mschuetz
Joined 11 years ago
Karma
1,461
Submissions
489
Member since
Sep 13
Joined 11 years ago
Yes, I also prefer doing it that way, but in Cuda with the driver API. Allows you to handle kernels like shaders, including editing and hot-reloading at runtime.
The reason I'm sticking with CUDA is because it's by far the most convenient API to use, without nonsense like 50-liners to alloc memory or the need to manage descriptors, bindings, queue families, etc.
Wildly exaggerated. I use github almost daily and can't remember when the last downtime was.