cmpfeil
cmpfeil
Thanks for the quick reply! Following your input I can report the following: * The explicit kernel version does not work either, although instead of ERROR#2(a-e) there is only one...
Thanks for all the input. Update from my side: With only a slight modification, I got the CUDA explicit kernel version of axpy running (without `GTENSOR_USE_THRUST`). ``` #include #include #include...
> Making GT_LAMBDA device only is a major problem, it would break all host launches. Not obvious to me how to workaround that limitation - I wonder if there is...
Sure - I will follow the steps you suggested and open a draft PR. Got 1-2 busy weeks ahead, but after that I'm all on it.
Due to holidays everything took a bit longer than expected, but now it's there: draft PR #276.
Would be eager to see this; in particular also specializations `complex` and `complex`. Are there any plans on whether or when this might be available?