I never understood the benefit of this. You need to go backwards at some point regardless.
Martin
- 0 Posts
- 7 Comments
Martin@feddit.nuto Linux@programming.dev•New to Linux? 4 things to focus on before you switch1·2 months agoWhy does everything be number lists?
Martin@feddit.nuto Programming@programming.dev•Can anybody explain why CUDA and Rocm are necessary and why OpenCL isn't the solution?3·2 months agoCUDA 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 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.
That makes a lot of sense actually.