ive been running mw seperation wu on my gpus. i saw this post and was hoping to get n-body simulations working for cpu as well. i took that app_info.xml example and modified with the files i have locally for those wu. this is my app_info.xml:

<app_info>
<app>
<name>milkyway</name>
</app>
<file_info>
<name>milkyway_separation_1.02_windows_x86_64__opencl_amd_ati.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>milkyway</app_name>
<version_num>102</version_num>
<flops>1.0e11</flops>
<avg_ncpus>0.05</avg_ncpus>
<max_ncpus>1</max_ncpus>
<plan_class>ati14ati</plan_class>
<coproc>
<type>ATI</type>
<count>0.5</count>
</coproc>
<cmdline>--gpu-target-frequency 10 --gpu-disable-checkpointing</cmdline>
<file_ref>
<file_name>milkyway_separation_1.02_windows_x86_64__opencl_amd_ati.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app>
<name>milkyway_nbody</name>
<user_friendly_name>MilkyWay@Home nbody Simulation</user_friendly_name>
</app>
<file_info>
<name>milkyway_nbody_0.84_windows_x86_64__mt.exe</name>
<executable/>
</file_info>
<file_info>
<name>libgomp_64-1_nbody_0.84.dll</name>
<executable/>
</file_info>
<file_info>
<name>pthreadGC2_64_nbody_0.84.dll</name>
<executable/>
</file_info>
<app_version>
<app_name>milkyway_nbody</app_name>
<version_num>84</version_num>
<plan_class>mt</plan_class>
<avg_ncpus>4</avg_ncpus>
<max_ncpus>4</max_ncpus>
<cmdline>--nthreads=4</cmdline>
<file_ref>
<file_name>milkyway_nbody_0.84_windows_x86_64__mt.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>libgomp_64-1_nbody_0.84.dll</file_name>
</file_ref>
<file_ref>
<file_name>pthreadGC2_64_nbody_0.84.dll</file_name>
</file_ref>
</app_version>
</app_info>

the gpu still works fine but i all the n-body wu fail on this host

heres one error as an example:

<core_client_version>7.0.25</core_client_version>
<![CDATA[
<message>
- exit code -1073741515 (0xc0000135)
</message>
]]>

for this task.

i got a total of 46 errors for n-body wu. they die immediately so i stopped work for those and will continue crunching gpu on that machine until i can figure this out.

can anyone tell me what may be wrong here? any information would be appreciated.

thanks.

rob

Been a while since I was running nbody, but I think I remember you need to change

<file_ref>
<file_name>libgomp_64-1_nbody_0.84.dll</file_name>
</file_ref>
<file_ref>
<file_name>pthreadGC2_64_nbody_0.84.dll</file_name>
</file_ref>

to something like this

<file_ref>
<file_name>libgomp_64-1_nbody_0.84.dll</file_name>
<open_name>libgomp_64-1.dll</open_name>
</file_ref>
<file_ref>
<file_name>pthreadGC2_64_nbody_0.84.dll</file_name>
<open_name>pthreadGC2_64.dll</open_name>
</file_ref>

This opens the dlls under their std name and you don't have to rename them in your directory (and do it again with every new version).

Been a while since I was running nbody, but I think I remember you need to change

<file_ref>
<file_name>libgomp_64-1_nbody_0.84.dll</file_name>
</file_ref>
<file_ref>
<file_name>pthreadGC2_64_nbody_0.84.dll</file_name>
</file_ref>

to something like this

<file_ref>
<file_name>libgomp_64-1_nbody_0.84.dll</file_name>
<open_name>libgomp_64-1.dll</open_name>
</file_ref>
<file_ref>
<file_name>pthreadGC2_64_nbody_0.84.dll</file_name>
<open_name>pthreadGC2_64.dll</open_name>
</file_ref>

This opens the dlls under their std name and you don't have to rename them in your directory (and do it again with every new version).

thanks for the idea. i tried to update the app_info.xml file with the <open_name> tag as suggested. it still errored out the wu. afterwards, i changed the filename of those dlls and it all works now. i dont understand why the actual dll filename would cause issues but now it all works so thats good.

i guess ill have to remember to update the filename for those dlls in the future. although your suggestion was intended to allow me to avoid this, it wouldnt work on this particular machine.

thanks for the help.

rob