There was a problem with translating --device to -d and parsing it inside the app.
I think it is fixed in 1.02 release because I've just seen a first completed and validated task.

For me the GPU app still only works on one GPU, allowing two WU's to run only runs them both on the same GPU which leaves any other GPU's doing nothing. For me at least nothing has changed :(

For sh#%s & giggles I even tried to changing the command to -d 1 in the job_160.xml file and another time tried pausing the WU and changing it in job.xml file in the slot directory but with the same result. As far as boinc is aware all is working as it should be with a WU running on each device but in reality there both being crunched by the same GPU.

Will the new build of enigma-cuda.exe, be implemented on the enigma server, or is there a cheat sheet for dummies ?

I'll update the apps on the server later today. GPU workunits generator will be stopped for around ~1h right before update.

A new build of enigma-cuda.exe is available. This build:

1) does not use AVX or SSE instructions (the speed is the same);
2) has a new command line option, -d <cuda device number> (0-based indexing).

The source and new binaries are here: https://github.com/VE3NEA/enigma-cuda