Martin

CUDA can (depending on circumstances) give slightly better performance than OpenCL. So if you know that your target hosts will have Nvidia GPUs ( for example ML in your own data centers) that might be beneficial.

OpenCL will run on multiple platforms so if you don’t know the target hosts (for example consumer hardware for gaming) this makes life easier for the developer.

The frameworks and libraries around the different specs differ, so if there is a library that is useful for your use case, that will effect your decision to pick one over the other

I hate articles that are just a tease for a YouTube video.

I have a great boss that knows that whatever I decide to do is probably the right priority. As long as our users are happy she is happy.

Is it quicker to fix it then to get the issue triaged? Just fix it and move on.