If the app_config is not working try this here:

<exclude_gpu> <url>http://srbase.my-firewall.org/sr5/</url> <device_num>1</device_num> <type>NVIDIA|ATI</type> <app>GPU72</app> </exclude_gpu>

change the type what you have in your PC and put this code in the option section of cc_config

On one of my systems I have a HD7950 (Dev 0) and a Vega 64 (Dev 1). If I include the following in the options section of my cc_config.xml file:

Well, then that stinks because I don't want it to run on my 1st GPU (7950) as it lags big time then. That is why I have the Vega 64 as my 2nd GPU so it can run full boar on it without any concerns of using that PC for other things.

This is the only project I've ran that has ever done this. Never had an issue with any other GPU project and telling it what GPU to run on or not to run on.

EDIT: Also, I don't think anyone here who says they are running 1 task/WU on both GPUs actually are. I have yet to see it happen running on NVIDIA like it was state to. If it's always running on 1st device, then how can it possible run simultaneously on the 2nd device as well for the same WU?

In case it helps now, or in the future !

I believe BOINC numbers GPUs in the order it receives information about them from CAL, CUDA or OpenCL drivers. (This from the BOINC forum a couple of years ago.)

I do not know if the mfakto/mfaktc when given a device number is then using the BOINC GPU numbering or a number assigned by the OS when it enumerates the GPUs.

Just putting it out there :)

In case it helps now, or in the future !

I believe BOINC numbers GPUs in the order it receives information about them from CAL, CUDA or OpenCL drivers. (This from the BOINC forum a couple of years ago.)

I do not know if the mfakto/mfaktc when given a device number is then using the BOINC GPU numbering or a number assigned by the OS when it enumerates the GPUs.

Just putting it out there :)

<app_config> <app> <name>GPU72</name> <project_max_concurrent>1</project_max_concurrent> <gpu_versions> <gpu_usage>1</gpu_usage> <cpu_usage>0.01</cpu_usage> </gpu_versions> </app> </app_config>

Is this working for Multi-GPU? If not I will remove it and will only use the cc_config solution, next step is the opencl error thing.

<app_config> <app> <name>GPU72</name> <project_max_concurrent>1</project_max_concurrent> <gpu_versions> <gpu_usage>1</gpu_usage> <cpu_usage>0.01</cpu_usage> </gpu_versions> </app> </app_config>

Can anyone post a app_config.xml file that works successfully with a AMD GPU? (Ubuntu, Intel CPU).

I managed to get mfakto running standalone with:

<app_config>
<app>
<name>GPU72</name>
<max_concurrent>1</max_concurrent>
</app>
<app_version>
<app_name>GPU72</app_name>
<plan_class>opencl_ati_101</plan_class>
<cmdline>-d 1</cmdline>
</app_version>
</app_config>

As long as you only have 1 AMD GPU, then:

<app_config>
<app>
<name>GPU72</name>
<max_concurrent>1</max_concurrent>
<gpu_versions>
<gpu_usage>1</gpu_usage>
<cpu_usage>0.1</cpu_usage>
</gpu_versions>
</app>
</app_config>

Can you also try with
-d 0
-d 10
-d 11

test with wrapper app, change the job....xml to job.xml and start the wrapper.

On one of my systems I have a HD7950 (Dev 0) and a Vega 64 (Dev 1). If I include the following in the options section of my cc_config.xml file:

<exclude_gpu> <url>http://srbase.my-firewall.org/sr5/</url> <type>ATI</type> <device_num>0</device_num> <app>GPU72</app> </exclude_gpu>

That should tell it to ignore my 7950 (Dev 0) and run on my Vega 64. However, that is not the case. It still runs on the 2st device no matter what. The status column in BOINC manager says it's running on Device 1 like the cc_config.xml tells it to, but according to GPU utilization in both GPU-Z and HWiNFO it is still running on 1st device.

EDIT: So by default nature of the app, it will always use the 1st device no matter what it is told in cc_config or app_config it seems? At least on AMD GPUs. NVIDIA is a different story I think?

On one of my systems I have a HD7950 (Dev 0) and a Vega 64 (Dev 1). If I include the following in the options section of my cc_config.xml file:

<exclude_gpu> <url>http://srbase.my-firewall.org/sr5/</url> <type>ATI</type> <device_num>0</device_num> <app>GPU72</app> </exclude_gpu>

That should tell it to ignore my 7950 (Dev 0) and run on my Vega 64. However, that is not the case. It still runs on the 2st device no matter what. The status column in BOINC manager says it's running on Device 1 like the cc_config.xml tells it to, but according to GPU utilization in both GPU-Z and HWiNFO it is still running on 1st device.

EDIT: So by default nature of the app, it will always use the 1st device no matter what it is told in cc_config or app_config it seems? At least on AMD GPUs. NVIDIA is a different story I think?

I'm successfully using this in my cc_config to exclude the second GPU in all of my two-GPU systems, so that one doesn't go to waste when running GPU72. I am running another project on the second GPU in those rigs.