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 . . . 8 · 9 · 10 · 11

AuthorMessage
Profile Paul D Harris
Volunteer tester

Send message
Joined: 1 Dec 99
Posts: 1122
Credit: 33,600,005
RAC: 0
United States
Message 1271238 - Posted: 13 Aug 2012, 19:29:40 UTC - in response to Message 1271188.  

Only one typo that i can see, just remove the -ve sign from the last <cmdline>-</cmdline> entry,

Claggy

Thanks Claggy
You mean this <cmdline>-</cmdline> to this <cmdline></cmdline>
ID: 1271238 · Report as offensive
Claggy
Volunteer tester

Send message
Joined: 5 Jul 99
Posts: 4654
Credit: 47,537,079
RAC: 4
United Kingdom
Message 1271247 - Posted: 13 Aug 2012, 20:04:02 UTC - in response to Message 1271238.  

Only one typo that i can see, just remove the -ve sign from the last <cmdline>-</cmdline> entry,

Claggy

Thanks Claggy
You mean this <cmdline>-</cmdline> to this <cmdline></cmdline>

Yep,

Claggy
ID: 1271247 · 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 1271250 - Posted: 13 Aug 2012, 20:08:53 UTC - in response to Message 1271238.  
Last modified: 13 Aug 2012, 20:10:18 UTC

Only one typo that i can see, just remove the -ve sign from the last <cmdline>-</cmdline> entry,

Claggy

Thanks Claggy
You mean this <cmdline>-</cmdline> to this <cmdline></cmdline>


But I see you're using 0.5GPU so you've to use atleast 1 cmd_line setting,
1 instance_per_device, IIRC.......

And I wouldn't stick to defaults, depending of the GPU you're using.
Use an unroll factor smaller as the # of CU's in your GPU, not the default 2,
but 10 to # of CU's.
Ffa_block can also be larger then 4096, double it and use ffa_block_fetch 4096,
for a start.
Or you can do 1 instance per device.
ID: 1271250 · Report as offensive
Claggy
Volunteer tester

Send message
Joined: 5 Jul 99
Posts: 4654
Credit: 47,537,079
RAC: 4
United Kingdom
Message 1271252 - Posted: 13 Aug 2012, 20:18:55 UTC - in response to Message 1271250.  

Only one typo that i can see, just remove the -ve sign from the last <cmdline>-</cmdline> entry,

Claggy

Thanks Claggy
You mean this <cmdline>-</cmdline> to this <cmdline></cmdline>


But I see you're using 0.5GPU so you've to use atleast 1 cmd_line setting,
1 instance_per_device, IIRC.......


an instances_per_device parameter is no longer required, from the release notes:

-instances_per_device param still supported but not required for using multiple instances of app.
One should set <count> tag in app_info to get multiple instances running.


AP6 for NV & ATi GPUs r1316 released

Claggy
ID: 1271252 · Report as offensive
Profile Paul D Harris
Volunteer tester

Send message
Joined: 1 Dec 99
Posts: 1122
Credit: 33,600,005
RAC: 0
United States
Message 1271355 - Posted: 14 Aug 2012, 3:20:15 UTC

So what should my app_info.xml look like?
Here is my graphics.

Graphics
AL2016W (1680x1050@59Hz)
767MB GeForce GTX 460 (nVidia) 75 °C
767MB GeForce GTX 460 (nVidia) 76 °C
ForceWare version 304.48
SLI Disabled

MY 3 WU errored out how to fix?

Workunit 1032412105 http://setiathome.berkeley.edu/workunit.php?wuid=1032412105
Exit status -1073741515 (0xffffffffc0000135) Unknown error number

Workunit 1032343887 http://setiathome.berkeley.edu/workunit.php?wuid=1032343887
Exit status -1073741515 (0xffffffffc0000135) Unknown error number

Workunit 1032246042 http://setiathome.berkeley.edu/workunit.php?wuid=1032246042
Exit status -1073741515 (0xffffffffc0000135) Unknown error number

ID: 1271355 · Report as offensive
Speedy
Volunteer tester
Avatar

Send message
Joined: 26 Jun 04
Posts: 1639
Credit: 12,921,799
RAC: 89
New Zealand
Message 1271359 - Posted: 14 Aug 2012, 3:44:11 UTC - in response to Message 1271355.  

So what should my app_info.xml look like?
Here is my graphics.

Paul the following works fine for my GTX 470

<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>601</version_num>
<avg_ncpus>0.04</avg_ncpus>
<max_ncpus>0.2</max_ncpus>
<platform>windows_intelx86</platform>
<plan_class>cuda_fermi</plan_class>
<cmdline>-instances_per_device 1 -unroll 10 -ffa_block 6144 -ffa_block_fetch 1536 -sbs 256</cmdline>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
<file_ref>
<file_name>AP6_win_x86_SSE2_OpenCL_NV_r1316.exe</file_name>
<main_program/>
</file_ref>
</app_version>

Make sure <name>AP6_win_x86_SSE2_OpenCL_NV_r1316.exe</name> & <file_name>AP6_win_x86_SSE2_OpenCL_NV_r1316.exe</file_name> lines are the same as the files in your setiathome.berkeley.edu folder
ID: 1271359 · Report as offensive
Previous · 1 . . . 8 · 9 · 10 · 11

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.