<div dir="ltr"><div class="gmail_extra">Hi Jacob and David,<br><br></div><div class="gmail_extra">Thanks to your suggestion:<br><br>'Second: I am not at a GPU expert, but when I was testing the develop<br>
> branch in preparation for the 8.1 release, I ran in to the same<br>
> problem, using the same CUDA compiler (the current release, 9.1). I<br>
> did some googling and found reports about similar/identical errors,<br>
> and it looks like this is due to an internal CUDA compiler bug: nvcc<br>
> crashes with a segfault when trying to compile our code. Compilers<br>
> really shouldn't crash like that, no matter how<br>
> bad/evil/weird/outdated our code might be. For me the error went away<br>
> if I add "-G" to the list of compiler options (edit the CMakeLists.txt<br>
> file, insert "-G;" in the option string in the 'SET(CUDA_NVCC_FLAGS<br>
> ...' line). However, that is a pretty ugly blunt axe solution. It<br>
> selects "debug" mode, which makes it *much* slower, which is very<br>
> probably very unwelcome. Maybe this compiler bug will be fixed in the<br>
> next CUDA release? You could maybe also try downgrading to an older<br>
> CUDA version, maybe that makes the crash go away without speed<br>
> penalty. I did not yet find time to try this myself, unfortunately.'<br><br></div><div class="gmail_extra">I was able to install Gate 8.0 with GPU support! (Cuda 9.0)<br><br></div><div class="gmail_extra">Thank you!<br><br></div><div class="gmail_extra">Pedro<br></div></div>