able to process any AP work on your GPU is because you have the AP NV app section in 3 times try deleting the section in your app info i put in Red

It doesn't matter, the app_versions sections are different, one having the windows_intelx86 platform and the other the windows_x86_64 platform,
But he should modify the cmd line parameters so they are the same.

What i find strange is why is he running a x40 Cuda4 app? surely he should have upgraded to x41g when it became available.

Claggy
ID: 1263519 · Report as offensive
JohnDK Crowdfunding Project Donor*Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 28 May 00
Posts: 1222
Credit: 451,243,443
RAC: 1,127
Denmark
Message 1263719 - Posted: 23 Jul 2012, 15:12:17 UTC

I've noticed that some WUs are getting low credits, is there a problem somewhere? It's not happening only with the latest app, it also happened with previous versions, not sure when I first noticed it.

http://setiathome.berkeley.edu/results.php?hostid=6442255&offset=0&show_names=0&state=3&appid=12
ID: 1263719 · Report as offensive
Previous · 1 . . . 5 · 6 · 7 · 8 · 9 · 10 · 11 · Next

Message boards : Number crunching : New AstroPulse for GPU ( ATi & NV) released (r1316)


 
©2024 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.