Does anybody have a working app_info.xml for GPU cuda WU's?

Anthony.

---

The longer I live, the more reasons I develop for wanting to die.

See my post in the other thread.

---

Hello everyone......................

I got tired of not receiving work for Seti so I joined up here. So far I just have the stock installation running. Is there a way to run more than one CUDA task on my NVIDIA GPU?

Hope to enjoy a steady RAC here, not like it is at SETI.

Thanks

[edit] checked GPU and it's loaded to 99% so I would guess running 2 is pointless.

---

Boinc...Boinc...Boinc...Boinc

It's not pointless!

The MW WU's do some CPU Work at the end. You can mask this time when you are doing 2 WU's parallel (with a little time shift).

During one WU is doing the end Work on CPU, the other WU runn's 100 % on the GPU. -> You get better Performance .
But Note if you are crunching on CPU also leave one Core/GPU free for MW.

I do my work only on ATI's (they are bette in DP then Nvidias)so I have no app_info.xml, but search on the forum.
regards

Franz


[edit]
I've found something:

- <app_info>
- <app>
<name>milkyway</name>
</app>
- <file_info>
<name>milkyway_separation_0.82_windows_x86_64__cuda_opencl.exe</name>
<executable />
</file_info>
- <app_version>
<app_name>milkyway</app_name>
<version_num>82</version_num>
<flops>1.0e11</flops>
<avg_ncpus>0.05</avg_ncpus>
<max_ncpus>1</max_ncpus>
<plan_class>cuda</plan_class>
- <coproc>
<type>CUDA</type>
<count>0.5</count>
</coproc>
<cmdline />
- <file_ref>
<file_name>milkyway_separation_0.82_windows_x86_64__cuda_opencl.exe</file_name>
<main_program />
</file_ref>
</app_version>
</app_info>

The <count>0.5</count>
Tag was changed from 1 to 0.5 wich makes 2 WU's run
In the <name> & <file_name> Tag you have to insert your stock_app (32 or 64 bit)

HTH